case study a teaching method

• Columbia University in the City of New York
• Office of Teaching, Learning, and Innovation
• University Policies
• Columbia Online
• Academic Calendar
• Resources and Technology
• Resources and Guides

Case Method Teaching and Learning

What is the case method? How can the case method be used to engage learners? What are some strategies for getting started? This guide helps instructors answer these questions by providing an overview of the case method while highlighting learner-centered and digitally-enhanced approaches to teaching with the case method. The guide also offers tips to instructors as they get started with the case method and additional references and resources.

On this page:

What is case method teaching.

• Case Method at Columbia

Why use the Case Method?

Case method teaching approaches, how do i get started.

• Additional Resources

The CTL is here to help!

For support with implementing a case method approach in your course, email [email protected] to schedule your 1-1 consultation .

Cite this resource: Columbia Center for Teaching and Learning (2019). Case Method Teaching and Learning. Columbia University. Retrieved from [today’s date] from https://ctl.columbia.edu/resources-and-technology/resources/case-method/  

Case method 1 teaching is an active form of instruction that focuses on a case and involves students learning by doing 2 3 . Cases are real or invented stories 4  that include “an educational message” or recount events, problems, dilemmas, theoretical or conceptual issue that requires analysis and/or decision-making.

Case-based teaching simulates real world situations and asks students to actively grapple with complex problems 5 6 This method of instruction is used across disciplines to promote learning, and is common in law, business, medicine, among other fields. See Table 1 below for a few types of cases and the learning they promote.

Table 1: Types of cases and the learning they promote.

For a more complete list, see Case Types & Teaching Methods: A Classification Scheme from the National Center for Case Study Teaching in Science.

Back to Top

Case Method Teaching and Learning at Columbia

The case method is actively used in classrooms across Columbia, at the Morningside campus in the School of International and Public Affairs (SIPA), the School of Business, Arts and Sciences, among others, and at Columbia University Irving Medical campus.

Faculty Spotlight:

Professor Mary Ann Price on Using Case Study Method to Place Pre-Med Students in Real-Life Scenarios

Read more  

Professor De Pinho on Using the Case Method in the Mailman Core

Case method teaching has been found to improve student learning, to increase students’ perception of learning gains, and to meet learning objectives 8 9 . Faculty have noted the instructional benefits of cases including greater student engagement in their learning 10 , deeper student understanding of concepts, stronger critical thinking skills, and an ability to make connections across content areas and view an issue from multiple perspectives 11 . 

Through case-based learning, students are the ones asking questions about the case, doing the problem-solving, interacting with and learning from their peers, “unpacking” the case, analyzing the case, and summarizing the case. They learn how to work with limited information and ambiguity, think in professional or disciplinary ways, and ask themselves “what would I do if I were in this specific situation?”

The case method bridges theory to practice, and promotes the development of skills including: communication, active listening, critical thinking, decision-making, and metacognitive skills 12 , as students apply course content knowledge, reflect on what they know and their approach to analyzing, and make sense of a case. 

Though the case method has historical roots as an instructor-centered approach that uses the Socratic dialogue and cold-calling, it is possible to take a more learner-centered approach in which students take on roles and tasks traditionally left to the instructor. 

Cases are often used as “vehicles for classroom discussion” 13 . Students should be encouraged to take ownership of their learning from a case. Discussion-based approaches engage students in thinking and communicating about a case. Instructors can set up a case activity in which students are the ones doing the work of “asking questions, summarizing content, generating hypotheses, proposing theories, or offering critical analyses” 14 . 

The role of the instructor is to share a case or ask students to share or create a case to use in class, set expectations, provide instructions, and assign students roles in the discussion. Student roles in a case discussion can include: 

• discussion “starters” get the conversation started with a question or posing the questions that their peers came up with; 
• facilitators listen actively, validate the contributions of peers, ask follow-up questions, draw connections, refocus the conversation as needed; 
• recorders take-notes of the main points of the discussion, record on the board, upload to CourseWorks, or type and project on the screen; and 
• discussion “wrappers” lead a summary of the main points of the discussion. 

Prior to the case discussion, instructors can model case analysis and the types of questions students should ask, co-create discussion guidelines with students, and ask for students to submit discussion questions. During the discussion, the instructor can keep time, intervene as necessary (however the students should be doing the talking), and pause the discussion for a debrief and to ask students to reflect on what and how they learned from the case activity. 

Note: case discussions can be enhanced using technology. Live discussions can occur via video-conferencing (e.g., using Zoom ) or asynchronous discussions can occur using the Discussions tool in CourseWorks (Canvas) .

Table 2 includes a few interactive case method approaches. Regardless of the approach selected, it is important to create a learning environment in which students feel comfortable participating in a case activity and learning from one another. See below for tips on supporting student in how to learn from a case in the “getting started” section and how to create a supportive learning environment in the Guide for Inclusive Teaching at Columbia . 

Table 2. Strategies for Engaging Students in Case-Based Learning

Approaches to case teaching should be informed by course learning objectives, and can be adapted for small, large, hybrid, and online classes. Instructional technology can be used in various ways to deliver, facilitate, and assess the case method. For instance, an online module can be created in CourseWorks (Canvas) to structure the delivery of the case, allow students to work at their own pace, engage all learners, even those reluctant to speak up in class, and assess understanding of a case and student learning. Modules can include text, embedded media (e.g., using Panopto or Mediathread ) curated by the instructor, online discussion, and assessments. Students can be asked to read a case and/or watch a short video, respond to quiz questions and receive immediate feedback, post questions to a discussion, and share resources. 

For more information about options for incorporating educational technology to your course, please contact your Learning Designer .

To ensure that students are learning from the case approach, ask them to pause and reflect on what and how they learned from the case. Time to reflect  builds your students’ metacognition, and when these reflections are collected they provides you with insights about the effectiveness of your approach in promoting student learning.

Well designed case-based learning experiences: 1) motivate student involvement, 2) have students doing the work, 3) help students develop knowledge and skills, and 4) have students learning from each other.  

Designing a case-based learning experience should center around the learning objectives for a course. The following points focus on intentional design. 

Identify learning objectives, determine scope, and anticipate challenges. 

• Why use the case method in your course? How will it promote student learning differently than other approaches? 
• What are the learning objectives that need to be met by the case method? What knowledge should students apply and skills should they practice? 
• What is the scope of the case? (a brief activity in a single class session to a semester-long case-based course; if new to case method, start small with a single case). 
• What challenges do you anticipate (e.g., student preparation and prior experiences with case learning, discomfort with discussion, peer-to-peer learning, managing discussion) and how will you plan for these in your design? 
• If you are asking students to use transferable skills for the case method (e.g., teamwork, digital literacy) make them explicit. 

Determine how you will know if the learning objectives were met and develop a plan for evaluating the effectiveness of the case method to inform future case teaching. 

• What assessments and criteria will you use to evaluate student work or participation in case discussion? 
• How will you evaluate the effectiveness of the case method? What feedback will you collect from students? 
• How might you leverage technology for assessment purposes? For example, could you quiz students about the case online before class, accept assignment submissions online, use audience response systems (e.g., PollEverywhere) for formative assessment during class? 

Select an existing case, create your own, or encourage students to bring course-relevant cases, and prepare for its delivery

• Where will the case method fit into the course learning sequence? 
• Is the case at the appropriate level of complexity? Is it inclusive, culturally relevant, and relatable to students? 
• What materials and preparation will be needed to present the case to students? (e.g., readings, audiovisual materials, set up a module in CourseWorks). 

Plan for the case discussion and an active role for students

• What will your role be in facilitating case-based learning? How will you model case analysis for your students? (e.g., present a short case and demo your approach and the process of case learning) (Davis, 2009). 
• What discussion guidelines will you use that include your students’ input? 
• How will you encourage students to ask and answer questions, summarize their work, take notes, and debrief the case? 
• If students will be working in groups, how will groups form? What size will the groups be? What instructions will they be given? How will you ensure that everyone participates? What will they need to submit? Can technology be leveraged for any of these areas? 
• Have you considered students of varied cognitive and physical abilities and how they might participate in the activities/discussions, including those that involve technology? 

Student preparation and expectations

• How will you communicate about the case method approach to your students? When will you articulate the purpose of case-based learning and expectations of student engagement? What information about case-based learning and expectations will be included in the syllabus?
• What preparation and/or assignment(s) will students complete in order to learn from the case? (e.g., read the case prior to class, watch a case video prior to class, post to a CourseWorks discussion, submit a brief memo, complete a short writing assignment to check students’ understanding of a case, take on a specific role, prepare to present a critique during in-class discussion).

Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. 

Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846

Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. 

Garvin, D.A. (2003). Making the Case: Professional Education for the world of practice. Harvard Magazine. September-October 2003, Volume 106, Number 1, 56-107.

Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. 

Golich, V.L.; Boyer, M; Franko, P.; and Lamy, S. (2000). The ABCs of Case Teaching. Pew Case Studies in International Affairs. Institute for the Study of Diplomacy. 

Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. 

Herreid, C.F. (2011). Case Study Teaching. New Directions for Teaching and Learning. No. 128, Winder 2011, 31 – 40. 

Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. 

Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar  

Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. 

Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. 

Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002

Schiano, B. and Andersen, E. (2017). Teaching with Cases Online . Harvard Business Publishing. 

Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. 

Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). 

Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass.

Additional resources 

Teaching with Cases , Harvard Kennedy School of Government. 

Features “what is a teaching case?” video that defines a teaching case, and provides documents to help students prepare for case learning, Common case teaching challenges and solutions, tips for teaching with cases. 

Promoting excellence and innovation in case method teaching: Teaching by the Case Method , Christensen Center for Teaching & Learning. Harvard Business School. 

National Center for Case Study Teaching in Science . University of Buffalo. 

A collection of peer-reviewed STEM cases to teach scientific concepts and content, promote process skills and critical thinking. The Center welcomes case submissions. Case classification scheme of case types and teaching methods:

• Different types of cases: analysis case, dilemma/decision case, directed case, interrupted case, clicker case, a flipped case, a laboratory case. 
• Different types of teaching methods: problem-based learning, discussion, debate, intimate debate, public hearing, trial, jigsaw, role-play. 

Columbia Resources

Resources available to support your use of case method: The University hosts a number of case collections including: the Case Consortium (a collection of free cases in the fields of journalism, public policy, public health, and other disciplines that include teaching and learning resources; SIPA’s Picker Case Collection (audiovisual case studies on public sector innovation, filmed around the world and involving SIPA student teams in producing the cases); and Columbia Business School CaseWorks , which develops teaching cases and materials for use in Columbia Business School classrooms.

Center for Teaching and Learning

The Center for Teaching and Learning (CTL) offers a variety of programs and services for instructors at Columbia. The CTL can provide customized support as you plan to use the case method approach through implementation. Schedule a one-on-one consultation. 

Office of the Provost

The Hybrid Learning Course Redesign grant program from the Office of the Provost provides support for faculty who are developing innovative and technology-enhanced pedagogy and learning strategies in the classroom. In addition to funding, faculty awardees receive support from CTL staff as they redesign, deliver, and evaluate their hybrid courses.

The Start Small! Mini-Grant provides support to faculty who are interested in experimenting with one new pedagogical strategy or tool. Faculty awardees receive funds and CTL support for a one-semester period.

Explore our teaching resources.

• Blended Learning
• Contemplative Pedagogy
• Inclusive Teaching Guide
• FAQ for Teaching Assistants
• Metacognition

CTL resources and technology for you.

• Overview of all CTL Resources and Technology
• The origins of this method can be traced to Harvard University where in 1870 the Law School began using cases to teach students how to think like lawyers using real court decisions. This was followed by the Business School in 1920 (Garvin, 2003). These professional schools recognized that lecture mode of instruction was insufficient to teach critical professional skills, and that active learning would better prepare learners for their professional lives. ↩
• Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. ↩
• Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. ↩
• Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. ↩
• Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. ↩
• Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. ↩
• Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. ↩
• Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846 ↩
• Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. ↩
• Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. ↩
• Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). ↩
• Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002 ↩
• Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass. ↩
• Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar ↩

This website uses cookies to identify users, improve the user experience and requires cookies to work. By continuing to use this website, you consent to Columbia University's use of cookies and similar technologies, in accordance with the Columbia University Website Cookie Notice .

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• J Microbiol Biol Educ
• v.16(1); 2015 May

Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains †

Associated data.

• Appendix 1: Example assessment questions used to assess the effectiveness of case studies at promoting learning
• Appendix 2: Student learning gains were assessed using a modified version of the SALG course evaluation tool

Following years of widespread use in business and medical education, the case study teaching method is becoming an increasingly common teaching strategy in science education. However, the current body of research provides limited evidence that the use of published case studies effectively promotes the fulfillment of specific learning objectives integral to many biology courses. This study tested the hypothesis that case studies are more effective than classroom discussions and textbook reading at promoting learning of key biological concepts, development of written and oral communication skills, and comprehension of the relevance of biological concepts to everyday life. This study also tested the hypothesis that case studies produced by the instructor of a course are more effective at promoting learning than those produced by unaffiliated instructors. Additionally, performance on quantitative learning assessments and student perceptions of learning gains were analyzed to determine whether reported perceptions of learning gains accurately reflect academic performance. The results reported here suggest that case studies, regardless of the source, are significantly more effective than other methods of content delivery at increasing performance on examination questions related to chemical bonds, osmosis and diffusion, mitosis and meiosis, and DNA structure and replication. This finding was positively correlated to increased student perceptions of learning gains associated with oral and written communication skills and the ability to recognize connections between biological concepts and other aspects of life. Based on these findings, case studies should be considered as a preferred method for teaching about a variety of concepts in science courses.

INTRODUCTION

The case study teaching method is a highly adaptable style of teaching that involves problem-based learning and promotes the development of analytical skills ( 8 ). By presenting content in the format of a narrative accompanied by questions and activities that promote group discussion and solving of complex problems, case studies facilitate development of the higher levels of Bloom’s taxonomy of cognitive learning; moving beyond recall of knowledge to analysis, evaluation, and application ( 1 , 9 ). Similarly, case studies facilitate interdisciplinary learning and can be used to highlight connections between specific academic topics and real-world societal issues and applications ( 3 , 9 ). This has been reported to increase student motivation to participate in class activities, which promotes learning and increases performance on assessments ( 7 , 16 , 19 , 23 ). For these reasons, case-based teaching has been widely used in business and medical education for many years ( 4 , 11 , 12 , 14 ). Although case studies were considered a novel method of science education just 20 years ago, the case study teaching method has gained popularity in recent years among an array of scientific disciplines such as biology, chemistry, nursing, and psychology ( 5 – 7 , 9 , 11 , 13 , 15 – 17 , 21 , 22 , 24 ).

Although there is now a substantive and growing body of literature describing how to develop and use case studies in science teaching, current research on the effectiveness of case study teaching at meeting specific learning objectives is of limited scope and depth. Studies have shown that working in groups during completion of case studies significantly improves student perceptions of learning and may increase performance on assessment questions, and that the use of clickers can increase student engagement in case study activities, particularly among non-science majors, women, and freshmen ( 7 , 21 , 22 ). Case study teaching has been shown to improve exam performance in an anatomy and physiology course, increasing the mean score across all exams given in a two-semester sequence from 66% to 73% ( 5 ). Use of case studies was also shown to improve students’ ability to synthesize complex analytical questions about the real-world issues associated with a scientific topic ( 6 ). In a high school chemistry course, it was demonstrated that the case study teaching method produces significant increases in self-reported control of learning, task value, and self-efficacy for learning and performance ( 24 ). This effect on student motivation is important because enhanced motivation for learning activities has been shown to promote student engagement and academic performance ( 19 , 24 ). Additionally, faculty from a number of institutions have reported that using case studies promotes critical thinking, learning, and participation among students, especially in terms of the ability to view an issue from multiple perspectives and to grasp the practical application of core course concepts ( 23 ).

Despite what is known about the effectiveness of case studies in science education, questions remain about the functionality of the case study teaching method at promoting specific learning objectives that are important to many undergraduate biology courses. A recent survey of teachers who use case studies found that the topics most often covered in general biology courses included genetics and heredity, cell structure, cells and energy, chemistry of life, and cell cycle and cancer, suggesting that these topics should be of particular interest in studies that examine the effectiveness of the case study teaching method ( 8 ). However, the existing body of literature lacks direct evidence that the case study method is an effective tool for teaching about this collection of important topics in biology courses. Further, the extent to which case study teaching promotes development of science communication skills and the ability to understand the connections between biological concepts and everyday life has not been examined, yet these are core learning objectives shared by a variety of science courses. Although many instructors have produced case studies for use in their own classrooms, the production of novel case studies is time-consuming and requires skills that not all instructors have perfected. It is therefore important to determine whether case studies published by instructors who are unaffiliated with a particular course can be used effectively and obviate the need for each instructor to develop new case studies for their own courses. The results reported herein indicate that teaching with case studies results in significantly higher performance on examination questions about chemical bonds, osmosis and diffusion, mitosis and meiosis, and DNA structure and replication than that achieved by class discussions and textbook reading for topics of similar complexity. Case studies also increased overall student perceptions of learning gains and perceptions of learning gains specifically related to written and oral communication skills and the ability to grasp connections between scientific topics and their real-world applications. The effectiveness of the case study teaching method at increasing academic performance was not correlated to whether the case study used was authored by the instructor of the course or by an unaffiliated instructor. These findings support increased use of published case studies in the teaching of a variety of biological concepts and learning objectives.

Student population

This study was conducted at Kingsborough Community College, which is part of the City University of New York system, located in Brooklyn, New York. Kingsborough Community College has a diverse population of approximately 19,000 undergraduate students. The student population included in this study was enrolled in the first semester of a two-semester sequence of general (introductory) biology for biology majors during the spring, winter, or summer semester of 2014. A total of 63 students completed the course during this time period; 56 students consented to the inclusion of their data in the study. Of the students included in the study, 23 (41%) were male and 33 (59%) were female; 40 (71%) were registered as college freshmen and 16 (29%) were registered as college sophomores. To normalize participant groups, the same student population pooled from three classes taught by the same instructor was used to assess both experimental and control teaching methods.

Course material

The four biological concepts assessed during this study (chemical bonds, osmosis and diffusion, mitosis and meiosis, and DNA structure and replication) were selected as topics for studying the effectiveness of case study teaching because they were the key concepts addressed by this particular course that were most likely to be taught in a number of other courses, including biology courses for both majors and nonmajors at outside institutions. At the start of this study, relevant existing case studies were freely available from the National Center for Case Study Teaching in Science (NCCSTS) to address mitosis and meiosis and DNA structure and replication, but published case studies that appropriately addressed chemical bonds and osmosis and diffusion were not available. Therefore, original case studies that addressed the latter two topics were produced as part of this study, and case studies produced by unaffiliated instructors and published by the NCCSTS were used to address the former two topics. By the conclusion of this study, all four case studies had been peer-reviewed and accepted for publication by the NCCSTS ( http://sciencecases.lib.buffalo.edu/cs/ ). Four of the remaining core topics covered in this course (macromolecules, photosynthesis, genetic inheritance, and translation) were selected as control lessons to provide control assessment data.

To minimize extraneous variation, control topics and assessments were carefully matched in complexity, format, and number with case studies, and an equal amount of class time was allocated for each case study and the corresponding control lesson. Instruction related to control lessons was delivered using minimal slide-based lectures, with emphasis on textbook reading assignments accompanied by worksheets completed by students in and out of the classroom, and small and large group discussion of key points. Completion of activities and discussion related to all case studies and control topics that were analyzed was conducted in the classroom, with the exception of the take-home portion of the osmosis and diffusion case study.

Data collection and analysis

This study was performed in accordance with a protocol approved by the Kingsborough Community College Human Research Protection Program and the Institutional Review Board (IRB) of the City University of New York (CUNY IRB reference 539938-1; KCC IRB application #: KCC 13-12-126-0138). Assessment scores were collected from regularly scheduled course examinations. For each case study, control questions were included on the same examination that were similar in number, format, point value, and difficulty level, but related to a different topic covered in the course that was of similar complexity. Complexity and difficulty of both case study and control questions were evaluated using experiential data from previous iterations of the course; the Bloom’s taxonomy designation and amount of material covered by each question, as well as the average score on similar questions achieved by students in previous iterations of the course was considered in determining appropriate controls. All assessment questions were scored using a standardized, pre-determined rubric. Student perceptions of learning gains were assessed using a modified version of the Student Assessment of Learning Gains (SALG) course evaluation tool ( http://www.salgsite.org ), distributed in hardcopy and completed anonymously during the last week of the course. Students were presented with a consent form to opt-in to having their data included in the data analysis. After the course had concluded and final course grades had been posted, data from consenting students were pooled in a database and identifying information was removed prior to analysis. Statistical analysis of data was conducted using the Kruskal-Wallis one-way analysis of variance and calculation of the R 2 coefficient of determination.

Teaching with case studies improves performance on learning assessments, independent of case study origin

To evaluate the effectiveness of the case study teaching method at promoting learning, student performance on examination questions related to material covered by case studies was compared with performance on questions that covered material addressed through classroom discussions and textbook reading. The latter questions served as control items; assessment items for each case study were compared with control items that were of similar format, difficulty, and point value ( Appendix 1 ). Each of the four case studies resulted in an increase in examination performance compared with control questions that was statistically significant, with an average difference of 18% ( Fig. 1 ). The mean score on case study-related questions was 73% for the chemical bonds case study, 79% for osmosis and diffusion, 76% for mitosis and meiosis, and 70% for DNA structure and replication ( Fig. 1 ). The mean score for non-case study-related control questions was 60%, 54%, 60%, and 52%, respectively ( Fig. 1 ). In terms of examination performance, no significant difference between case studies produced by the instructor of the course (chemical bonds and osmosis and diffusion) and those produced by unaffiliated instructors (mitosis and meiosis and DNA structure and replication) was indicated by the Kruskal-Wallis one-way analysis of variance. However, the 25% difference between the mean score on questions related to the osmosis and diffusion case study and the mean score on the paired control questions was notably higher than the 13–18% differences observed for the other case studies ( Fig. 1 ).

Case study teaching method increases student performance on examination questions. Mean score on a set of examination questions related to lessons covered by case studies (black bars) and paired control questions of similar format and difficulty about an unrelated topic (white bars). Chemical bonds, n = 54; Osmosis and diffusion, n = 54; Mitosis and meiosis, n = 51; DNA structure and replication, n = 50. Error bars represent the standard error of the mean (SEM). Asterisk indicates p < 0.05.

Case study teaching increases student perception of learning gains related to core course objectives

Student learning gains were assessed using a modified version of the SALG course evaluation tool ( Appendix 2 ). To determine whether completing case studies was more effective at increasing student perceptions of learning gains than completing textbook readings or participating in class discussions, perceptions of student learning gains for each were compared. In response to the question “Overall, how much did each of the following aspects of the class help your learning?” 82% of students responded that case studies helped a “good” or “great” amount, compared with 70% for participating in class discussions and 58% for completing textbook reading; only 4% of students responded that case studies helped a “small amount” or “provided no help,” compared with 2% for class discussions and 22% for textbook reading ( Fig. 2A ). The differences in reported learning gains derived from the use of case studies compared with class discussion and textbook readings were statistically significant, while the difference in learning gains associated with class discussion compared with textbook reading was not statistically significant by a narrow margin ( p = 0.051).

The case study teaching method increases student perceptions of learning gains. Student perceptions of learning gains are indicated by plotting responses to the question “How much did each of the following activities: (A) Help your learning overall? (B) Improve your ability to communicate your knowledge of scientific concepts in writing? (C) Improve your ability to communicate your knowledge of scientific concepts orally? (D) Help you understand the connections between scientific concepts and other aspects of your everyday life?” Reponses are represented as follows: Helped a great amount (black bars); Helped a good amount (dark gray bars); Helped a moderate amount (medium gray bars); Helped a small amount (light gray bars); Provided no help (white bars). Asterisk indicates p < 0.05.

To elucidate the effectiveness of case studies at promoting learning gains related to specific course learning objectives compared with class discussions and textbook reading, students were asked how much each of these methods of content delivery specifically helped improve skills that were integral to fulfilling three main course objectives. When students were asked how much each of the methods helped “improve your ability to communicate knowledge of scientific concepts in writing,” 81% of students responded that case studies help a “good” or “great” amount, compared with 63% for class discussions and 59% for textbook reading; only 6% of students responded that case studies helped a “small amount” or “provided no help,” compared with 8% for class discussions and 21% for textbook reading ( Fig. 2B ). When the same question was posed about the ability to communicate orally, 81% of students responded that case studies help a “good” or “great” amount, compared with 68% for class discussions and 50% for textbook reading, while the respective response rates for helped a “small amount” or “provided no help,” were 4%, 6%, and 25% ( Fig. 2C ). The differences in learning gains associated with both written and oral communication were statistically significant when completion of case studies was compared with either participation in class discussion or completion of textbook readings. Compared with textbook reading, class discussions led to a statistically significant increase in oral but not written communication skills.

Students were then asked how much each of the methods helped them “understand the connections between scientific concepts and other aspects of your everyday life.” A total of 79% of respondents declared that case studies help a “good” or “great” amount, compared with 70% for class discussions and 57% for textbook reading ( Fig. 2D ). Only 4% stated that case studies and class discussions helped a “small amount” or “provided no help,” compared with 21% for textbook reading ( Fig. 2D ). Similar to overall learning gains, the use of case studies significantly increased the ability to understand the relevance of science to everyday life compared with class discussion and textbook readings, while the difference in learning gains associated with participation in class discussion compared with textbook reading was not statistically significant ( p = 0.054).

Student perceptions of learning gains resulting from case study teaching are positively correlated to increased performance on examinations, but independent of case study author

To test the hypothesis that case studies produced specifically for this course by the instructor were more effective at promoting learning gains than topically relevant case studies published by authors not associated with this course, perceptions of learning gains were compared for each of the case studies. For both of the case studies produced by the instructor of the course, 87% of students indicated that the case study provided a “good” or “great” amount of help to their learning, and 2% indicated that the case studies provided “little” or “no” help ( Table 1 ). In comparison, an average of 85% of students indicated that the case studies produced by an unaffiliated instructor provided a “good” or “great” amount of help to their learning, and 4% indicated that the case studies provided “little” or “no” help ( Table 1 ). The instructor-produced case studies yielded both the highest and lowest percentage of students reporting the highest level of learning gains (a “great” amount), while case studies produced by unaffiliated instructors yielded intermediate values. Therefore, it can be concluded that the effectiveness of case studies at promoting learning gains is not significantly affected by whether or not the course instructor authored the case study.

Case studies positively affect student perceptions of learning gains about various biological topics.

Finally, to determine whether performance on examination questions accurately predicts student perceptions of learning gains, mean scores on examination questions related to case studies were compared with reported perceptions of learning gains for those case studies ( Fig. 3 ). The coefficient of determination (R 2 value) was 0.81, indicating a strong, but not definitive, positive correlation between perceptions of learning gains and performance on examinations, suggesting that student perception of learning gains is a valid tool for assessing the effectiveness of case studies ( Fig. 3 ). This correlation was independent of case study author.

Perception of learning gains but not author of case study is positively correlated to score on related examination questions. Percentage of students reporting that each specific case study provided “a great amount of help” to their learning was plotted against the point difference between mean score on examination questions related to that case study and mean score on paired control questions. Positive point differences indicate how much higher the mean scores on case study-related questions were than the mean scores on paired control questions. Black squares represent case studies produced by the instructor of the course; white squares represent case studies produced by unaffiliated instructors. R 2 value indicates the coefficient of determination.

The purpose of this study was to test the hypothesis that teaching with case studies produced by the instructor of a course is more effective at promoting learning gains than using case studies produced by unaffiliated instructors. This study also tested the hypothesis that the case study teaching method is more effective than class discussions and textbook reading at promoting learning gains associated with four of the most commonly taught topics in undergraduate general biology courses: chemical bonds, osmosis and diffusion, mitosis and meiosis, and DNA structure and replication. In addition to assessing content-based learning gains, development of written and oral communication skills and the ability to connect scientific topics with real-world applications was also assessed, because these skills were overarching learning objectives of this course, and classroom activities related to both case studies and control lessons were designed to provide opportunities for students to develop these skills. Finally, data were analyzed to determine whether performance on examination questions is positively correlated to student perceptions of learning gains resulting from case study teaching.

Compared with equivalent control questions about topics of similar complexity taught using class discussions and textbook readings, all four case studies produced statistically significant increases in the mean score on examination questions ( Fig. 1 ). This indicates that case studies are more effective than more commonly used, traditional methods of content delivery at promoting learning of a variety of core concepts covered in general biology courses. The average increase in score on each test item was equivalent to nearly two letter grades, which is substantial enough to elevate the average student performance on test items from the unsatisfactory/failing range to the satisfactory/passing range. The finding that there was no statistical difference between case studies in terms of performance on examination questions suggests that case studies are equally effective at promoting learning of disparate topics in biology. The observations that students did not perform significantly less well on the first case study presented (chemical bonds) compared with the other case studies and that performance on examination questions did not progressively increase with each successive case study suggests that the effectiveness of case studies is not directly related to the amount of experience students have using case studies. Furthermore, anecdotal evidence from previous semesters of this course suggests that, of the four topics addressed by cases in this study, DNA structure and function and osmosis and diffusion are the first and second most difficult for students to grasp. The lack of a statistical difference between case studies therefore suggests that the effectiveness of a case study at promoting learning gains is not directly proportional to the difficulty of the concept covered. However, the finding that use of the osmosis and diffusion case study resulted in the greatest increase in examination performance compared with control questions and also produced the highest student perceptions of learning gains is noteworthy and could be attributed to the fact that it was the only case study evaluated that included a hands-on experiment. Because the inclusion of a hands-on kinetic activity may synergistically enhance student engagement and learning and result in an even greater increase in learning gains than case studies that lack this type of activity, it is recommended that case studies that incorporate this type of activity be preferentially utilized.

Student perceptions of learning gains are strongly motivating factors for engagement in the classroom and academic performance, so it is important to assess the effect of any teaching method in this context ( 19 , 24 ). A modified version of the SALG course evaluation tool was used to assess student perceptions of learning gains because it has been previously validated as an efficacious tool ( Appendix 2 ) ( 20 ). Using the SALG tool, case study teaching was demonstrated to significantly increase student perceptions of overall learning gains compared with class discussions and textbook reading ( Fig. 2A ). Case studies were shown to be particularly useful for promoting perceived development of written and oral communication skills and for demonstrating connections between scientific topics and real-world issues and applications ( Figs. 2B–2D ). Further, student perceptions of “great” learning gains positively correlated with increased performance on examination questions, indicating that assessment of learning gains using the SALG tool is both valid and useful in this course setting ( Fig. 3 ). These findings also suggest that case study teaching could be used to increase student motivation and engagement in classroom activities and thus promote learning and performance on assessments. The finding that textbook reading yielded the lowest student perceptions of learning gains was not unexpected, since reading facilitates passive learning while the class discussions and case studies were both designed to promote active learning.

Importantly, there was no statistical difference in student performance on examinations attributed to the two case studies produced by the instructor of the course compared with the two case studies produced by unaffiliated instructors. The average difference between the two instructor-produced case studies and the two case studies published by unaffiliated instructors was only 3% in terms of both the average score on examination questions (76% compared with 73%) and the average increase in score compared with paired control items (14% compared with 17%) ( Fig. 1 ). Even when considering the inherent qualitative differences of course grades, these differences are negligible. Similarly, the effectiveness of case studies at promoting learning gains was not significantly affected by the origin of the case study, as evidenced by similar percentages of students reporting “good” and “great” learning gains regardless of whether the case study was produced by the course instructor or an unaffiliated instructor ( Table 1 ).

The observation that case studies published by unaffiliated instructors are just as effective as those produced by the instructor of a course suggests that instructors can reasonably rely on the use of pre-published case studies relevant to their class rather than investing the considerable time and effort required to produce a novel case study. Case studies covering a wide range of topics in the sciences are available from a number of sources, and many of them are free access. The National Center for Case Study Teaching in Science (NCCSTS) database ( http://sciencecases.lib.buffalo.edu/cs/ ) contains over 500 case studies that are freely available to instructors, and are accompanied by teaching notes that provide logistical advice and additional resources for implementing the case study, as well as a set of assessment questions with a password-protected answer key. Case study repositories are also maintained by BioQUEST Curriculum Consortium ( http://www.bioquest.org/icbl/cases.php ) and the Science Case Network ( http://sciencecasenet.org ); both are available for use by instructors from outside institutions.

It should be noted that all case studies used in this study were rigorously peer-reviewed and accepted for publication by the NCCSTS prior to the completion of this study ( 2 , 10 , 18 , 25 ); the conclusions of this study may not apply to case studies that were not developed in accordance with similar standards. Because case study teaching involves skills such as creative writing and management of dynamic group discussion in a way that is not commonly integrated into many other teaching methods, it is recommended that novice case study teachers seek training or guidance before writing their first case study or implementing the method. The lack of a difference observed in the use of case studies from different sources should be interpreted with some degree of caution since only two sources were represented in this study, and each by only two cases. Furthermore, in an educational setting, quantitative differences in test scores might produce meaningful qualitative differences in course grades even in the absence of a p value that is statistically significant. For example, there is a meaningful qualitative difference between test scores that result in an average grade of C− and test scores that result in an average grade of C+, even if there is no statistically significant difference between the two sets of scores.

In the future, it could be informative to confirm these findings using a larger cohort, by repeating the study at different institutions with different instructors, by evaluating different case studies, and by directly comparing the effectiveness of the case studying teaching method with additional forms of instruction, such as traditional chalkboard and slide-based lecturing, and laboratory-based activities. It may also be informative to examine whether demographic factors such as student age and gender modulate the effectiveness of the case study teaching method, and whether case studies work equally well for non-science majors taking a science course compared with those majoring in the subject. Since the topical material used in this study is often included in other classes in both high school and undergraduate education, such as cell biology, genetics, and chemistry, the conclusions of this study are directly applicable to a broad range of courses. Presently, it is recommended that the use of case studies in teaching undergraduate general biology and other science courses be expanded, especially for the teaching of capacious issues with real-world applications and in classes where development of written and oral communication skills are key objectives. The use of case studies that involve hands-on activities should be emphasized to maximize the benefit of this teaching method. Importantly, instructors can be confident in the use of pre-published case studies to promote learning, as there is no indication that the effectiveness of the case study teaching method is reliant on the production of novel, customized case studies for each course.

SUPPLEMENTAL MATERIALS

Acknowledgments.

This article benefitted from a President’s Faculty Innovation Grant, Kingsborough Community College. The author declares that there are no conflicts of interest.

† Supplemental materials available at http://jmbe.asm.org

Using Case Studies to Teach

Why Use Cases?

Many students are more inductive than deductive reasoners, which means that they learn better from examples than from logical development starting with basic principles. The use of case studies can therefore be a very effective classroom technique.

Case studies are have long been used in business schools, law schools, medical schools and the social sciences, but they can be used in any discipline when instructors want students to explore how what they have learned applies to real world situations. Cases come in many formats, from a simple “What would you do in this situation?” question to a detailed description of a situation with accompanying data to analyze. Whether to use a simple scenario-type case or a complex detailed one depends on your course objectives.

Most case assignments require students to answer an open-ended question or develop a solution to an open-ended problem with multiple potential solutions. Requirements can range from a one-paragraph answer to a fully developed group action plan, proposal or decision.

Common Case Elements

Most “full-blown” cases have these common elements:

• A decision-maker who is grappling with some question or problem that needs to be solved.
• A description of the problem’s context (a law, an industry, a family).
• Supporting data, which can range from data tables to links to URLs, quoted statements or testimony, supporting documents, images, video, or audio.

Case assignments can be done individually or in teams so that the students can brainstorm solutions and share the work load.

The following discussion of this topic incorporates material presented by Robb Dixon of the School of Management and Rob Schadt of the School of Public Health at CEIT workshops. Professor Dixon also provided some written comments that the discussion incorporates.

Advantages to the use of case studies in class

A major advantage of teaching with case studies is that the students are actively engaged in figuring out the principles by abstracting from the examples. This develops their skills in:

• Problem solving
• Analytical tools, quantitative and/or qualitative, depending on the case
• Decision making in complex situations
• Coping with ambiguities

Guidelines for using case studies in class

In the most straightforward application, the presentation of the case study establishes a framework for analysis. It is helpful if the statement of the case provides enough information for the students to figure out solutions and then to identify how to apply those solutions in other similar situations. Instructors may choose to use several cases so that students can identify both the similarities and differences among the cases.

Depending on the course objectives, the instructor may encourage students to follow a systematic approach to their analysis.  For example:

• What is the issue?
• What is the goal of the analysis?
• What is the context of the problem?
• What key facts should be considered?
• What alternatives are available to the decision-maker?
• What would you recommend — and why?

An innovative approach to case analysis might be to have students  role-play the part of the people involved in the case. This not only actively engages students, but forces them to really understand the perspectives of the case characters. Videos or even field trips showing the venue in which the case is situated can help students to visualize the situation that they need to analyze.

Accompanying Readings

Case studies can be especially effective if they are paired with a reading assignment that introduces or explains a concept or analytical method that applies to the case. The amount of emphasis placed on the use of the reading during the case discussion depends on the complexity of the concept or method. If it is straightforward, the focus of the discussion can be placed on the use of the analytical results. If the method is more complex, the instructor may need to walk students through its application and the interpretation of the results.

Leading the Case Discussion and Evaluating Performance

Decision cases are more interesting than descriptive ones. In order to start the discussion in class, the instructor can start with an easy, noncontroversial question that all the students should be able to answer readily. However, some of the best case discussions start by forcing the students to take a stand. Some instructors will ask a student to do a formal “open” of the case, outlining his or her entire analysis.  Others may choose to guide discussion with questions that move students from problem identification to solutions.  A skilled instructor steers questions and discussion to keep the class on track and moving at a reasonable pace.

In order to motivate the students to complete the assignment before class as well as to stimulate attentiveness during the class, the instructor should grade the participation—quantity and especially quality—during the discussion of the case. This might be a simple check, check-plus, check-minus or zero. The instructor should involve as many students as possible. In order to engage all the students, the instructor can divide them into groups, give each group several minutes to discuss how to answer a question related to the case, and then ask a randomly selected person in each group to present the group’s answer and reasoning. Random selection can be accomplished through rolling of dice, shuffled index cards, each with one student’s name, a spinning wheel, etc.

Tips on the Penn State U. website: http://tlt.its.psu.edu/suggestions/cases/

If you are interested in using this technique in a science course, there is a good website on use of case studies in the sciences at the University of Buffalo.

Dunne, D. and Brooks, K. (2004) Teaching with Cases (Halifax, NS: Society for Teaching and Learning in Higher Education), ISBN 0-7703-8924-4 (Can be ordered at http://www.bookstore.uwo.ca/ at a cost of $15.00)

• --> Login or Sign Up

The Case Study Teaching Method

It is easy to get confused between the case study method and the case method , particularly as it applies to legal education. The case method in legal education was invented by Christopher Columbus Langdell, Dean of Harvard Law School from 1870 to 1895. Langdell conceived of a way to systematize and simplify legal education by focusing on previous case law that furthered principles or doctrines. To that end, Langdell wrote the first casebook, entitled A Selection of Cases on the Law of Contracts , a collection of settled cases that would illuminate the current state of contract law. Students read the cases and came prepared to analyze them during Socratic question-and-answer sessions in class.

The Harvard Business School case study approach grew out of the Langdellian method. But instead of using established case law, business professors chose real-life examples from the business world to highlight and analyze business principles. HBS-style case studies typically consist of a short narrative (less than 25 pages), told from the point of view of a manager or business leader embroiled in a dilemma. Case studies provide readers with an overview of the main issue; background on the institution, industry, and individuals involved; and the events that led to the problem or decision at hand. Cases are based on interviews or public sources; sometimes, case studies are disguised versions of actual events or composites based on the faculty authors’ experience and knowledge of the subject. Cases are used to illustrate a particular set of learning objectives; as in real life, rarely are there precise answers to the dilemma at hand.

Our suite of free materials offers a great introduction to the case study method. We also offer review copies of our products free of charge to educators and staff at degree-granting institutions.

For more information on the case study teaching method, see:

• Martha Minow and Todd Rakoff: A Case for Another Case Method
• HLS Case Studies Blog: Legal Education’s 9 Big Ideas
• Teaching Units: Problem Solving , Advanced Problem Solving , Skills , Decision Making and Leadership , Professional Development for Law Firms , Professional Development for In-House Counsel
• Educator Community: Tips for Teachers

Watch this informative video about the Problem-Solving Workshop:

<< Previous: About Harvard Law School Case Studies | Next: Downloading Case Studies >>

• Utility Menu

GA4 Tracking Code

fa51e2b1dc8cca8f7467da564e77b5ea

• Make a Gift
• Join Our Email List
• Teaching with Cases

At professional schools (like Harvard’s Law, Business, Education, or Medical Schools), courses often adopt the so-called "case method" of teaching , in which students are confronted with real-world problems or scenarios involving multiple stakeholders and competing priorities. Most of the cases which faculty use with their students are written by professionals who have expertise in researching and writing in that genre, and for good reason—writing a truly masterful case, one which can engage students in hours of debate and deliberation, takes a lot of time and effort. It can be effective, nevertheless, for you to try implementing some aspects of the case-teaching approach in your class. Among the benefits which accrue to using case studies are the following:

• the fact that it gives your students the opportunity to "practice" a real-world application;
• the fact that it compels them (and you!) to reconstruct all of the divergent and convergent perspectives which different parties might bring to the scenario;
• the fact that it motivates your students to anticipate a wide range of possible responses which a reader might have; and
• the fact that it invites your students to indulge in metacognition as they revisit the process by which they became more knowledgeable about the scenario.

Features of an Effective Teaching Case

While no two case studies will be exactly alike, here are some of those principles:

• The case should illustrate what happens when a concept from the course could be, or has been, applied in the real world. Depending on the course, a “concept” might mean any one among a range of things, including an abstract principle, a theory, a tension, an issue, a method, an approach, or simply a way of thinking characteristic of an academic field. Whichever you choose, you should make sure to “ground” the case in a realistic setting early in the narrative, so that participants understand their role in the scenario.
• The case materials should include enough factual content and context to allow students to explore multiple perspectives. In order for participants to feel that they are encountering a real-world application of the course material, and that they have some freedom and agency in terms of how they interpret it, they need to be able to see the issue or problem from more than one perspective. Moreover, those perspectives need to seem genuine, and to be sketched in enough detail to seem complex. (In fact, it’s not a bad idea to include some “extraneous” information about the stakeholders involved in the case, so that students have to filter out things that seem relevant or irrelevant to them.) Otherwise, participants may fall back on picking obvious “winners” and “losers” rather than seeking creative, negotiated solutions that satisfy multiple stakeholders.
• The case materials should confront participants with a range of realistic constraints, hard choices, and authentic outcomes. If the case presumes that participants will all become omniscient, enjoy limitless resources, and succeed, they won’t learn as much about themselves as team-members and decision-makers as if they are forced to confront limitations, to make tough decisions about priorities, and to be prepared for unexpected results. These constraints and outcomes can be things which have been documented in real life, but they can also be things which the participants themselves surface in their deliberations.

• The activity should include space to reflect upon the decision-making process and the lessons of the case. Writing a case offers an opportunity to engage in multiple layers of reflection. For you, as the case writer, it is an occasion to anticipate how you (if you were the instructor) might create scenarios that are aligned with, and likely to meet the learning objectives of, a given unit of your course. For the participants whom you imagine using your case down the road, the case ideally should help them (1) to understand their own hidden assumptions, priorities, values, and biases better; and (2) to close the gap between their classroom learning and its potential real-world applications.

For more information...

Kim, Sara et al. 2006. "A Conceptual Framework for Developing Teaching Cases: A Review and Synthesis of the Literature across Disciplines." Medical Education 40: 867–876.

Herreid, Clyde Freeman. 2011. "Case Study Teaching." New Directions for Teaching and Learning 128: 31–40.

Nohria, Nitin. 2021. "What the Case Study Method Really Teaches." Harvard Business Review .

Swiercz, Paul Michael. "SWIF Learning: A Guide to Student Written-Instructor Facilitated Case Writing."

• Designing Your Course
• A Teaching Timeline: From Pre-Term Planning to the Final Exam
• The First Day of Class
• Group Agreements
• Classroom Debate
• Flipped Classrooms
• Leading Discussions
• Polling & Clickers
• Problem Solving in STEM
• Engaged Scholarship
• Devices in the Classroom
• Beyond the Classroom
• On Professionalism
• Getting Feedback
• Equitable & Inclusive Teaching
• Advising and Mentoring
• Teaching and Your Career
• Teaching Remotely
• Tools and Platforms
• The Science of Learning
• Bok Publications
• Other Resources Around Campus

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

What the Case Study Method Really Teaches

• Nitin Nohria

Seven meta-skills that stick even if the cases fade from memory.

It’s been 100 years since Harvard Business School began using the case study method. Beyond teaching specific subject matter, the case study method excels in instilling meta-skills in students. This article explains the importance of seven such skills: preparation, discernment, bias recognition, judgement, collaboration, curiosity, and self-confidence.

During my decade as dean of Harvard Business School, I spent hundreds of hours talking with our alumni. To enliven these conversations, I relied on a favorite question: “What was the most important thing you learned from your time in our MBA program?”

• Nitin Nohria is the George F. Baker Jr. Professor at Harvard Business School and the former dean of HBS.

Partner Center

• Utility Menu

harvardchan_logo.png

Harvard T.H. Chan School of Public Health Case-Based Teaching & Learning Initiative

Teaching cases & active learning resources for public health education, teaching & learning with the case method.

2023. Case Compendium, University of California Berkeley Haas School of Business Center for Equity, Gender & Leadership . Visit website This resource, compiled by the Berkeley Haas Center for Equity, Gender & Leadership, is "a case compendium that includes: (a) case studies with diverse protagonists, and (b) case studies that build “equity fluency” by focusing on DEI-related issues and opportunities. The goal of the compendium is to support professors at Haas, and business schools globally, to identify cases they can use in their own classrooms, and ultimately contribute to advancing DEI in education and business."

Kane, N.M. , 2014. Benefits of Case-Based Teaching . Watch video Watch a demonstration of Prof. Nancy Kane teaching public health with the case method. (Part 3 of 3, 3 minutes)

Kane, N.M. , 2014. Case teaching demonstration: Should a health plan cover medical tourism? . Watch video Watch a demonstration of Prof. Nancy Kane teaching public health with the case method. (Part 2 of 3, 17 minutes)

Kane, N.M. , 2014. Case-based teaching at the Harvard T.H. Chan School of Public Health . Watch video Watch a demonstration of Prof. Nancy Kane teaching public health with the case method. (Part 1 of 3, 10 minutes)

2019. The Case Centre . Visit website A non-profit clearing house for materials on the case method, the Case Centre holds a large and diverse collection of cases, articles, book chapters and teaching materials, including the collections of leading business schools across the globe.

Austin, S.B. & Sonneville, K.R. , 2013. Closing the "know-do" gap: training public health professionals in eating disorders prevention via case-method teaching. International Journal of Eating Disorders , 46 (5) , pp. 533-537. Read online Abstract Expansion of our societies' capacity to prevent eating disorders will require strategic integration of the topic into the curricula of professional training programs. An ideal way to integrate new content into educational programs is through the case-method approach, a teaching method that is more effective than traditional teaching techniques. The Strategic Training Initiative for the Prevention of Eating Disorders has begun developing cases designed to be used in classroom settings to engage students in topical, high-impact issues in public health approaches to eating disorders prevention and screening. Dissemination of these cases will provide an opportunity for students in public health training programs to learn material in a meaningful context by actively applying skills as they are learning them, helping to bridge the "know-do" gap. The new curriculum is an important step toward realizing the goal that public health practitioners be fully equipped to address the challenge of eating disorders prevention. "Expansion of our societies' capacity to prevent eating disorders will require strategic integration of the topic into the curricula of professional training programs. An ideal way to integrate new content into educational programs is through the case-method approach, a teaching method that is more effective than traditional teaching techniques." Access full article with HarvardKey . 

Ellet, W. , 2018. The Case Study Handbook, Revised Edition: A Student's Guide , Harvard Business School Publishing. Publisher's Version "If you're like many people, you may find interpreting and writing about cases mystifying and time-consuming. In The Case Study Handbook, Revised Edition , William Ellet presents a potent new approach for efficiently analyzing, discussing, and writing about cases."

Andersen, E. & Schiano, B. , 2014. Teaching with Cases: A Practical Guide , Harvard Business School Publishing. Publisher's Version "The class discussion inherent in case teaching is well known for stimulating the development of students' critical thinking skills, yet instructors often need guidance on managing that class discussion to maximize learning. Teaching with Cases focuses on practical advice for instructors that can be easily implemented. It covers how to plan a course, how to teach it, and how to evaluate it." 

Honan, J. & Sternman Rule, C. , 2002. Case Method Instruction Versus Lecture-Based Instruction R. Reis, ed. Tomorrow's Professor . Read online "Faculty and discussion leaders who incorporate the case study method into their teaching offer various reasons for their enthusiasm for this type of pedagogy over more traditional, such as lecture-based, instructional methods and routes to learning." Exerpt from the book Using Cases in Higher Education: A Guide for Faculty and Administrators , by James P. Honan and Cheryl Sternman Rule.

Austin, J. , 1993. Teaching Notes: Communicating the Teacher's Wisdom , Harvard Business School Publishing. Publisher's Version "Provides guidance for the preparation of teaching notes. Sets forth the rationale for teaching notes, what they should contain and why, and how they can be prepared. Based on the experiences of Harvard Business School faculty."

Abell, D. , 1997. What makes a good case? . ECCHO–The Newsletter of the European Case Clearing House , 17 (1) , pp. 4-7. Read online "Case writing is both art and science. There are few, if any, specific prescriptions or recipes, but there are key ingredients that appear to distinguish excellent cases from the run-of-the-mill. This technical note lists ten ingredients to look for if you are teaching somebody else''s case - and to look out for if you are writing it yourself."

Herreid, C.F. , 2001. Don't! What not to do when teaching cases. Journal of College Science Teaching , 30 (5) , pp. 292. Read online "Be warned, I am about to unleash a baker’s dozen of 'don’ts' for aspiring case teachers willing to try running a classroom discussion armed with only a couple of pages of a story and a lot of chutzpah."

Garvin, D.A. , 2003. Making the case: Professional education for the world of practice . Harvard Magazine , 106 (1) , pp. 56-65. Read online A history and overview of the case-method in professional schools, which all “face the same difficult challenge: how to prepare students for the world of practice. Time in the classroom must somehow translate directly into real-world activity: how to diagnose, decide, and act."

• Writing a case (8)
• Writing a teaching note (4)
• Active learning (12)
• Active listening (1)
• Asking effective questions (5)
• Assessing learning (1)
• Engaging students (5)
• Leading discussion (10)
• Managing the classroom (4)
• Planning a course (1)
• Problem-based learning (1)
• Teaching & learning with the case method (14)
• Teaching inclusively (3)

• Case Teaching Resources

Teaching With Cases

Included here are resources to learn more about case method and teaching with cases.

What Is A Teaching Case?

This video explores the definition of a teaching case and introduces the rationale for using case method.

Narrated by Carolyn Wood, former director of the HKS Case Program

Learning by the Case Method

Questions for class discussion, common case teaching challenges and possible solutions, teaching with cases tip sheet, teaching ethics by the case method.

The case method is an effective way to increase student engagement and challenge students to integrate and apply skills to real-world problems. In these videos,  Using the Case Method to Teach Public Policy , you'll find invaluable insights into the art of case teaching from one of HKS’s most respected professors, Jose A. Gomez-Ibanez.

Chapter 1: Preparing for Class (2:29)

Chapter 2: How to begin the class and structure the discussion blocks (1:37)

Chapter 3: How to launch the discussion (1:36)

Chapter 4: Tools to manage the class discussion (2:23)

Chapter 5: Encouraging participation and acknowledging students' comments (1:52)

Chapter 6: Transitioning from one block to the next / Importance of body (2:05)

Chapter 7: Using the board plan to feed the discussion (3:33)

Chapter 8: Exploring the richness of the case (1:42)

Chapter 9: The wrap-up. Why teach cases? (2:49)

• CRLT Consultation Services
• Consultation
• Midterm Student Feedback
• Classroom Observation
• Teaching Philosophy
• Upcoming Events and Seminars
• CRLT Calendar
• Orientations
• Teaching Academies
• Provost's Seminars
• Past Events
• For Faculty
• For Grad Students & Postdocs
• For Chairs, Deans & Directors
• Customized Workshops & Retreats
• Assessment, Curriculum, & Learning Analytics Services
• CRLT in Engineering
• CRLT Players
• Foundational Course Initiative
• CRLT Grants
• Other U-M Grants
• Provost's Teaching Innovation Prize
• U-M Teaching Awards
• Retired Grants
• Staff Directory
• Faculty Advisory Board
• Annual Report
• Equity-Focused Teaching
• Preparing to Teach
• Teaching Strategies
• Testing and Grading
• Teaching with Technology
• Teaching Philosophy & Statements
• Training GSIs
• Evaluation of Teaching
• Occasional Papers

Case-based Teaching and Problem-based Learning

Case-based teaching.

With case-based teaching, students develop skills in analytical thinking and reflective judgment by reading and discussing complex, real-life scenarios. The articles in this section explain how to use cases in teaching and provide case studies for the natural sciences, social sciences, and other disciplines.

Teaching with Case Studies (Stanford University)

This article from the Stanford Center for Teaching and Learning describes the rationale for using case studies, the process for choosing appropriate cases, and tips for how to implement them in college courses.

The Case Method (University of Illinois)

Tips for teachers on how to be successful using the Case Method in the college/university classroom. Includes information about the Case Method values, uses, and additional resource links.

National Center for Case Study Teaching in Science (National Science Teaching Association)

This site offers resources and examples specific to teaching in the sciences. This includes the “UB Case Study Collection,” an extensive list of ready-to-use cases in a variety of science disciplines. Each case features a PDF handout describing the case, as well as teaching notes.

The Michigan Sustainability Cases Initiative (CRLT Occasional Paper)

This paper describes the Michigan Sustainability Cases Initiative, including links to the full library of cases, and it offers advice both for writing cases and facilitating case discussions effectively.

The Case Method and the Interactive Classroom (Foran, 2001, NEA Higher Education Journal)

First-person account of how a sociology faculty member at University of California, Santa Barbara began using case studies in his teaching and how his methods have evolved over time as a professor.

Problem-based Learning

Problem-based learning (PBL) is both a teaching method and an approach to the curriculum. It consists of carefully designed problems that challenge students to use problem solving techniques, self-directed learning strategies, team participation skills, and disciplinary knowledge. The articles and links in this section describe the characteristics and objectives of PBL and the process for using PBL. There is also a list of printed and web resources.

Problem-Based Learning Network (Illinois Mathematics and Science Academy)

Site includes an interactive PBL Model, Professional Development links, and video vignettes to illustrate how to effectively use problem-based learning in the classroom. The goals of IMSA's PBLNetwork are to mentor educators in all disciplines, to explore problem-based learning strategies, and to connect PBL educators to one another.

Problem-Based Learning: An Introduction (Rhem, 1998, National Teaching and Learning Forum)

This piece summarizes the benefits of using problem-based learning, its historical origins, and the faculty/student roles in PBL. Overall, this is an easy to read introduction to problem-based learning.

Problem-Based Learning (Stanford University, 2001)

This issue of Speaking of Teaching identifies the central features of PBL, provides some guidelines for planning a PBL course, and discusses the impact of PBL on student learning and motivation.

Problem-Based Learning Clearinghouse (University of Delaware)

Collection of peer reviewed problems and articles to assist educators in using problem-based learning. Teaching notes and supplemental materials accompany each problem, providing insights and strategies that are innovative and classroom-tested. Free registration is required to view and download the Clearinghouse’s resources.

See also: The International Journal of Problem-Based Learning

Contact CRLT

location_on University of Michigan 1071 Palmer Commons 100 Washtenaw Ave. Ann Arbor, MI 48109-2218

phone Phone: (734) 764-0505

description Fax: (734) 647-3600

email Email: [email protected]

Connect with CRLT

directions Directions to CRLT

group Staff Directory

markunread_mailbox Subscribe to our Blog

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

Teaching with Case Studies

The Case Study method is based on focused stories, rooted in reality, and provides contextual information such as background, characters, setting, and enough specific details to provide some guidance. Cases can be used to illustrate, remediate, and practice critical thinking, teamwork, research, and communication skills. Classroom applications of the case study method include:

• Socratic cross examination
• Directed discussion or research teams
• Public hearings or trials
• Dialogue paper (e.g., 10 exchanges between two characters from opposing sides of an issue that finish with a personal opinion or reflection)

At the Fifth Annual Conference on Case Study Teaching in Science hosted by the University of Buffalo-SUNY, two broad categories of case studies were identified (recognizing potential overlap):

• Open or Closed: Open cases are left to one’s interpretation and may have multiple correct or valid answers depending on the rationale and facts presented in the case analysis. Closed cases have specific, correct answers or processes that must be followed in order to arrive at the correct analysis.
• Analysis or Dilemma: Analysis Cases (Issues Cases) are a general account of “what happened.” Dilemma Cases (Decision Cases) require students to make a decision or take action given certain information.

Case Study Analysis Process

Based on a variety of different case study analysis models, we have identified four basic stages students follow in analyzing a case study. This process may vary depending on discipline and if case studies are being used as part of a problem-based learning exercise.

• Observe the facts and issues that are present without interpretation (“what do we know”).
• Develop hypotheses/questions, formulate predictions, and provide explanations or justifications based on the known information (“what do we need to know”).
• Collect and explore relevant data to answer open questions, reinforce/refute hypotheses, and formulate new hypotheses and questions.
• Communicate findings including citations and documentation.

How to Write a Case Study

Effective case studies tell a story, have compelling and identifiable characters, contain depth and complexity, and have dilemmas that are not easily resolved. The following steps provide a general guide for use in identifying the various issues and criteria comprising a good case study.

• Identify a course and list the teachable principles, topics, and issues (often a difficult or complex concept students just don’t “get”).
• List any relevant controversies and subtopics that further describe your topics.
• Identify stakeholders or those affected by the issue (from that list, consider choosing one central character on which to base the case study).
• Identify teaching methods that might be used (team project, dialogue paper, debate, etc.) as well as the most appropriate assessment method (peer or team assessments, participation grade, etc.).
• Decide what materials and resources will be provided to students.
• Identify and describe the deliverables students will produce (paper, presentation, etc.).
• Select the category of case study (open or closed/analysis or dilemma) that best fits your topic, scenario, learning outcomes, teaching method, and assessment strategy. Write your case study and include teaching notes outlining the critical elements identified above.
• Teach the case and subsequently make any necessary revisions.

Problem-Based Learning (PBL)

PBL uses case studies in a slightly different way by providing a more specific structure for learning. The medical field uses this approach extensively. According to Barrows & Tamblyn (1980), the case problem is presented first in the learning sequence, before any background preparation has occurred. The case study analysis process outlined above is used with PBL; the main difference being that cases are presented in pieces, with increasing amounts of specific detail provided in each layer of the case (e.g., part one of the case may simply be a patient admission form, part two may provide a summary of patient examination notes, part three may contain specific medical test results, and so on).

The problem-based learning approach encourages student-directed learning and allows the instructor to serve as a facilitator. Students frame and identify problems and continually identify and test hypotheses. During group tutorials, case-related questions arise that students are unable to answer. These questions form the basis for learning issues that students will study independently between sessions. This method requires an alert and actively involved instructor to facilitate.

Guide to Teaching with Technology Copyright © 2019 by Centre for Pedagogical Innovation is licensed under a Creative Commons Attribution 4.0 International License , except where otherwise noted.

Share This Book

• ⋮⋮⋮ ×

Teaching with the Case Method

Related links.

Investigative Case Based Learning

By Ann Velenchik Wellesley College

With considerable help from Pat Conway , Mike Hemesath , Eric Ribbens , and David Schodt

What is Teaching with the Case Method?

The case method combines two elements: the case itself and the discussion of that case. A teaching case is a rich narrative in which individuals or groups must make a decision or solve a problem. A teaching case is not a "case study" of the type used in academic research. Teaching cases provide information, but neither analysis nor conclusions. The analytical work of explaining the relationships among events in the case, identifying options, evaluating choices and predicting the effects of actions is the work done by students during the classroom discussion. Learn more about the Case Method

Why Teach with the Case Method?

In a case discussion, students "do" the work of the discipline, rather than watch or read about how it is done by others. By engaging in the case, students apply the concepts, techniques and methods of the discipline and improve their ability to apply them. Case discussions bring energy and excitement to the classroom, providing students with an opportunity to work with a range of evidence, and improving their ability to apply the vocabulary, theory and methods they have learned in the course. Learn more about teaching with Cases

How to Teach with the Case Method?

Case method teaching brings together three components: an appropriate case, students who are prepared to engage with the case material in a discussion, and an instructor who knows the case, has a plan for the discussion and is ready to deal with the unexpected. This section provides detailed instructions on how to develop each of these components. Learn how to teach with Cases

Teaching Economics with the Case Method

Case examples.

Browse the collection of teaching examples

Browse a list of references related to teaching with Cases

      Next Page »

Teaching History Through the Case Method

Explore more.

• Case Teaching
• Course Materials

T he case method is typically synonymous with business school curriculum. Through active case discussion, students put themselves in the proverbial shoes of a case protagonist, often a manager or leader of a company or organization facing a difficult business challenge. Students apply critical thinking skills to work through complicated problems and process contending points of view, then engage with their classmates in developing a solution together. This intellectual energy is the pedagogical “magic” instructors strive for.

Perhaps a lesser-known power of the case method, however, is in its applicability across a variety of topics and student levels. Take, for instance, history, government, civics, and democracy—topics that feel particularly pertinent given the roller-coaster US election and other polarizing political events around the world.

In an effort to bring these important topics, particularly American history, to life, historian David Moss, the Paul Whiton Cherington Professor of Business Administration at Harvard Business School (HBS), has taken the case method’s magic from the business school to the high school. In 2015, Moss launched a pilot program in 11 public, charter, and private high schools across the United States. He provided 23 history and civics teachers with historical cases that showcase the foundations of US democracy—as well as worksheets, assignment questions, and teaching plans. He then made the cases available for free to high school students to encourage case teaching among this group.

The goal of this program, called the Case Method Project , is to demonstrate that teaching with cases can strengthen high school and college education as well as ensure “a more exciting, relevant, and effective experience for students and teachers across a range of subjects,” according to its site.

“The results [of the Case Method Project] have been incredibly positive, especially in terms of strengthening students’ critical thinking, their retention and understanding of course material, and their civic interest and engagement.” David Moss

Since its initial launch, the program has grown considerably. Today Moss is working with over 350 teachers in more than 250 high schools across 45 states and the District of Columbia. “We’ve now reached well over 30,000 students as part of the initial pilot,” he says. “The project has grown considerably over the last several years, and the results have been incredibly positive, especially in terms of strengthening students’ critical thinking, their retention and understanding of course material, and their civic interest and engagement. Because of this success, we’re aiming to reach much larger numbers of teachers and students going forward through the new Case Method Institute for Education and Democracy, which started up this summer.”

The case method has proven remarkably effective in teaching high schoolers the critical thinking skills that the world’s future leaders so greatly need. Here, to help educators see the different ways and venues in which case teaching can be used, we showcase the collection of cases Moss authored and provided in support of this effort.

Democracy Cases to Use in Class

Here is a list of Moss’s cases , which you can use to engage students in conversations about US history and democracy. We hope you find these cases helpful.

James Madison, the ‘Federal Negative,’ and the Making of the U.S. Constitution (1787) and as a supplement: In Detail: Debt and Paper Money in Rhode Island (1786)

Battle Over a Bank: Defining the Limits of Federal Power Under a New Constitution (1791)

Democracy, Sovereignty, and the Struggle over Cherokee Removal (1836)

Banking and Politics in Antebellum New York (1838)

Property, Suffrage, and the "Right of Revolution" in Rhode Island, 1842

Debt and Democracy: The New York Constitutional Convention of 1846

The Struggle Over Public Education in Early America (1851)

A Nation Divided: The United States and the Challenge of Secession (1861)

Reconstruction A: The Crisis of 1877

Reconstruction B: Jury Rights in Virginia, 1877-1880

An Australian Ballot for California? (1891)

Labor, Capital, and Government: The Anthracite Coal Strike of 1902

The Jungle and the Debate over Federal Meat Inspection in 1906

The Battle Over the Initiative and Referendum in Massachusetts (1918)

Regulating Radio in the Age of Broadcasting (1927)

The Pecora Hearings (1932-34)

Martin Luther King and the Struggle for Black Voting Rights (1965)

Democracy and Women’s Rights in America: The Fight over the ERA (1982)

Manufacturing Constituencies: Race and Redistricting in North Carolina, 1993

Leadership and Independence at the Federal Reserve (2009)

Citizens United and Corporate Speech (2010)

Do you use the case method to spark discussion and debate on topics outside of business disciplines? Let us know .

Related Articles

We use cookies to understand how you use our site and to improve your experience, including personalizing content. Learn More . By continuing to use our site, you accept our use of cookies and revised Privacy Policy .

Case Method Project

• Harvard Business School →
• Case Method Project →

Bringing case method teaching to high schools & colleges: U.S. History, Government, Civics & Democracy

About the project  .

The Case Method Project is an initiative formed to achieve two goals:

• Bring case method teaching to high schools and colleges
• Use this methodology to deepen students’ understanding of American democracy

Based on the highly successful experience of Harvard Business School and other graduate and professional programs that use case-based teaching, we believe the case method can be employed to strengthen high school and college education as well, ensuring a more exciting, relevant, and effective experience for students and teachers across a range of subjects. We also believe the case method can be especially effective at engaging students with topics in history and democracy and that it presents a unique opportunity to help reverse the broad decline in civic education – and civic engagement – in the United States.

Curriculum  

For current partners  .

Already working with the Case Method Project?

Connect to other educators in our network and download case materials via ShareVault .

For Prospective Partners  

Interested in learning more about the Case Method Project?

Find out how to bring the case method to your school.

Eleanor Cannon Houston, TX Eleanor Cannon Houston, TX

Maureen O’Hern Dorchester, MA Maureen O’Hern Dorchester, MA

Michael Gordon Munster, IN Michael Gordon Munster, IN

“ I have had few weeks in teaching that I enjoyed as much as doing this case....My biggest dilemma now is how many cases I want to fit into the year. ”

In the News

A Better Way to Teach History

• The Atlantic

Rewriting History

• HBS Alumni Bulletin

All Hail Partisan Politics

• Harvard Gazette

How to Teach Civics in School

• The Economist

HYPOTHESIS AND THEORY article

This article is part of the research topic.

Using Case Study and Narrative Pedagogy to Guide Students Through the Process of Science

Molecular Storytelling: A Conceptual Framework for Teaching and Learning with Molecular Case Studies Provisionally Accepted

• 1 School of Interdisciplinary Arts and Sciences, University of Washington Bothell, United States
• 2 Institute for Quantitative Biomedicine, Rutgers, The State University of New Jersey, United States
• 3 Research Collaboratory for Structural Bioinformatics Protein Data Bank, Rutgers, The State University of New Jersey,, United States

The final, formatted version of the article will be published soon.

Molecular case studies (MCSs) provide educational opportunities to explore biomolecular structure and function using data from public bioinformatics resources. The conceptual basis for the design of MCSs has yet to be fully discussed in the literature, so we present molecular storytelling as a conceptual framework for teaching with case studies. Whether the case study aims to understand the biology of a specific disease and design its treatments or track the evolution of a biosynthetic pathway, vast amounts of structural and functional data, freely available in public bioinformatics resources, can facilitate rich explorations in atomic detail. To help biology and chemistry educators use these resources for instruction, a community of scholars collaborated to create the Molecular CaseNet. This community uses storytelling to explore biomolecular structure and function while teaching biology and chemistry. In this article, we define the structure of an MCS and present an example. Then, we articulate the evolution of a conceptual framework for developing and using MCSs. Finally, we related our framework to the development of technological, pedagogical, and content knowledge (TPCK) for educators in the Molecular CaseNet. The report conceptualizes an interdisciplinary framework for teaching about the molecular world and informs lesson design and education research.

Keywords: Molecular education, Case studies, Technological pedagogical and content knowledge (TPCK), Molecular structure and function, molecular visualization, Bioinformatics education, conceptual modeling

Received: 31 Jan 2024; Accepted: 23 Apr 2024.

Copyright: © 2024 Trujillo and Dutta. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Prof. Caleb M. Trujillo, University of Washington Bothell, School of Interdisciplinary Arts and Sciences, Bothell, United States

People also looked at

Using Active Learning Techniques in Ongoing Bible Study Groups

Four tips for ensuring this model’s success in your church..

• Lifeway Adults

April 23, 2024

Church leaders are constantly seeking ways to drive group engagement and learning. Although a lecture-style model may be comfortable for the leader, this method may not fit the learning preferences of everyone in the group. Moreover, going through the lesson content in the same lecture format week after week can lead to disengagement over time. To address this issue, academic institutions across the country have adopted an active learning methodology.

Starting in the fall of 2024, The Gospel Project Bible study for adults will employ the active learning method to enhance learning and engagement. However, trying new teaching methods may sound daunting for leaders. Below is an explanation of the active learning method, along with four tips for ensuring this model’s success in your church.

Making the Change to Active Learning

Active learning is a teaching method in which the group is asked to review new lesson materials prior to engaging with the lesson in a group setting. For instance, they may read an article or pertinent content pertaining to the session before group time and then engage with the lesson via group activities designed for multiple learning styles. Leaders, however, may wonder how they can encourage the group to prepare for the lesson each week when many of them may want just to show up.

1. Leadership from Above

It is crucial to have leadership support for the active learning model. The group is much more likely to consistently prepare beforehand for the group time when they hear their pastors supporting this model. Pastors and ministry leaders can discuss how excited the church is to adopt this learning method while they highlight the available groups. As time goes on, they can share stories about how this new model has helped those attending these Bible studies understand the Scriptures and grow in their walk with Christ more so that others can see how active learning is beneficial.

2. Leadership at the Group Leader Level

Similarly, group leaders must communicate the new expectations to their groups and be excited about it! Active learning benefits group leaders also because they can spend more time answering questions about the Scripture passage and applying the concepts than they do setting up the context. The group has begun processing the content on their own time already.By expecting the group to prepare in advance, leaders can jump into exploring and applying the main message of the Scripture passage.

3. Communicate How the Active Learning Addresses Multiple Learning Styles

One challenge of a lecture teaching model is that the key concepts are communicated in one way. Even if the group reads ahead of group time – the lecture format leaves little time for engaging with the content in multiple learning styles, such as visual, auditory, social, kinesthetic, etc. However, using the active learning method enables the group time to vary in multiple learning styles. Communicating the opportunity for enhanced learning and providing examples of how this method caters to multiple learning styles will help the group understand the value of active learning.

For example, you could place the group into pairs to share their thoughts on questions pertaining to the material or role-play a scenario which engages social learning. You could use the group time to play a game or build something illustrating a key concept, engaging in kinesthetic learning. Some other examples include evaluating a case study or debating a topic pertaining to the lesson. Thus, active learning engages several learning styles instead of catering to one, creating the opportunity for the group to engage with Scripture in the way God wired them.

4. Provide Leader Training

Of course, it is crucial to provide leader training for the active learning model. During the training, model active learning by expecting your leaders to watch or read some of the material in advance and then pick a few group activities to model the concepts. Encourage your leaders to observe others using active learning techniques.

With support from church staff and ample training for group leaders, active learning techniques will help groups thrive, as everyone engages with the lesson before group gatherings, and apply concepts better by leveraging multiple learning styles.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Review Article
• Open access
• Published: 23 April 2024

Research on flipped classrooms in foreign language teaching in Chinese higher education

• Wen Kong 1 ,
• Di Li 2 &
• Quanjiang Guo   ORCID: orcid.org/0000-0002-7846-1363 3  

Humanities and Social Sciences Communications volume  11 , Article number:  525 ( 2024 ) Cite this article

Metrics details

• Language and linguistics

This review examines 233 articles published in Chinese academic journals between 2011 and 2021, documenting the state of research concerning flipped classrooms (FCs) in foreign language teaching within the context of higher education in China. Employing the methodological approach of a scoping review, the investigation is underpinned by the five-stage framework articulated by Arksey and O’Malley. The results reveal a notable surge in FC-related studies between 2013 and 2017, with a subsequent decline in scholarly attention. The majority of the reviewed studies on FCs focused on English instruction at the college level, with a conspicuous dearth of inquiry into the application of FCs in the teaching of other foreign languages. All studies were categorized as either empirical or non-empirical, and the most frequently used instruments for data collection were surveys and interviews; case studies were underrepresented in the literature. Early studies focused on the introduction of the new model, while more recent investigations focused on the impact of its implementation. The findings of the in-depth content analysis unearthed a prevailing trend of high learner satisfaction with the FC model, along with favorable direct and indirect educational outcomes. Noteworthy factors influencing the efficacy of FCs included learners’ foreign language proficiency and their self-regulation or self-discipline abilities. The paper concludes with a discussion of the challenges in FC implementation and a call for future research on this promising pedagogy.

Similar content being viewed by others

The implementation of a flipped classroom approach at a UK dental school

Rebecca S. L. Binnie & Stephen J. Bonsor

Effectiveness of the flipped classroom model on students’ self-reported motivation and learning during the COVID-19 pandemic

José María Campillo-Ferrer & Pedro Miralles-Martínez

Content validity of the Constructivist Learning in Higher Education Settings (CLHES) scale in the context of the flipped classroom in higher education

Turki Mesfer Alqahtani, Farrah Dina Yusop & Siti Hajar Halili

Introduction

The flipped classroom (FC), also known as the “inverted classroom”, is a pedagogical approach that first emerged in the 1980s and came into more widespread use in the 2000s (Baker, 2000 ; Bergmann and Sams, 2012 ; Khan, 2012 ). It has gained prominence as advances in technology afford increasing opportunities for ubiquitous access to a variety of online resources. The FC model removes in-class lectures, freeing up classroom time for more in-depth exploration of topics through discussion with peers or problem-solving activities facilitated by instructors. The removed content is often delivered to learners through pre-class materials like video recordings. As a result, in the FC, learning activities that are active and social occur inside the classroom while most information transmission occurs outside the classroom. Today, the FC has been implemented in many different disciplines and in schools and universities around the world (Akcayir and Akcayir, 2018 ).

Proponents of the FC assert its pedagogical merits on several fronts. First, it alleviates the constraints associated with requiring all learning to happen at the same time and place, furnishing learners with an individualized education that enables flexible online study at their own pace as long as an internet connection is available (Hung, 2014 ). Second, it allocates class time to the cultivation of learners’ higher-order cognitive skills, emphasizing application, analysis, and evaluation, as opposed to lower-order skills such as knowledge and comprehension (Brinks-Lockwood, 2014 ; Lee and Wallace, 2018 ). Third, in contrast to traditional lecturing, the FC is a student-centered approach emphasizing engagement and active learning (Steen-Utheim and Foldnes, 2018 ), fostering students’ autonomy by endowing them with heightened responsibility for their learning (Brinks-Lockwood, 2014 ; O’Flaherty and Philips, 2015 ).

Vygotsky’s social constructivism ( 1978 ) has frequently been adopted as a theoretical foundation for designing learning experiences in technologically rich environments (Marzouki et al., 2017 ), and this framework highlights the particular benefits of technology-enhanced FC pedagogy (Jarvis et al., 2014 ). As mentioned above, in an FC model, learners can watch pre-recorded videos in their own time before class to remember basic information and understand concepts as they prepare for classroom activities, while the higher-order skills of analyzing, applying, evaluating, and creating can be collaborative and interactive, taking place in class with the guidance of a teacher, and thus facilitating progression within the learners’ proximal developmental zone.

Since its introduction in foreign language teaching (FLT) in China in 2011, the FC has attracted increasing research attention and has been welcomed by foreign language teachers (Yan and Zhou, 2021 ). Over the past decade, the Ministry of Education of the People’s Republic of China has exerted increasing pressure on higher education institutions to transition from traditional teacher-centered lecture-style approaches to innovative methods integrating technology and the internet, with the goals of enhancing learning, sustaining student engagement, and improving student satisfaction (Ministry of Education of People’s Republic China, 2021 ). The FC model, combined with traditional face-to-face teaching and personalized online learning, has emerged as a popular strategy in China to meet ministry requirements while delivering cost-effective and learner-centered curricula in response to the increasing student enrollment in higher education.

Despite the wide adoption of FCs in FLT in China, literature reviews about their implementation and effects have been notably scarce in the last decade. A search of the China National Knowledge Infrastructure (CNKI), the largest national research and information publishing company housing China’s most extensive academic database, revealed only three reviews—by Deng ( 2016 ), Qu ( 2019 ), and Su et al. ( 2019 )—published prior to the end of 2021. These reviews primarily focused on FCs in the context of English as a foreign language (EFL) education, overlooking most of the over 100 foreign languages taught in Chinese higher education. As a result, these reviews fell short of delivering a comprehensive analysis of research pertaining to FCs, and the reliability and generalizability of their findings in non-EFL contexts are questionable. Moreover, Deng ( 2016 ) and Su et al.’s (2019) reviews included all published papers without establishing clear inclusion and exclusion criteria. For example, they did not exclude articles that made a passing or token reference to the FC model, short papers of only one or two pages in length, book reviews, or editorials. Qu’s study ( 2019 ), on the other hand, was constrained in scope to articles within the Chinese Social Sciences Citation Index (CSSCI), a sub-database developed by Nanjing University of China Academy of Social Sciences Research Evaluation Center and the Hong Kong University of Science and Technology, and thus omitted relevant contributions from other academic journals. The CNKI incorporates both the CSSCI and the Core Journals of China (CJC), an equally significant sub-database overseen by the Peking University Library and experts from relevant institutions. Given the exclusion of the latter, a reevaluation of the scope and potential limitations of Qu’s study is warranted.

Thus, there persists an imperative for a comprehensive synthesis of the extant studies on FCs in FLT within Chinese higher education over the past decade. The restricted visibility of studies conducted in China, owing to their publication in Chinese and confinement to Chinese academic journals, makes it difficult for international researchers and practitioners to access and comprehend this body of literature. Such understanding among the global academic community is necessary for exploring both the strengths and limitations of FCs in diverse cultural and linguistic contexts.

Research method

The current study adopts a scoping review approach based on the methodological framework developed by Arksey and O’Malley ( 2005 ) to provide both quantitative and qualitative data for researchers and practitioners.

A scoping review is a relatively new approach to synthesizing research data which has been gaining popularity in many disciplines (Davis et al., 2009 ; Daudt et al., 2013 ). It is often undertaken as an independent project when a research area is complex, and no review of that area has previously been made available. A scoping review serves to highlight the relevant literature to researchers with the aim of rapidly mapping the key concepts characterizing a research area and the main sources and types of evidence available (Arksey and O’Malley, 2005 ; Mays et al., 2005 ; Levac et al., 2010 ). According to Arksey and O’Malley ( 2005 ), this kind of review addresses four goals: to examine the extent, range, and nature of research activity; to determine the value of undertaking a full systematic review; to summarize and disseminate research findings; and to identify research gaps in the existing literature. The scoping review is increasingly being employed in the field of foreign language education to provide a comprehensive view of FLT studies, identify implications for theory and pedagogy, or inform subsequent in-depth reviews and empirical studies (Chan et al., 2022 ; Hillman et al., 2020 ; Tullock and Ortega, 2017 ).

The difference between a scoping review and a narrative or traditional literature review lies in the transparency of the review process. A narrative review usually depends on the author’s own knowledge or experience to describe the studies reviewed and uses an implicit process to provide evidence (Garg et al., 2008 ). The reader cannot determine how much literature has been consulted or whether certain studies have been ignored due to contradictory findings. A scoping review, in contrast, uses an explicit, rigorous, and systematic approach to retrieve relevant articles to ensure the transparency and replicability of the data extraction process. For example, the methodological framework adopted by Arksey and O’Malley ( 2005 ) for conducting a scoping study comprises five stages: identifying the research questions; identifying relevant studies; selecting studies for inclusion; charting the data; and collating, summarizing, and reporting the results. By presenting the process and results in an accessible and summarized format, reviewers are in a position to illustrate the field of interest in terms of the volume, nature, and characteristics of the primary research, enabling researchers, practitioners, and policymakers to make effective use of the findings.

Figure 1 presents the process of the scoping review in the current study based on the five-stage methodological framework developed by Arksey and O’Malley ( 2005 ).

Process of the scoping review.

Process of the scoping review

Identifying research questions.

This scoping review is driven by four research questions:

RQ1. What is the current state of FC research in FLT within the context of higher education in China?

RQ2. What research methods and instruments have been employed in the included FC studies?

RQ3. What research foci and trends are displayed in the included FC studies?

RQ4. What are the major findings of the included FC studies?

RQ1 aims to provide an overview of studies on FCs in FLT in Chinese higher education by providing details about the basic information about existing publications, such as the number of publications per year and the distribution of publications by foreign language context. RQ2 leads to a classification of the research methods and instruments used to collect data in FC research. RQ3 explores the topics and trends in FC research over the past decade with the help of the literature visualization and analysis tool CiteSpace5.8R3. RQ4 reveals the effects of the FC model on direct and indirect educational outcomes, learners’ satisfaction with FCs, and the factors influencing the impact of FCs, as documented in the reviewed sources.

Searching for relevant studies

To be as comprehensive as possible in identifying primary evidence and to ensure the quality of the published articles, we searched both CSSCI and CJC in the CNKI database. The key search terms were developed and categorized based on two dimensions according to the purpose of the review. One dimension related to teaching or learning in FCs, while the other dimension related to the types of foreign languages. The key search terms and search methods are listed in Table 1 .

As the FC approach was introduced into FLT in China in 2011, the search included articles published between 2011 and 2021. Further inclusion and exclusion criteria were developed to focus on the scope of the review; these are outlined in Table 2 .

Study selection

Figure 2 shows a process diagram of the study selection process, which consisted of four phases: searching the databases; identifying the total number of articles in each database; screening titles, abstracts, and full texts; and selecting eligible articles for inclusion.

Flowchart diagram for article selection.

The final database search was conducted on January 16, 2022, and resulted in the identification of a total of 333 articles. Subsequently, all potentially relevant articles went through a three-step screening process. The first step excluded 9 duplicates. The second step excluded irrelevant articles by screening titles and abstracts; 37 articles were removed at this stage as they were book reviews, conference proceedings, reports, editorials, or other non-refereed publications. The third step filtered articles by screening full texts; 54 articles were excluded because they made only passing reference to the FC or were not related to higher education. This meticulous selection yielded a corpus of 233 articles suitable for in-depth analysis, each of which was scrutinized by the authors to confirm its suitability for inclusion. During the selection process, the 233 articles were also systematically categorized into two groups: 131 non-empirical and 102 empirical studies. The non-empirical studies were further divided into two subcategories. The first type was literature reviews; the second type was those drawing on personal observations, reflections on current events, or the authority or experience of the author (Dan, 2021 ). The empirical studies used a variety of systematic methods of collecting materials and analyzing data, including quantitative methods (e.g., survey, correlational research, experimental research) and/or qualitative methods (e.g., interview, case study, record keeping, observation, ethnographic research) (Dan, 2021 ).

Data charting and collation

The fourth stage of Arksey and O’Malley’s scoping review framework is the charting of the selected articles. Summaries of each study were developed. for all studies, these summaries included the author, year of publication, citations per year, foreign language taught, and a brief description of the outcomes. For empirical sources, details related to the research design, study population, and sample size were also provided. Tables 3 and 4 list the top ten most-cited non-empirical and empirical sources. In Table 4 , which references experimental and control groups in results summaries, the experimental group (EG) was the group that took courses in the FC model, while the control group (CG) took courses in a traditional classroom.

Results and analysis

In accordance with the fifth stage of Arksey and O’Malley’s framework for a scoping review, the findings from the 233 included studies are summarized and discussed in the following three sections. Section 4.1 summarizes basic information regarding the included studies; section 4.2 presents a holistic analysis of the research foci and trends over time using keyword clustering analysis and keyword burst analysis; and section 4.3 offers an in-depth content analysis focusing on the categorization of the included studies and discussion of the major findings.

Basic information on the included studies

Distribution by year of publication.

As Fig. 3 shows, the first studies on FCs in the field of FLT in China emerged in 2013. The number of such studies began to steadily increase and reached a peak in 2016 and 2017. Although there was some decrease after that, the FC model has continued to attract research attention, in line with global trends. According to Akçayir and Akçayir’s (2018) review of the literature on FCs published in Social Sciences Citation Index (SSCI) journals as of 31 December 2016, the first article about the FC was published in 2000, but the second was not published until more than a decade later, in 2012; 2013 was also the year that FC studies became popular among scholars. A possible explanation for this increase in interest is the growing availability of internet technologies and the popularity of online learning platforms, such as MOOCs and SPOCs (Small Private Online Courses), along with the view of the FC as a promising model that can open doors to new approaches in higher education in the new century.

Number of articles published by year.

Distribution by foreign language

Figure 4 shows the distribution of foreign languages discussed in the FC literature. The FC model was mainly implemented in EFL teaching (93%), which reflects the dominance of English in FLT in Chinese higher education. Only five articles discussed the use of FC models in Japanese teaching, while one article was related to French teaching. Ten non-empirical studies (4%) reported the feasibility of FC models in FLT without mentioning a specific foreign language.

Distribution by foreign language type.

Research methods of the included studies

Figure 5 shows a breakdown of the methodologies adopted by the studies included in our review. Among the 131 non-empirical studies, three were literature reviews, while the remaining 128 (55%) were descriptive studies based on the introduction of the FC model, including descriptions of its strengths and associated challenges and discussions of its design and implementation in FLT.

Methodological paradigms.

Of the 102 empirical studies, 60 (26%) used quantitative methods for data collection, eight (3%) used qualitative methods, and 34 (15%) used mixed methods. It is interesting to note that although quantitative methods are more common in FC studies, seven of the top ten most-cited empirical studies (as listed above in Table 4 ) used mixed methods. A potential reason may be that research findings collected with triangulation from various data sources or methods are seen as more reliable and valid and, hence, more accepted by scholars.

A breakdown of the data collection approaches used in the 102 reviewed empirical studies is displayed in Table 5 . It is important to note that most studies used more than one instrument, and therefore, it is possible for percentages to add up to more than 100%. The survey, as a convenient, cost-effective, and reliable research method, was the tool most frequently used to gain a comprehensive picture of the attitudes and characteristics of a large group of learners. Surveys were used in 79 of the 102 studies—73 times with learners and six times with teachers—to explore students’ learning experiences, attitudes, and emotions, as well as teachers’ opinions. Some studies used paper-based surveys, while others used online ones. Interviews with learners were used in 33 studies to provide in-depth information; one study used interviews with teachers. Surveys and interviews were combined in 24 studies to obtain both quantitative and qualitative data. Other research approaches included comparing the test scores between experimental and control groups (used in 25 studies) or using the results of course assessments (17 studies) to investigate the effects of the FC on academic performance. Learners’ self-reports (9 studies) were also used to capture the effects of the FC on learners’ experience and cognitive changes that could not be obtained in other ways, while one study used a case study for a similar purpose. Teachers’ class observations and reflections were used in eight studies to evaluate students’ engagement, interaction, activities, and learning performance.

Holistic analysis of the research foci and the changing trends of the included studies

A holistic analysis of the research foci in studies of FCs in China was conducted using CiteSpace5.8.R3, a software developed by Chaomei Chen ( http://cluster.cis.drexel.edu/~cchen/citespace/ , accessed on 20 February 2022), to conduct a visual analysis of the literature. This software can help conduct co-citation analysis, keyword co-occurrence analysis, keyword clustering analysis, keyword burst analysis, and social network analysis (Chen, 2016 ). In this study, keyword clustering analysis and keyword burst analysis were chosen to capture important themes and reveal changing trends in FC research.

Keyword clustering analysis primarily serves to identify core topics in a corpus. Figure 6 presents a graph of the top ten keyword clusters identified in the included studies. In this graph, the lower the ID number of a given cluster, the more keywords are in that cluster. As shown in the top left corner of Fig. 6 , the value of modularity q is 0.8122, which is greater than the critical value of 0.3, indicating that the clustering effect is good; the mean silhouette value is 0.9412, which is >0.5, indicating that the clustering results are significant and can accurately represent hot spots and topics in FC research (Hu and Song, 2021 ). The top ten keyword clusters include #0翻转课堂 (flipped classroom), #1大学英语 (college English), #2 MOOC, #3教学模式 (teaching model), #4元认知 (metacognition), #5微课 (micro lecture), #6微课设计 (micro lecture design), #7英语教学 (English teaching), #8 SPOC, and #9 POA (production-oriented approach).

The graph of the top ten keyword clusters.

Keyword burst analysis is used to showcase the changes in keyword frequencies over a given period of time. By analyzing the rise and decline of keywords, and in particular, the years in which some keywords suddenly become significantly more prevalent (“burst”), we can identify emerging trends in the evolution of FC research. Figure 7 displays the 11 keywords with the strongest citation bursts. We can roughly divide the evolution of FC research documented in Fig. 7 into two periods. The first period (2014 to 2017) focused on the introduction of the new model and the analysis of its feasibility in FLT. The keywords that underwent bursts in this period included “MOOC”, “自主学习” (independent learning), “模式” (model), “学习模式” (learning model), “教师话语” (teacher discourse), “茶文化” (tea culture), and “可行性” (feasibility). The reason for the appearance of the keyword “tea culture” lies in the fact that three articles discussing the use of FCs in teaching tea culture in an EFL environment were published in the same journal, entitled Tea in Fujian , during this period. The second period (2018–2021) focused on the investigation of the effect of FCs and the design of micro lectures. Keywords undergoing bursts during this period included “互联网+” (internet plus), “课堂环境” (classroom environment), “教学效果” (teaching effect), and “微课设计” (micro lecture design). The latter two topics (“teaching effect” and “micro lecture design”) may continue to be prevalent in the coming years.

Top 11 keywords with the strongest citation bursts.

In-depth content analysis of the included studies

Along with the findings from the keyword clustering analysis and keyword burst analysis, an open coding system was created to categorize the research topics and contents of the 233 articles for in-depth analysis. Non-empirical and empirical studies were classified further into detailed sub-categories based on research foci and findings. It is important to note that some studies reported more than one research focus. For such studies, more than one sub-category or more than one code was applied; therefore, it is possible for percentages to add up to more than 100%. The findings for each category are discussed in detail in the following sections.

Non-empirical studies

The 131 non-empirical studies can be roughly divided into two categories, as shown in Table 6 . The first category, literature reviews, has no sub-categories. The second, descriptive studies, includes discussions of how to use FCs in FLT; descriptions of the process of implementing the FC in FLT; and comparisons between FCs and traditional classes or comparisons of FCs in Chinese and American educational contexts.

The sub-categories of “introduction and discussion” and “introduction and description” in Table 6 comprise 91.6% of the non-empirical studies included in our review. The difference between them lies in that the former is based on the introduction of the FC literature, while the latter is based both on the introduction of the FC literature and exploration of researchers’ teaching experience; the latter might have become qualitative studies if researchers had gone further in providing systematic methods of collecting information or an analysis of the impact of FCs.

Empirical studies

The 102 empirical studies were divided into four categories based on the domain of their reported findings: the effect of FCs on learners; learners’ satisfaction with FCs; factors influencing FCs; or other research foci. Each group was further classified into more detailed sub-categories.

Effect of FCs on learners

Studies on the effect of FCs on learners were divided into two types, as presented in Table 7 : those concerned with the direct effect of FCs on learning performance and those exploring the indirect effect on learners’ perceptions. Eight codes were applied to categorize the direct effect of FCs on learning performance, which was usually evaluated through test scores; 14 codes were used to categorize the indirect effect of FCs on learners’ perceptions, which were usually investigated through surveys or questionnaires. We do not provide percentages for each code in Tables 7 – 9 because, given that the total number of empirical studies is 102, the percentages are almost identical to the frequencies.

The results shown in Table 7 reveal that 84 studies of direct educational outcomes reported that FCs had a positive effect on basic language skills, content knowledge, and foreign language proficiency. Of these, 64 were concerned with the positive effect of FCs on foreign language proficiency, speaking skills, or listening skills. This result might be explained by the features of FCs. The main difference between FCs and traditional classrooms is that the teaching of content in FCs has been removed from the classes themselves and is often delivered to the students through video recordings, which can be viewed repeatedly outside of the class. In-class time can thus be used for discussion, presentations, or the extension of the knowledge provided in the videos. It is evident that students have more opportunities to practice listening and speaking in FCs, and foreign language proficiency is naturally expected. Only three studies reported that FCs had no effect or a negative effect on the development of foreign language proficiency, speaking, listening, and writing skills. Yan and Zhou ( 2021 ) found that after the FC model had been in place for one semester, college students’ reading abilities improved significantly, while there was no significant improvement in their listening and writing abilities. Yin ( 2016 ) reported that after FC had been implemented for one semester, there was no significant difference in college students’ speaking scores.

A total of 96 studies reported positive effects on indirect educational outcomes, including: boosting learners’ motivation, interest, or confidence; enhancing engagement, interaction, cooperation, creativity, independent learning ability, or critical thinking ability; fostering information literacy, learning strategies, learning efficiency, or self-efficacy; or relieving stress or anxiety. The most frequently documented indirect effect of FCs is improvement in students’ independent learning ability. Only one study found that the FC did not significantly increase student interest in the course (Wang, 2015 ). Similarly, only one study found that students’ anxiety in the FC was significantly higher than that in a traditional class (Gao and Li, 2016 ).

Learners’ satisfaction with FCs

Table 8 presents the results regarding learners’ satisfaction with FCs. Nine codes were used to categorize the different aspects of learners’ satisfaction investigated in the 102 empirical studies. Some researchers represented learner satisfaction using the percentage of students choosing each answer on a five-point Likert scale from 1 (not at all satisfied) to 5 (very satisfied), while others used average scores based on Likert scale values. For the purposes of our synthesis of findings, if the percentage is above 60% or the average score is above 3, the finding is categorized as satisfied; otherwise, it is categorized as not satisfied.

The results in Table 8 show that among the nine aspects investigated, teaching approach and learning outcomes were most frequently asked about in the research, and learners were generally satisfied with both. Only one study (Li and Cao, 2015 ) reported significant dissatisfaction; in this case, 76.19% of students were not satisfied with the videos used in college English teaching due to their poor quality.

Factors influencing the effect of FCs

Eleven factors were found to influence the effect of FCs; these are categorized in Table 9 .

The results shown in Table 9 indicate that learners’ foreign language proficiency and self-regulation or self-discipline abilities are two important factors influencing the effect of FCs. Learners with high foreign language proficiency benefited more from FCs than those with low foreign language proficiency (Lv and Wang, 2016 ; Li and Cao, 2015 ; Wang and Zhang, 2014 ; Qu and Miu, 2016 ; Wang and Zhang, 2013 ; Cheng, 2016 ; Jia et al., 2016 ; Liu, 2016 ), and learners with good self-regulation and self-discipline abilities benefited more than those with limited abilities (Wang and Zhang, 2014 ; Lu, 2014 ; Lv and Wang, 2016 ; Dai and Chen 2016 ; Jia et al. 2016 ; Ling, 2018 ). It is interesting to note that two studies explored the relationship between gender and FCs (Wang and Zhang, 2014 ; Zhang and He, 2020 ), and both reported that girls benefited more from FCs because they were generally more self-disciplined than boys.

Studies with other research foci

There were six studies with other research foci, three of which investigated teachers’ attitudes toward FCs (Liao and Zou, 2019 ; Zhang and Xu, 2018 ; Zhang et al., 2015 ). The results of the surveys in these three studies showed that teachers generally held positive attitudes towards FCs and felt that the learning outcomes were better than those of traditional classes. However, some problems were also revealed in these studies. First, 56% of teachers expressed the desire to receive training before using FCs due to a lack of theoretical and practical expertise regarding this new model. Second, 87% of teachers thought that the FC increased their workload, as they were spending a significant amount of time learning to use new technology and preparing online videos or materials, yet no policy was implemented in the schools to encourage them to undertake this work. Third, 72% of teachers felt that the FC increased the academic burden students faced in their spare time (Zhang and Xu, 2018 ; Zhang et al., 2015 ). The final three studies include Cheng’s ( 2016 ) investigation of the mediative functions of college EFL teachers in the FC, Wang and Ma’s ( 2017 ) construction of a model for assessing the teaching quality of classes using the FC model, and Luo’s ( 2018 ) evaluation of the learning environment of an FC-model college English MOOC.

Discussion and conclusions

This investigation employed literature visualization to systematically analyze 233 research papers sourced from CSSCI and CJC in the CNKI database, thereby conducting a scoping review delineating the landscape of FC research within the domain of FLT in the context of higher education in China.

Our findings in relation to RQ1 highlight a substantial surge in the number of articles relating to FCs in FLT between 2013 and 2017, followed by a discernible, albeit moderate, decrease. Despite this trend, FC studies continue to be of significant interest to foreign language educators and researchers. This may be attributed to Chinese government policies encouraging higher education reform, increased internet access among educators and learners, and the burgeoning popularity of online courses such as MOOCs and SPOCs. However, the majority of the reviewed FC studies were conducted in college English classes, with only 6 studies on classes teaching foreign languages other than English. It seems that foreign language education in China (and in much of the world) has become synonymous with the teaching and learning of English, with other languages occupying a marginal position, struggling to find space in educational programs. In a multilingual world in which each language offers different possibilities for understanding others, their cultures, their epistemologies, and their experiences, this monolingual approach to FLT is dangerous (Liddicoat, 2022 ). The promotion of linguistic diversity in foreign language education policies and research is thus imperative. Another gap that needs to be addressed is the paucity of studies on the implementation of FCs in adult education. The FC model is expected to be potentially effective for teaching adult learners because it is similar in some respects to online distance learning.

In answer to RQ2, we found that the commonly used research methods and instruments in studies of the FC model include surveys, interviews, comparisons of academic measures between EGs and CGs, and course assessments. The case study is the least used method, likely due to limitations such as time demand, researcher bias, and the fact that it provides little basis for the generalization of results to the wider population. However, more case studies are needed in future research on FCs because they can provide detailed and insightful qualitative information that cannot be gathered in other ways.

Our findings regarding RQ3 show that research foci within the FC domain have evolved over time from initial exploration and feasibility discussions to a subsequent focus on the design of FCs incorporating micro-lectures based on MOOC or SPOC structures, and then to the present focus on the examination of FCs’ impacts on learners. The results of the keyword burst analysis indicate that these thematic areas are likely to persist as prominent subjects of research interest for the foreseeable future.

In response to RQ4, our in-depth content analysis found that FCs, on the whole, yield positive outcomes, although isolated studies identify limited negative impacts. FCs are most frequently associated with enhancements in student learning performance, fostering independent learning, promoting engagement and cooperation, and mitigating stress or anxiety. The results of this study suggest that well-designed FCs present a significant opportunity for foreign language educators to revolutionize instructional approaches. Furthermore, well-structured FCs can facilitate the development of learners’ potential while concurrently enabling the seamless integration of digital technology into FLT.

Most learners are satisfied with FCs, particularly with the innovative pedagogical approach of reversing traditional classes. FCs are perceived as beneficial for improving learning outcomes, creating an environment conducive to peer interaction, and gaining immediate teacher feedback and support. In addition, students’ interest in classes is enhanced by the rich and diverse online learning materials uploaded by teachers, which can be accessed conveniently at any time in any place. Furthermore, the dynamic and formative online assessment approach is also welcomed by students because it provides immediate feedback and the ability to discuss any problems they have with teachers or peers online or offline.

However, it is worth noting that most of the reviewed studies on FCs focused on one course, usually over only one semester. Students’ increase in motivation or improvements in learning outcomes might, therefore, be a result of the Hawthorne effect. Compared with the traditional didactic lecture format, the novelty of FCs, when used for the first time, might generate excitement among students, thus increasing their attention and enhancing learning outcomes, but such benefits will diminish over time. Therefore, there is a need to examine whether this model is suitable for large-scale implementation and whether its effects might be sustained over longer periods of implementation.

Learners’ foreign language proficiency and self-regulation or self-discipline abilities are the two key factors influencing the effect of FCs. These two factors are closely related; self-regulation or self-discipline is a prerequisite for successful foreign language learning in FC contexts and plays a crucial role in students’ success in the pre-class sessions for which they are personally responsible. In addition, factors such as learners’ attitudes, expectations of and adaptability to the FC model, the learning tasks and learning environment, the teaching organization and assessment methods, and the learner’s gender also have some impact on the effect of FCs. However, due to the limited number of studies, there is not sufficient evidence to warrant the generalization of any of these effects.

This scoping review highlights some potential challenges that need to be addressed for the effective implementation of FCs.

First, despite the benefits of the FC model, FCs are not equally advantageous to all students due to the self-regulated nature of the model. Many learners have reported difficulties in completing their individual online tasks outside the classroom (Yoon et al., 2021 ). The non-traditional configuration of FCs poses a formidable challenge, particularly for students less inclined to engage in pre-class online activities characterized by a lack of interactivity and for those who are less self-disciplined. Consequentially, students may attend class without having assimilated the pre-assigned material, thereby diminishing the efficacy of this instructional approach. To address this issue, additional support or prompts for students should be provided to remind them of the need to self-regulate their learning. For example, Park and Jo ( 2015 ) employed a learning analytics dashboard displaying visual representations of students’ learning patterns derived from login traces, such as login frequency and interval regularity, within the course’s learning management system. These visual indicators allowed students to monitor their learning engagement and performance in comparison to those of their peers.

Second, a persistent problem with FCs is the inability of students to interact with their peers or receive prompt feedback from instructors after completing independent online learning activities. While some researchers identified a need for teachers to provide immediate online feedback or opportunities for peer discussion, our review of the literature shows that scant attention has been given to this issue. Researchers note that under-stimulation, low perceived control over tasks, and delayed or insufficient feedback in online learning contribute significantly to learner boredom or absenteeism (Yazdanmehr et al., 2021 ; Tao and Gao, 2022 ). Online pedagogical innovations are needed to solve these new problems. For instance, the establishment of online groups employing chat software like QQ or WeChat could facilitate instantaneous feedback or peer interaction through text-based communication, thereby enhancing learners’ satisfaction with FC courses.

Third, despite recognizing the value of FCs in enhancing the learning experience for students, teachers often lack the requisite training to implement FCs effectively. Insights derived from interviews with teachers, as noted in several of the reviewed studies, reveal a pronounced desire for increased opportunities to learn about the underlying theories of FCs and acquire the skills necessary for the translation of FC concepts into pedagogical practice. Specifically, teachers express a need for guidance in creating engaging instructional videos, determining optimal video length to sustain learner interest, and ascertaining the ideal duration for online quizzes to foster optimal learner performance. Further research is required on strategies and technologies that can help teachers produce high-quality videos despite limited time and technical skills. Support from professional communities, institutions, and technology specialists is thus essential for the provision of effective hybrid offline and online instruction.

Fourth, additional research is required to determine whether workloads for students and teachers are increased by the use of FCs. If this is the case, as found in some of the reviewed studies, then the compelling benefits of FCs would be offset by the extra time needed, making it difficult to draw the conclusion that FCs are more efficient than traditional classes. The majority of language teachers, due to limited skills in technology, online environment management, and online interaction, feel too physically and emotionally overworked to expend more time and energy on enhancing teaching effectiveness. With few teachers having excess spare time, the thought of designing and creating new content might discourage even the most enthusiastic teachers.

Finally, robust empirical evidence is needed to evaluate whether FCs can facilitate students’ higher-order thinking through the use of creative technologies and assessment approaches. Constructs such as creativity and critical thinking are not always easily reduced to measurable items on survey instruments or scores on examinations (Haladyna et al., 2002 ).

In conclusion, the insights garnered from this study have the potential to enrich the global discourse on the benefits and limitations of FCs in diverse cultural and linguistic contexts. Our review included literature accessible through CSSCI and CJC in the CNKI database, and while this provides a thorough selection of the Chinese literature on the subject, our search approach may have excluded valuable FC-related papers published in other languages and countries. Consequently, different search criteria might yield different selection and data results. Future researchers are encouraged to undertake more comprehensive literature reviews encompassing broader databases to fill the gaps in our work and to augment the depth and breadth of knowledge in this domain.

Data availability

The raw data for this paper were collected from articles in Chinese Social Sciences Citation Index (CSSCI) journals and A Guide to the Core Journals of China of Peking University (PKU journals) in the database of China National Knowledge Infrastructure (CNKI) ( https://www.cnki.net/ ). The raw data used to support the findings of this study are available from the corresponding author upon request.

Akcayir G, Akcayir M (2018) The flipped classroom: a review of its advantages and challenges. Comput Educ 126:334–345. https://doi.org/10.1016/j.compedu.2018.07.021

Article   Google Scholar  

Arksey H, O’Malley L (2005) Scoping studies: towards a methodological framework. Int J Soc Res Methodol 8:19–32. https://doi.org/10.1080/1364557032000119616

Baker JW (2000) The ‘Classroom Flip’: using web course management tools to become the guide by the side. In: Chambers JA ed Selected papers from the 11th international conference on college teaching and learning. Florida Community College at Jacksonville, Jacksonville, FL

Google Scholar  

Bergmann J, Sams A (2012) Flip your classroom: reach every student in every class every day. International Society for Technology in Education, Eugene, OR

Brinks-Lockwood R (2014) Flip it! Strategies for the ESL classroom. University of Michigan Press, Ann Arbor, MI

Book   Google Scholar  

Cao P (2020) Construction of blended learning and evaluation of its effect based on a flipped class approach in an ESP course. Foreign Lang World 6:87–94

Chan L, Woore R, Molway L, Mutton T (2022) Learning and teaching Chinese as a foreign language: a scoping review. Rev Educ 10:1–35. https://doi.org/10.1002/rev3.3370

Chen C (2016) CiteSpace: a practical guide for mapping scientific literature. Nova Science Publishers, Hauppauge, NY, USA

Cheng Y (2014) Facing the challenge and flipping ourselves—opportunities and challenges faced by foreign language teachers under the new paradigm of education. Technol Enhanc Foreign Lang 157:44–47

Cheng X (2016) An empirical study of implementations of mediative functions of college EFL teachers in flipped classrooms. Technol Enhanc Foreign Lang 168:48–53

Cui Y, Wang Y (2014) Flipped class model and its application to college English teaching. China Educ Technol 334:116–121

Dan V (2021) Empirical and nonempirical methods. https://www.ls1.ifkw.uni-muenchen.de/personen/wiss_ma/dan_viorela/empirical_and_non_empirical.pdf . Accessed 23 Aug 2021

Daudt HM, van Mossel C, Scott SJ (2013) Enhancing the scoping study methodology: a large, inter-professional team’s experience with Arksey and O’Malley’s framework. BMC Med Res Methodol 13:48, http://www.biomedcentral.com/1471-2288/13/48

Article   PubMed   PubMed Central   Google Scholar  

Dai C, Chen J (2016) An analysis of contributing factors of college English flipped classroom with MOOC philosophy. Technol Enhanc Foreign Lang 172:35–41

Davis K, Drey N, Gould D (2009) What are scoping studies? A review of the nursing literature. Int J Nurs Stud 46:1386–1400. https://doi.org/10.1016/j.ijnurstu.2009.02.010

Article   PubMed   Google Scholar  

Deng D (2016) A review of the research on the application of the flipped classroom model in college English teaching. Foreign Lang World 175:89–96

Dou J, Wen S (2015) The teaching reform exploration of college English flipped classroom based on APP. Heilongjiang Res High Educ 5:162–167

Gao Z, Li J (2016) English classroom anxiety of Chinese learners: flipped vs. traditional. Technol Enhanc Foreign Lang 167:37–42

Garg AX, Hackam D, Tonelli M (2008) Systematic review and meta-analysis: When one study is just not enough. Clin J Am Soc Nephrol 3:253–260. https://doi.org/10.2215/CJN.01430307

Haladyna T, Downing S, Rodriguez M (2002) A review of multiple-choice item writing guidelines for classroom assessment. Appl Meas Educ 15:309–334. https://doi.org/10.1207/S15324818AME15035

Hillman S, Selvi AF, Yazan B (2020) A scoping review of world Englishes in the Middle East and North Africa. World Englishes 40:1–17. https://doi.org/10.1111/weng.12505

Hu J, Wu Z (2014) An empirical study on the MOOC-based college English flipped classroom instructional model. Technol Enhanc Foreign Lang 160:40–45

Hu Z, Song J (2021) Research hotspots and trends of online and offline hybrid teaching in China—bibliometric analysis of journal literature based on CNKI (2015–2020). In: 2021 2nd international conference on education, knowledge and information management. IEEE. https://doi.org/10.1109/ICEKIM52309.2021.00032

Hung HT (2014) Flipping the classroom for English language learners to foster active learning. Comput Assist Lang Learn 28:81–96. https://doi.org/10.1080/09588221.2014.967701

Jarvis W, Halvorson W, Sadeque S, Johnston S (2014) A large class engagement(LCE) model based on service-dominant logic (SDL) and flipped classrooms. Educ Res Perspect 41:1–24. http://www.erpjournal.net/

Jia L, Zhang G, Shi C (2016) Flipping medical English reading class based on Wechat public platform and Wechat community. Technol Enhanc Foreign Lang 168:65–69

Jiang Q, Tao Y (2018) The application of “flipped classroom” in teaching MTI translation theory and its effect analysis. Foreign Lang Educ 5:70–74

ADS   Google Scholar  

Jiang Y, Hu J (2018) A study on the large-scale instruction mechanism of SPOC-based college English flipped classroom. Technol Enhanc Foreign Lang 182:9–15

Khan S (2012) The one world schoolhouse: education reimagined. Hodder and Stoughton, London

Lee G, Wallace A (2018) Flipped learning in the English as a foreign language classroom: outcomes and perceptions. TESOL Q 52:62–84

Levac D, Colquhoun H, O’Brien K (2010) Scoping studies: advancing the methodology. Implement. Sci. 5(69):1–9

Li X, Cao H (2015) Research on flipped classroom based on micro-lecture—a case study in college English teaching through videos. Mod Educ Technol 9:70–76. https://doi.org/10.3969/j.issn.1009-8097.2015.09.011

Li X, Wang B (2017) An empirical study on college English flipped classroom model based on context awareness. Technol Enhanc Foreign Lang 178:71–77

Li J, Wu Z (2015) Practice and reflections on flipped college English class. Foreign Lang China 6:4–9. https://doi.org/10.13564/j.cnki.issn.1672-9382.2015.06.002

Liao G, Zou X (2019) Optimizing the teaching design to develop learners’ autonomous study. Educ Res Mon 10:105–111

Liddicoat AJ (2022) Language planning for diversity in foreign language education. Curr Issues Lang Plan 23(5):457–465. https://doi.org/10.1080/14664208.2022.2088968

Ling R (2018) Research on Japanese pronunciation teaching with the flipped classroom model. Jpn Learn Res 4:68–76. https://doi.org/10.13508/j.cnki.jsr.2018.04.010

Article   ADS   Google Scholar  

Liu Y (2016) Research on the construction of flipped classroom model for vocabulary instruction and its effectiveness. Technol Enhanc Foreign Lang 167:43–49

Liu Z, Wu Q (2015) Cultivation of college students’ learning autonomy from the perspective of “Flipped Classroom”. Mod Educ Technol 11:67–72. https://doi.org/10.3969/j.issn.1009-8097.2015.11.010

Lu H (2014) Feasibility analysis on the application of micro-class based “Flipped Classroom” mode in college English teaching. Technol Enhanc Foreign Lang 158:33–36

Luo S (2018) Evaluating the learning environment of MOOC-based college English flipped classrooms. Technol Enhanc Foreign Lang 182:16–22

Lv T, Wang N (2016) A study on the effect of the flipped classroom based on SPOC+teaching resource platform. China Educ Technol 352:85–90

Mays N, Pope C, Popay J (2005) Systematically reviewing qualitative and quantitative evidence to inform management and policy-making in the health field. J Health Serv Res Policy 1:6–20. https://doi.org/10.1258/1355819054308576

Marzouki OF, Idrissi MK, Bennani S (2017) Effects of social constructivist mobile learning environments on knowledge acquisition: a meta-analysis. Int J Interact Mob Technol 11(1):18–39. https://doi.org/10.3991/ijim.v11i1.5982

Ministry of Education of People’s Republic China (2021) 10-year development plan for education information (2011–2020). http://www.moe.gov.cn/srcsite/A16/s3342/201203/t20120313_133322.html . Accessed 30 Dec 2021

O’ Flaherty J, Philips C (2015) The use of flipped classroom in higher education: a scoping review. Internet High Educ 25:85–95. https://doi.org/10.1016/j.iheduc.2015.02.002

Park Y, Jo I-H (2015) Development of the learning analytics dashboard to support students’ learning performance. J Univers Comput Sci 21(1):110–133. https://doi.org/10.3217/jucs-021-01-0110

Qiao H (2017) Study of blended English learning model based on community of inquiry. Technol Enhanc Foreign Lang 176:43–48

Qu S (2019) A content analysis of researches on EFL flipped classrooms in China’s universities. Technol Enhanc Foreign Lang 187:62–68

Qu Q, Miu R (2016) A research on learning strategies of flipped classroom teaching model. China Educ Technol 350:114–119

Shen Y, Sheng Y (2015) Construction of the flipped college English classroom based on Community of Inquiry. Foreign Lang. World 4:81–89

Steen-Utheim AT, Foldnes NA (2018) Qualitative investigation of student engagement in a flipped classroom. Teach High Educ 23:30–324. https://doi.org/10.1080/13562517.2017.1379481

Su X, Liu S, Ma W (2019) The use of flipped classrooms in Chinese college English teaching: a review. Foreign Lang Lit 35:142–148. 1674-6414(2019) 01-0142-07

Tao J, Gao X (2022) Teaching and learning languages online: challenges and responses. System 107:1–9. https://doi.org/10.1016/j.system.2022.102819

Tullock B, Ortega L (2017) Fluency and multilingualism in study abroad: Lessons from a scoping review. System 71:7–21. https://doi.org/10.1016/j.system.2017.09.019

Vygotsky LS (1978) Mind in society: the development of higher psychological processes. Harvard University Press, Cambridge

Wan M(2016) An empirical study on the application of flipped classroom in college English teaching High Educ Explor 5:69–72. www.cnki.net

Wang H (2015) An action research on interpreting teaching based on the flipped classroom. Chin Transl J 1:59–62

Wang X (2014) College foreign language teaching based on MOOC. Heilongjiang Res High Educ 8:157–159

Wang Y (2016) Research on English learning anxiety of non-English majors under flipped class model. J Guangxi Norm Univ: Philos Soc Sci Ed 4:134–139. https://doi.org/10.16088/j.issn.1001-6597.2016.04.020

Wang N, Chen J, Zhang D (2016) SPOC-based flipped classroom of college English: Construction of an efficient learning model. Technol Enhanc Foreign Lang 169:52–57

Wang G, Ma S (2017) A study on college English classroom “Flip Degree” assessment index. Technol Enhanc Foreign Lang 177:23–28

Wang H, Zhang L (2014) The application of flipped classroom in English teaching. Teach Manag 7:141–144. www.cnki.net

Wang S, Zhang L (2014) A study of college EFL learners’ acceptance towards flipped classroom. Mod Educ Technol 3:71–78. https://doi.org/10.3969/j.issn.1009-8097.2014.03.010

Article   CAS   Google Scholar  

Wang X, Zhang C (2013) The application research of flipped classroom in university teaching. Mod Educ Technol 8:11–16. https://doi.org/10.3969/j.issn.1009-8097.2013.08.002

Wang L, Zhao M, Yang W (2018) An empirical study of the instructional model of college oral English flipped classroom based on principles of CDIO engineering education. Technol Enhanc Foreign Lang 180:72–77

Wang Z, Wu M (2017) The analysis of the impact factors on students’ learning behaviors under flipped classroom model. Technol Enhanc Foreign Lang 177:29–34

Wu L (2015) A study on the flipped classroom model in teaching listening and speaking for academic English for general purposes. E-Educ Res 11:81–87. https://doi.org/10.13811/j.cnki.eer.2015.11.013

Xie P (2020) Applying MOOC-based blended learning to the courses of English education. Foreign Lang Educ China 2:43–49

Xu H (2017) An explorative study of college students’ critical thinking under flipped classroom. Technol Enhanc Foreign Lang 173:29–33

Xu T, Li X (2014) Exploration to project-based flipped classroom—new concept, method and technology in English teaching: a case study based on new college English. Foreign Lang China 15:81–87. https://doi.org/10.13564/j.cnki.issn.1672-9382.2014.05.011

Yan J, Zhang W, Yu Y (2016) School-based flipped classroom teaching reform on video-aural-oral course of college English. Mod Educ Technol 2:94–99. https://doi.org/10.3969/j.issn.1009-8097.2016.02.014

Yan Z, Zhou P(2021) Effect of flipped teaching on college students’ EFL acquisition. Foreign Language Learn Theory Pract 2:86–96

Yazdanmehr E, Shirvan ME, Saghafi K (2021) A process tracing study of the dynamic patterns of boredom in an online L3 course of German during COVID-19 pandemic. Foreign Lang Ann 54(3):714–739. https://doi.org/10.1111/flan.12548

Yin H (2016) An empirical study and critical reflection on the flipped classroom model. J Res Educ Ethn Minor 1:25–30

Yoon M, Hill J, Kim D (2021) Designing supports for promoting self-regulated learning in the flipped classroom. J Comput High Educ 33:398–418. https://doi.org/10.1007/s12528-021-09269-z

Yu P (2014) The application of flipped classroom in English teaching. Teach Manag 9:62–64. www.cnki.net

Yu Z, Chen W (2016) The Influence of clicker-aided college English flipped classroom on meta-cognition, cognitive loads and learning achievements. Technol Enhanc Foreign Lang 170:32–37

Zhai X, Lin L (2014) Factors analysis of Chinese learners’ satisfaction in western flipped classroom model (FCM) teaching—an empirical study based on college English. China Educ Technol 327:104–109

Zhang D (2021) Construction and application of a blended golden course framework of college English. Technol Enhanc Foreign Lang 197:71–77

Zhang M, Deng L(2021) Construction and application of “emergent flipped learning” teaching model in the integration of Chinese culture into college English teaching Foreign Language Learn Theory Pract 1:61–70

Zhang M, He X (2020) A study on the adaptability of blended college English learning. Technol Enhanc Foreign Lang. 4:89–94

Zhang M, Sun X (2015) MOOC-based flipped classroom teaching model for follow-up college English courses. Mod Educ Technol 8:81–87. https://doi.org/10.3969/j.issn.1009-8097.2015.08.01

Zhang J, Li K, Du X (2015) College English classroom: based on the survey of the current situation. Mod Educ Technol 7:68–74. https://doi.org/10.3969/j.issn.1009-8097.2015.07.011

Zhang Y, Xu Z (2018) Research on the acceptance of college English teachers’ flipped classroom. Theory Pract Educ 36:53–55

ADS   CAS   Google Scholar  

Zhou P (2015) Flipped classroom based on modern educational technology and its theoretical foundations. Technol Enhanc Foreign Lang 162:72–76

Zhu L, Xu Y, Han J (2021) An approach for the integration of foreign language teaching and information technology. Foreign Lang World 2:46–62

Download references

Acknowledgements

This research was funded by The 14th Five-year Plan for Education Science of Jiangsu Province (Grant number: D/2021/01/79), Changzhou University (Grant number: GJY2021013), and Department of Education of Zhejiang Province, China (Project of Ideological and Political Construction of Courses 2021-337).

Author information

Authors and affiliations.

Department of English, Changzhou University, 213100, Changzhou, Jiangsu Province, China

School of English Education, Guangdong University of Foreign Studies, 510006, Guangzhou, Guangdong Province, China

College of Science & Technology, Ningbo University, 315200, Ningbo, Zhejiang Province, China

Quanjiang Guo

You can also search for this author in PubMed   Google Scholar

Contributions

Conceptualization, WK and Q-JG; methodology, WK; software, DL; validation, WK, DL, and Q-JG; formal analysis, WK and Q-JG; investigation, WK and Q-JG; resources, DL; data curation, DL; writing—original draft preparation, WK and Q-JG; writing—review and editing, WK and Q-JG; visualization, WK and Q-JG; supervision, WK; project administration, WK; funding acquisition, WK and Q-JG. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Quanjiang Guo .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Ethical approval

Ethical approval was not required as the study did not involve human participants.

Informed consent

Informed consent was not required as the study did not involve human participants.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Kong, W., Li, D. & Guo, Q. Research on flipped classrooms in foreign language teaching in Chinese higher education. Humanit Soc Sci Commun 11 , 525 (2024). https://doi.org/10.1057/s41599-024-03019-z

Download citation

Received : 17 October 2023

Accepted : 02 April 2024

Published : 23 April 2024

DOI : https://doi.org/10.1057/s41599-024-03019-z

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

• Columbia University in the City of New York
• University Policies
• Academic Calendar
• Columbia Online
• Office of the Vice Provost for Teaching, Learning, and Innovation

• Resources and Technology
• Teaching Resources

Case Method Teaching and Learning

What is the case method? How can the case method be used to engage learners? What are some strategies for getting started? This guide helps instructors answer these questions by providing an overview of the case method while highlighting learner-centered and digitally-enhanced approaches to teaching with the case method. The guide also offers tips to instructors as they get started with the case method and additional references and resources.

On this page:

What is case method teaching.

• Case Method at Columbia

Why use the Case Method?

Case method teaching approaches, how do i get started.

• Additional Resources

Case method 1 teaching is an active form of instruction that focuses on a case and involves students learning by doing 2 3 . Cases are real or invented stories 4  that include “an educational message” or recount events, problems, dilemmas, theoretical or conceptual issue that requires analysis and/or decision-making.

Case-based teaching simulates real world situations and asks students to actively grapple with complex problems 5 6 This method of instruction is used across disciplines to promote learning, and is common in law, business, medicine, among other fields. See Table 1 below for a few types of cases and the learning they promote.

Table 1: Types of cases and the learning they promote.

For a more complete list, see Case Types & Teaching Methods: A Classification Scheme from the National Center for Case Study Teaching in Science.

Back to Top

Case Method Teaching and Learning at Columbia

The case method is actively used in classrooms across Columbia, at the Morningside campus in the School of International and Public Affairs (SIPA), the School of Business, Arts and Sciences, among others, and at Columbia University Irving Medical campus.

Faculty Spotlight:

Professor Mary Ann Price on Using Case Study Method to Place Pre-Med Students in Real-Life Scenarios

Read more  

Professor De Pinho on Using the Case Method in the Mailman Core

Case method teaching has been found to improve student learning, to increase students’ perception of learning gains, and to meet learning objectives 8 9 . Faculty have noted the instructional benefits of cases including greater student engagement in their learning 10 , deeper student understanding of concepts, stronger critical thinking skills, and an ability to make connections across content areas and view an issue from multiple perspectives 11 . 

Through case-based learning, students are the ones asking questions about the case, doing the problem-solving, interacting with and learning from their peers, “unpacking” the case, analyzing the case, and summarizing the case. They learn how to work with limited information and ambiguity, think in professional or disciplinary ways, and ask themselves “what would I do if I were in this specific situation?”

The case method bridges theory to practice, and promotes the development of skills including: communication, active listening, critical thinking, decision-making, and metacognitive skills 12 , as students apply course content knowledge, reflect on what they know and their approach to analyzing, and make sense of a case. 

Though the case method has historical roots as an instructor-centered approach that uses the Socratic dialogue and cold-calling, it is possible to take a more learner-centered approach in which students take on roles and tasks traditionally left to the instructor. 

Cases are often used as “vehicles for classroom discussion” 13 . Students should be encouraged to take ownership of their learning from a case. Discussion-based approaches engage students in thinking and communicating about a case. Instructors can set up a case activity in which students are the ones doing the work of “asking questions, summarizing content, generating hypotheses, proposing theories, or offering critical analyses” 14 . 

The role of the instructor is to share a case or ask students to share or create a case to use in class, set expectations, provide instructions, and assign students roles in the discussion. Student roles in a case discussion can include: 

• discussion “starters” get the conversation started with a question or posing the questions that their peers came up with; 
• facilitators listen actively, validate the contributions of peers, ask follow-up questions, draw connections, refocus the conversation as needed; 
• recorders take-notes of the main points of the discussion, record on the board, upload to CourseWorks, or type and project on the screen; and 
• discussion “wrappers” lead a summary of the main points of the discussion. 

Prior to the case discussion, instructors can model case analysis and the types of questions students should ask, co-create discussion guidelines with students, and ask for students to submit discussion questions. During the discussion, the instructor can keep time, intervene as necessary (however the students should be doing the talking), and pause the discussion for a debrief and to ask students to reflect on what and how they learned from the case activity. 

Note: case discussions can be enhanced using technology. Live discussions can occur via video-conferencing (e.g., using Zoom ) or asynchronous discussions can occur using the Discussions tool in CourseWorks (Canvas) .

Table 2 includes a few interactive case method approaches. Regardless of the approach selected, it is important to create a learning environment in which students feel comfortable participating in a case activity and learning from one another. See below for tips on supporting student in how to learn from a case in the “getting started” section and how to create a supportive learning environment in the Guide for Inclusive Teaching at Columbia . 

Table 2. Strategies for Engaging Students in Case-Based Learning

Approaches to case teaching should be informed by course learning objectives, and can be adapted for small, large, hybrid, and online classes. Instructional technology can be used in various ways to deliver, facilitate, and assess the case method. For instance, an online module can be created in CourseWorks (Canvas) to structure the delivery of the case, allow students to work at their own pace, engage all learners, even those reluctant to speak up in class, and assess understanding of a case and student learning. Modules can include text, embedded media (e.g., using Panopto or Mediathread ) curated by the instructor, online discussion, and assessments. Students can be asked to read a case and/or watch a short video, respond to quiz questions and receive immediate feedback, post questions to a discussion, and share resources. 

For more information about options for incorporating educational technology to your course, please contact your Learning Designer .

To ensure that students are learning from the case approach, ask them to pause and reflect on what and how they learned from the case. Time to reflect  builds your students’ metacognition, and when these reflections are collected they provides you with insights about the effectiveness of your approach in promoting student learning.

Well designed case-based learning experiences: 1) motivate student involvement, 2) have students doing the work, 3) help students develop knowledge and skills, and 4) have students learning from each other.  

Designing a case-based learning experience should center around the learning objectives for a course. The following points focus on intentional design. 

Identify learning objectives, determine scope, and anticipate challenges. 

• Why use the case method in your course? How will it promote student learning differently than other approaches? 
• What are the learning objectives that need to be met by the case method? What knowledge should students apply and skills should they practice? 
• What is the scope of the case? (a brief activity in a single class session to a semester-long case-based course; if new to case method, start small with a single case). 
• What challenges do you anticipate (e.g., student preparation and prior experiences with case learning, discomfort with discussion, peer-to-peer learning, managing discussion) and how will you plan for these in your design? 
• If you are asking students to use transferable skills for the case method (e.g., teamwork, digital literacy) make them explicit. 

Determine how you will know if the learning objectives were met and develop a plan for evaluating the effectiveness of the case method to inform future case teaching. 

• What assessments and criteria will you use to evaluate student work or participation in case discussion? 
• How will you evaluate the effectiveness of the case method? What feedback will you collect from students? 
• How might you leverage technology for assessment purposes? For example, could you quiz students about the case online before class, accept assignment submissions online, use audience response systems (e.g., PollEverywhere) for formative assessment during class? 

Select an existing case, create your own, or encourage students to bring course-relevant cases, and prepare for its delivery

• Where will the case method fit into the course learning sequence? 
• Is the case at the appropriate level of complexity? Is it inclusive, culturally relevant, and relatable to students? 
• What materials and preparation will be needed to present the case to students? (e.g., readings, audiovisual materials, set up a module in CourseWorks). 

Plan for the case discussion and an active role for students

• What will your role be in facilitating case-based learning? How will you model case analysis for your students? (e.g., present a short case and demo your approach and the process of case learning) (Davis, 2009). 
• What discussion guidelines will you use that include your students’ input? 
• How will you encourage students to ask and answer questions, summarize their work, take notes, and debrief the case? 
• If students will be working in groups, how will groups form? What size will the groups be? What instructions will they be given? How will you ensure that everyone participates? What will they need to submit? Can technology be leveraged for any of these areas? 
• Have you considered students of varied cognitive and physical abilities and how they might participate in the activities/discussions, including those that involve technology? 

Student preparation and expectations

• How will you communicate about the case method approach to your students? When will you articulate the purpose of case-based learning and expectations of student engagement? What information about case-based learning and expectations will be included in the syllabus?
• What preparation and/or assignment(s) will students complete in order to learn from the case? (e.g., read the case prior to class, watch a case video prior to class, post to a CourseWorks discussion, submit a brief memo, complete a short writing assignment to check students’ understanding of a case, take on a specific role, prepare to present a critique during in-class discussion).

Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. 

Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846

Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. 

Garvin, D.A. (2003). Making the Case: Professional Education for the world of practice. Harvard Magazine. September-October 2003, Volume 106, Number 1, 56-107.

Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. 

Golich, V.L.; Boyer, M; Franko, P.; and Lamy, S. (2000). The ABCs of Case Teaching. Pew Case Studies in International Affairs. Institute for the Study of Diplomacy. 

Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. 

Herreid, C.F. (2011). Case Study Teaching. New Directions for Teaching and Learning. No. 128, Winder 2011, 31 – 40. 

Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. 

Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar  

Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. 

Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. 

Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002

Schiano, B. and Andersen, E. (2017). Teaching with Cases Online . Harvard Business Publishing. 

Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. 

Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). 

Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass.

Additional resources 

Teaching with Cases , Harvard Kennedy School of Government. 

Features “what is a teaching case?” video that defines a teaching case, and provides documents to help students prepare for case learning, Common case teaching challenges and solutions, tips for teaching with cases. 

Promoting excellence and innovation in case method teaching: Teaching by the Case Method , Christensen Center for Teaching & Learning. Harvard Business School. 

National Center for Case Study Teaching in Science . University of Buffalo. 

A collection of peer-reviewed STEM cases to teach scientific concepts and content, promote process skills and critical thinking. The Center welcomes case submissions. Case classification scheme of case types and teaching methods:

• Different types of cases: analysis case, dilemma/decision case, directed case, interrupted case, clicker case, a flipped case, a laboratory case. 
• Different types of teaching methods: problem-based learning, discussion, debate, intimate debate, public hearing, trial, jigsaw, role-play. 

Columbia Resources

Resources available to support your use of case method: The University hosts a number of case collections including: the Case Consortium (a collection of free cases in the fields of journalism, public policy, public health, and other disciplines that include teaching and learning resources; SIPA’s Picker Case Collection (audiovisual case studies on public sector innovation, filmed around the world and involving SIPA student teams in producing the cases); and Columbia Business School CaseWorks , which develops teaching cases and materials for use in Columbia Business School classrooms.

Center for Teaching and Learning

The Center for Teaching and Learning (CTL) offers a variety of programs and services for instructors at Columbia. The CTL can provide customized support as you plan to use the case method approach through implementation. Schedule a one-on-one consultation. 

Office of the Provost

The Hybrid Learning Course Redesign grant program from the Office of the Provost provides support for faculty who are developing innovative and technology-enhanced pedagogy and learning strategies in the classroom. In addition to funding, faculty awardees receive support from CTL staff as they redesign, deliver, and evaluate their hybrid courses.

The Start Small! Mini-Grant provides support to faculty who are interested in experimenting with one new pedagogical strategy or tool. Faculty awardees receive funds and CTL support for a one-semester period.

Explore our teaching resources.

• About the TOF Program
• 2017-18 Fellows
• 2016-17 Fellows

CTL resources and technology for you.

• About the LTF Program
• 2015-16 Fellows
• Senior Lead Teaching Fellowship
• The origins of this method can be traced to Harvard University where in 1870 the Law School began using cases to teach students how to think like lawyers using real court decisions. This was followed by the Business School in 1920 (Garvin, 2003). These professional schools recognized that lecture mode of instruction was insufficient to teach critical professional skills, and that active learning would better prepare learners for their professional lives. ↩
• Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. ↩
• Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. ↩
• Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. ↩
• Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. ↩
• Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. ↩
• Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. ↩
• Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846 ↩
• Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. ↩
• Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. ↩
• Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). ↩
• Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002 ↩
• Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass. ↩
• Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar ↩

This website uses cookies to identify users, improve the user experience and requires cookies to work. By continuing to use this website, you consent to Columbia University's use of cookies and similar technologies, in accordance with the Columbia University Website Cookie Notice .

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

2 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

Center for Innovative Teaching and Learning

Is it pedagogy or andragogy? Considering different teaching methods for different learners and contexts

While university environment focuses on educating students 18 and older, the teaching methods used may reflect the course’s field of study or purpose as opposed to the learner’s age. To determine which teaching methods we should use for our courses, we need to understand the differences between approaches to pedagogy vs. andragogy. 

Pedagogy focuses on dependent learners, who are conceptual learners. Learners understand that acquiring knowledge is essential for advancing through the curriculum. The instructor structures the acquisition of foundational knowledge and skills by determining and defining learning stages. The learning process is guided by the type of pedagogy used . The motivation to learn is external, driven by recognition and grades.  

Suggested times to use a pedagogical approach:

• Courses designed for first-year students
• Subjects that benefit from structured and sequential knowledge acquisition
• Required courses
• When modeling how to work with dependent learners

Andragogy focuses on adult learners, who are practical learners. Learners want the rationale behind their studies, how it applies to life outside of the course, and how it connects to previous experiences. The role of the instructor is facilitator in this student-led instructional approach. The learning process often includes active participation and collaboration with others. The motivation to learn is intrinsic, especially when the knowledge is presented in a way that focuses on problem-solving.  

Suggested times to use an andragogical approach:

• Courses are upper-level and have independent research or large projects
• Courses with online, distanced, or hybrid modalities

Some of us might use a combination of pedagogy and andragogy depending on the field, purpose, progression, and modality of the course. Regardless of age and motivation, not every student is ready to move to self-directed learning once they start college, and they may require some guidance and support when moving towards more autonomy as a learner.  

Additional Resources

To learn more about teaching methods and ways to appeal to different learners, check out the following resources: 

• 3 Adult Learning Theories Every E-Learning Designer Must Know Association for Talent Development  
• Andragogy vs. Pedagogy: Key Differences in Learning WGU  
• Deconstructing ChatGPT on the Future of Continuing Education Inside Higher Ed  
• Effective Teaching Practices NIU CITL  
• From the Inside Out: Reflecting on a Dual Lens Inside Higher Ed  
• How to Make Your Teaching More Inclusive Chronicle of Higher Education  
• Learning in a Time of Abundance Inside Higher Ed   
• The Needs and Preferences of Fully Online Learners Inside Higher Ed  
• Pedagogy, Andragogy, & Heutagogy University of Illinois Springfield  
• Pedagogy and course design need to change. Here’s how. Inside Higher Ed  
• Pedagogy of Kindness in Practice NIU CITL  
• Pedagogical Strategies and Practices Montclair State University   
• The Pulse: Design for the Mind Inside Higher Ed  
• Questioning as a Foundation for Pedagogy Inside Higher Ed  
• The Rise of Do-It-Yourself Education Inside Higher Ed  
• What is pedagogy in education? Augusta University  

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

• Open access
• Published: 19 April 2024

GbyE: an integrated tool for genome widely association study and genome selection based on genetic by environmental interaction

• Xinrui Liu 1 , 2 ,
• Mingxiu Wang 1 ,
• Jie Qin 1 ,
• Yaxin Liu 1 ,
• Shikai Wang 1 ,
• Shiyu Wu 1 ,
• Ming Zhang 1 ,
• Jincheng Zhong 1 &
• Jiabo Wang 1  

BMC Genomics volume  25 , Article number:  386 ( 2024 ) Cite this article

131 Accesses

Metrics details

The growth and development of organism were dependent on the effect of genetic, environment, and their interaction. In recent decades, lots of candidate additive genetic markers and genes had been detected by using genome-widely association study (GWAS). However, restricted to computing power and practical tool, the interactive effect of markers and genes were not revealed clearly. And utilization of these interactive markers is difficult in the breeding and prediction, such as genome selection (GS).

Through the Power-FDR curve, the GbyE algorithm can detect more significant genetic loci at different levels of genetic correlation and heritability, especially at low heritability levels. The additive effect of GbyE exhibits high significance on certain chromosomes, while the interactive effect detects more significant sites on other chromosomes, which were not detected in the first two parts. In prediction accuracy testing, in most cases of heritability and genetic correlation, the majority of prediction accuracy of GbyE is significantly higher than that of the mean method, regardless of whether the rrBLUP model or BGLR model is used for statistics. The GbyE algorithm improves the prediction accuracy of the three Bayesian models BRR, BayesA, and BayesLASSO using information from genetic by environmental interaction (G × E) and increases the prediction accuracy by 9.4%, 9.1%, and 11%, respectively, relative to the Mean value method. The GbyE algorithm is significantly superior to the mean method in the absence of a single environment, regardless of the combination of heritability and genetic correlation, especially in the case of high genetic correlation and heritability.

Conclusions

Therefore, this study constructed a new genotype design model program (GbyE) for GWAS and GS using Kronecker product. which was able to clearly estimate the additive and interactive effects separately. The results showed that GbyE can provide higher statistical power for the GWAS and more prediction accuracy of the GS models. In addition, GbyE gives varying degrees of improvement of prediction accuracy in three Bayesian models (BRR, BayesA, and BayesCpi). Whatever the phenotype were missed in the single environment or multiple environments, the GbyE also makes better prediction for inference population set. This study helps us understand the interactive relationship between genomic and environment in the complex traits. The GbyE source code is available at the GitHub website ( https://github.com/liu-xinrui/GbyE ).

Peer Review reports

Genetic by environmental interaction (G × E) is crucial of explaining individual traits and has gained increasing attention in research. It refers to the influence of genetic factors on susceptibility to environmental factors. In-depth study of G × E contributes to a deeper understanding of the relationship between individual growth, living environment and phenotypes. Genetic factors play a role in most human diseases at the molecular or cellular level, but environmental factors also contribute significantly. Researchers aim to uncover the mechanisms behind complex diseases and quantitative traits by investigating the interactions between organisms and their environment. Common, complex, or rare human diseases are often considered as outcomes resulting from the interplay of genes, environmental factors, and their interactions. Analyzing the joint effects of genes and the environment can provide valuable insights into the underlying pathway mechanisms of diseases. For instance, researchers have successfully identified potential loci associated with asthma risk through G × E interactions [ 1 ], and have explored predisposing factors for challenging-to-treat diseases like cancer [ 2 , 3 ], rhinitis [ 4 ], and depression [ 5 ].

However, two main methods are currently being used by breeders in agricultural production to increase crop yields and livestock productivity [ 6 ]. The first is to develop varieties with relatively low G × E effect to ensure stable production performance in different environments. The second is to use information from different environments to improve the statistical power of genome-wide association study (GWAS) to reveal potential loci of complex traits. The first method requires long-term commitment, while the second method clearly has faster returns. In GWAS, the use of multiple environments or phenotypes for association studies has become increasingly important. This not only improves the statistical power of environmental susceptibility traits[ 7 ], but also allows to detect signaling loci for G × E. There are significant challenges when using multiple environments or phenotypes for GWAS, mainly because most diseases and quantitative traits have numerous associated loci with minimal impact [ 8 ], and thus it is impossible to determine the effect size regulated by environment in these loci. The current detection strategy for G × E is based on complex statistical model, often requiring the use of a large number of samples to detect important signals [ 9 , 10 ]. In GS, breeders can use whole genome marker data to identify and select target strains in the early stages of animal and plant production [ 11 , 12 , 13 ]. Initially, GS models, similar to GWAS models, could only analyze a single environment or phenotype [ 14 ]. To improve the predictive accuracy of the models, higher marker densities are often required, allowing the proportion of genetic variation explained by these markers to be increased, indirectly obtaining higher predictive accuracy. It is worth mentioning that the consideration of G × E and multiple phenotypes in GS models [ 15 ] has been widely studied in different plant and animal breeding [ 16 ]. GS models that allow G × E have been developed [ 17 ] and most of them have modeled and interpreted G × E using structured covariates [ 18 ]. In these studies, most of the GS models provided more predictive accuracy when combined with G × E compared to single environment (or phenotype) analysis. Hence, there is need to develop models that leverage G × E information for GWAS and GS studies.

This study developed a novel genotype-by-environment method based on R, termed GbyE, which leverages the interaction among multiple environments or phenotypes to enhance the association study and prediction performance of environmental susceptibility traits. The method enables the identification of mutation sites that exhibit G × E interactions in specific environments. To evaluate the performance of the method, simulation experiments were conducted using a dataset comprising 282 corn samples. Importantly, this method can be seamlessly integrated into any GWAS and GS analysis.

Materials and methods

Support packages.

The development purpose of GbyE is to apply it to GWAS and GS research, therefore it uses the genome association and prediction integrated tool (GAPIT) [ 19 ], Bayesian Generalized Linear Regression (BGLR) [ 20 ], and Ridge Regression Best Linear Unbiased Prediction (rrBLUP) [ 21 ]package as support packages, where GbyE only provides conversion of interactive formats and file generation. In order to simplify the operation of the GbyE function package, the basic calculation package is attached to this package to support the operation of GbyE, including four function packages GbyE.Simulation.R (Dual environment phenotype simulation based on heritability, genetic correlation, and QTL quantity), GbyE.Calculate.R (For numerical genotype and phenotype data, this package can be used to process interactive genotype files of GbyE), GbyE.Power.FDR.R (Calculate the statistical power and false discovery rate (FDR) of GWAS), and GbyE.Comparison.Pvalue.R (GbyE generates redundant calculations in GWAS calculations, and SNP effect loci with minimal p -values can be filtered by this package).

Samples and sequencing data

In this study, a small volume of data was used for software simulation analysis, which is widely used in testing tasks of software such as GAPIT, TASSEL, and rMPV. The demonstration data comes from 282 inbred lines of maize, including 4 phenotypic data. In any case, there are no missing phenotypes in these data, and this dataset can be obtained from the website of GAPIT ( https://zzlab.net/GAPIT/index.html , accessed on May 1, 2022). Among them, our phenotype data was simulated using a self-made R simulation function, and the Mean and GbyE phenotype files were calculated. Convert this format to HapMap format using PLINK v1.09 and scripts written by oneself.

Simulated traits

Phenotype simulation was performed by modifying the GAPIT.Phenotype.Simulation function in the GAPIT. Based on the input parameter NQTN, the random selected markers’ genotype from whole genome were used to simulate genetic effect in the simulated trait. The genotype effects of these selected QTNs were randomly sampled from a multivariate normal distribution, the correlation value between these normal distribution was used to define the genetic relationship between each environments. The additive heritability ( \({{\text{h}}}_{{\text{g}}}^{2}\) ) was used to scale the relationship between additive genetic variance and phenotype variance. The simulated phenotype conditions in this paper are set as follows: 1) The three levels of \({{\text{h}}}_{{\text{g}}}^{2}\) were set at 0.8, 0.5, and 0.2, representing high ( \({{\text{h}}}_{{\text{h}}}^{2}\) ), median ( \({{\text{h}}}_{{\text{m}}}^{2}\) ) and low ( \({{\text{h}}}_{{\text{l}}}^{2}\) ) heritability; 2) Genetic correlation were set three levels 0.8, 0.5, 0.2 representing high ( \({{\text{R}}}_{{\text{h}}}\) ), medium ( \({{\text{R}}}_{{\text{m}}}\) ) and low ( \({{\text{R}}}_{{\text{l}}}\) ) genetic correlation; 3) 20 pre-set effect loci of QTL. The phenotype values in each environment were simulated together following above parameters.

Genetic by environment interaction model

The pipeline analysis process of GbyE includes three steps: data preprocessing, production converted, Association analysis. Normalize the phenotype data matrix Y of the dual environment and perform GbyE conversion to generate phenotype data in GbyE.Y format. The genotype data format, such as hapmap, vcf, bed and other formats firstly need to be converted into numerical genotype format (homozygotes were coded as 0 or 2, heterozygotes were coded as 1) using software or scripts such as GAPIT, PLINK, etc. The environment (E) matrix is environment index matrix. The G (n × m) originally of genotype matrix was converted as GbyE.GD(2n × 2 m) \(\left[\begin{array}{cc}G& 0\\ G& G\end{array}\right]\) during the Kronecker product, and the Y vector (n × 1) was also converted as the GbyE.Y vector (2n × 1) after normalization. The duplicated data format indicated different environments, genetic effect, and populations. The genomic data we used in the analysis was still retained the whole genome information. The first column of E is the additive effect, which was the average genetic effect among environments. The others columns of E are the interactive effect, which should be less one column than the number of environments. Because it need to avoid the linear dependent in the model. In the GbyE algorithm, we coded the first environment as background as default, that means the genotype in the first environment are 0, the others are 1. Then the Kronecker product of G and environment index matrix was named as GbyE.GD. The interactive effect part of the GbyE.GD matrix in the GWAS and GS were the relative values based on the first environment (Fig.  1 ). The GbyE environmental interaction matrix can be easily obtained by constructing the interaction matrix E (e.g., Eq. 1 ) such that the genotype matrix G is Kronecker-product with the design interaction matrix E (e.g., Eq. 2 ), in which \(\left[\begin{array}{c}G\\ G\end{array}\right]\) matrix is defined as additive effect and \(\left[\begin{array}{c}0\\ G\end{array}\right]\) matrix is defined as interactive effect. \(\left[\begin{array}{cc}G& 0\\ G& G\end{array}\right]\) matrix is called gene by environment interaction matrix, hereinafter referred to as the GbyE matrix. The phenotype file (GbyE.Y) and genotype file (GbyE.GD) after transformation by GbyE will be inputted into the GWAS and GS models and computed as standard phenotype and genotype files.

where G is the matrix of whole genotype and E is the design matrix for exploring interactive effects. GbyE mainly uses the Kronecker product of the genetic matrix (G) and the environmental matrix (E) as the genotype for subsequent GWAS as a way to distinguish between additive and interactive effects.

The workflow pipeline of GbyE. The GbyE contains three main steps. (Step 1) Preprocessing of phenotype and genotype data,. The phenotype values in each environment was normalized respectively. Meanwhile, all genotype from HapMap, VCF, BED, and other types were converted to numeric genotype; (Step 2) Generate GbyE phenotype and interactive genotype matrix through the transformation of GbyE. In GbyE.GD matrix, the blue characters indicate additive effect, and red ones indicate interactive effect; (Step 3) The MLM and rrBLUP and BGLR were used to perform GWAS and GS

Association analysis model

The mixed linear model (MLM) of GAPIT is used as the basic model for GWAS analysis, and the principal component analysis (PCA) parameter is set to 3. Then the p -values of detection results are sorted and their power and FDR values are calculated. General expression of MLM (Fig.  1 ):

where Y is the vector of phenotypic measures (2n × 1); PCA and SNP i were defined as fixed effects, with a size of (2n × 2 m); Z is the incidence matrix of random effects; μ is the random effect vector, which follows the normal distribution μ ~ N(0, \({\delta }_{G}^{2}\) K) with mean vector of 0 and variance covariance matrix of \({\delta }_{G}^{2}\) K, where the \({\delta }_{G}^{2}\) is the total genetic variance including additive variance and interactive variance, the K is the kinship matrix built with all genotype including additive genotype and interactive genotype; e is a random error vector, and its elements need not be independent and identically distributed, e ~ N(0, \({\delta }_{e}^{2}\) I), where the \({\delta }_{e}^{2}\) is the residual and environment variance, the I is the design matrix.

Detectivity of GWAS

In the GWAS results, the list of markers following the order of P-values was used to evaluate detectivity of GWAS methods. When all simulated QTNs were detected, the power of the GWAS method was considered as 1 (100%). From the list of markers, following increasing of the criterion of real QTN, the power values will be increasing. The FDR indicates the rate between the wrong criterion of real QTNs and the number of all un-QTNs. The mean of 100 cycles was used to consider as the reference value for statistical power comparison. Here, we used a commonly used method in GWAS research with multiple traits or environmental phenotypes as a comparison[ 22 ]. This method obtains the mean of phenotypic values under different conditions as the phenotypic values for GWAS analysis, called the Mean value method, Compare the calculation results of GbyE with the additive and interactive effects of the mean method to evaluate the detection power of the GbyE strategy. Through the comprehensive analysis of these evaluation indicators, we aim to comprehensively evaluate the statistical power of the GbyE strategy in GWAS and provide a reference for future optimization research.

Among them, the formulae for calculating Power and FDR are as follows:

where \({{\text{n}}}_{{\text{i}}}\) indicates whether the i-th detection is true, true is 1, false is 0; \({{\text{m}}}_{{\text{r}}}\) is the total number of all true QTLs in the sample size; the maximum value of Power is 1.

where \({{\text{N}}}_{{\text{i}}}\) represents the i-th true value detected in the pseudogene, true is 1, false is 0. and cumulative calculation; \({{\text{M}}}_{{\text{f}}}\) is the number of all labeled un-QTNs in the total samples; the maximum value of FDR is 1.

Genomic prediction

To comparison the prediction accuracy of different GS models using GbyE, we performed rrBLUP, Bayesian methods using R packages. All phenotype of reference population and genotype of all population were used to train the model and predict genomic estimated breeding value (gEBV) of all individuals. The correlation between real phenotypes and gEBV of inference population was considered as prediction accuracy. fivefold cross-validation and 100 times repeats was performed to avoid over prediction and reduce bias. In order to distinguish the additive and interactive effects in GbyE, we designed two lists of additive and interactive effects in the "ETA" of BGLR, and put the additive and interactive effects into the model as two kinships for random objects. However, it was not possible to load the gene effects of the two lists in rrBLUP, so the additive and interactive genotypes together were used to calculate whole genetic kinship in rrBLUP (Fig.  1 ). Relevant parameters in BGLR are set as follows: 1) model set to "RRB"; 2) nIter is set to "12000"; 3) burnIn is set to "10000". The results of the above operations are averaged over 100 cycles. We also validated the GbyE method using four other Bayesian methods (BayesA, BayesB, BayesCpi, and Bayesian LASSO) in addition to RRB in BGLR.

Partial missing phentoype in the prediction

In this study, we artificially missed phenotype values in the single and double environments in the whole population from 281 inbred maize datasets. In the missing single environment case, the inference set in the cross-validation was selected from whole population, and each individual in the inference were only missed phenotypes in the one environment. The phenotype in the other environment was kept. The genotypes were always kept. In the case of missing double environments, both phenotypes and genotypes of environment 1 and environment 2 are missing, and the model can only predict phenotypic values in the two missing environments through the effects of other markers. In addition, the data were standardized and unstandardized to assess whether standardization had an effect on the estimation of the model. This experiment was tested using the "ML" method in rrBLUP to ensure the efficiency of the model.

GWAS statistical power of models at different heritabilities and genetic correlations

Power-FDR plots were used to demonstrate the detection efficiency of GbyE at three genetic correlation and three genetic power levels, with a total of nine different scenarios simulated (from left to right for high and low genetic correlation and from top to bottom for high and low genetic power). In order to distinguish whether the effect of improving the detection ability of genome-wide association analysis in GbyE is an additive effect or an effect of environmental interactions, we plotted their Power-FDR curves separately and added the traditional Mean method for comparative analysis. As shown in Fig.  2 , GbyE algorithm can detect more statistically significant genetic loci with lower FDR under any genetic background. However, in the combination with low heritability (Fig.  2 A, B, C), the interactive effect detected more real loci than GbyE under low FDR, but with the continued increase of FDR, GbyE detected more real loci than other groups. Under the combination with high heritability, all groups have high statistical power at low FDR, but with the increase of FDR, the statistical effect of GbyE gradually highlights. From the analysis of heritability combinations at all levels, the effect of heritability on interactive effect is not obvious, but GbyE always maintains the highest statistical power. The average detection power of GWAS in GbyE can be increased by about 20%, and with the decrease of genetic correlation, the effect of GbyE gradually highlights, indicating that the G × E plays a role.

The power-FDR testing in simulated traits. Comparing the efficacy of the GbyE algorithm with the conventional mean method in terms of detection power and FDR. From left to right, the three levels of genetic correlation are indicated in order of low, medium and high. From top to bottom, the three levels of heritability, low, medium and high, are indicated in order. (1) Inter: Interactive section extracted from GbyE; (2) AddE: Additive section extracted from GbyE; (3) \({{\text{h}}}_{{\text{l}}}^{2}\) , \({{\text{h}}}_{{\text{m}}}^{2}\) , \({{\text{h}}}_{{\text{g}}}^{2}\) : Low, medium, high heritability; (4) \({{\text{R}}}_{{\text{l}}}\) , \({{\text{R}}}_{{\text{m}}}\) , \({{\text{R}}}_{{\text{l}}}\) : where R stands for genetic correlation, represents three levels of low, medium and high

Resolution of additive and interactive effect

The output results of GbyE could be understood as resolution of additive and interactive genetic effect. Hence, we created a combined Manhattan plots with Mean result from MLM, additive, and interactive results from GbyE. As shown in Fig.  3 , true marker loci were detected on chromosomes 1, 6 and 9 in Mean, and the same loci were detected on chromosomes 1 and 6 for the additive result in GbyE (the common loci detected jointly by the two results were marked as solid gray lines in the figure). All known pseudo QTNs were labeled with gray dots in the circle. Total 20 pseudo QTNs were simulated in such trait (The heritability is set to 0.9, and the genetic correlation is set to 0.1). Although the additive section in GbyE did not catch the locus on chromosome 9 yet (those p-values of markers did not show above the significance threshold (p-value < 3.23 × 10 –6 )), it has shown high significance relative to other markers of the same chromosome. In the reciprocal effect of GbyE, we detected more significant loci on chromosomes 1, 2, 3 and 10, and these loci were not detected in either of the two previous sections. An integrate QQ plot (Fig.  3 D) shows that the overall statistical power of the additive section in Mean and GbyE are close, nevertheless, the interactive section in the GbyE provided a bit of inflation.

Manhattan statistical comparison plot. Manhattan comparison plots of mean ( A ), additive ( B ) and gene-environment interactive sections ( C ) at a heritability of 0.9 and genetic correlation of 0.1. Different colors are used in the diagram to distinguish between different chromosomes (X-axis). Loci with reinforcing circles and centroids are set up as real QTN loci. Consecutive loci found in both parts are shown as id lines, and loci found separately in the reciprocal effect only are shown as dashed lines. Parallel horizontal lines indicate significance thresholds ( p -value < 3.23 × 10 –6 ). D Quantile–quantile plots of simulated phenotypes for demo data from genome-wide association studies. x-axis indicates expected values of log p -values and y-axis is observed values of log p -values. The diagonal coefficients in red are 1. GbyE-inter is the interactive section in GbyE; GbyE-AddE is the additive section in GbyE

Genomic selection in assumption codistribution

The prediction accuracy of GbyE was significantly higher than the Mean value method by model statistics of rrBLUP in most cases of heritability and genetic correlation (Fig.  4 ). The prediction accuracy of the additive effect was close to that of Mean value method, which was consistent with the situation under the low hereditary. The prediction accuracy of interactive sections in GbyE remains at the same level as in GbyE, and interactive section plays an important role in the model. We observed that in \({{\text{h}}}_{{\text{l}}}^{2}{{\text{R}}}_{{\text{h}}}\) (Fig.  4 C), \({{\text{h}}}_{{\text{m}}}^{2}{{\text{R}}}_{{\text{h}}}\) (Fig.  4 F), \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{l}}}\) (Fig.  4 G), the prediction accuracy of GbyE was slightly higher than the Mean value method, but there was no significant difference overall. In addition, we only observed that the prediction accuracy of GbyE was slightly lower than the Mean value method in \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{l}}}\) (Fig.  4 H), but there was still no significant difference between GbyE and Mean value methods. Under the combination of low heritability and genetic correlation, the prediction accuracy of Mean value method and additive effect model remained at a similar level. However, with the continuous increase of heritability and genetic correlation, the difference in prediction accuracy between the two gradually increases. In summary, the GbyE algorithm can improve the accuracy of GS by capturing information on multiple environment or trait effects under the rrBLUP model.

Box-plot of model prediction accuracy. The prediction accuracy (pearson's correlation coefficient) of the GbyE algorithm was compared with the tradition al Mean value method in a simulation experiment of genomic selection under the rrBLUP operating environment. The effect of different levels of heritability and genetic correlation on the prediction accuracy of genomic selection was simulated in this experiment. Each row from top to bottom represents low heritability ( \({{\text{h}}}_{{\text{l}}}^{2}\) ), medium heritability ( \({{\text{h}}}_{{\text{m}}}^{2}\) ) and high heritability ( \({{\text{h}}}_{{\text{h}}}^{2}\) ), respectively; each column from left to right represents low genetic correlation ( \({{\text{R}}}_{{\text{l}}}\) ), medium genetic correlation ( \({{\text{R}}}_{{\text{m}}}\) ) and high genetic correlation ( \({{\text{R}}}_{{\text{h}}}\) ), respectively; The X-axis shows the different test methods and effects, and the Y-axis shows the prediction accuracy

Genomic selection in assumption un-codistribution

The overall performance of GbyE under the 'BRR' statistical model based on the BGLR package remained consistent with rrBLUP, maintaining high predictive accuracy in most cases of heritability and genetic relatedness (Fig. S1 ). However, when the heritability is set to low and medium, the difference between the prediction accuracy of GbyE algorithm and Mean value method gradually decreases with the continuous increase of genetic correlation, and there is no statistically significant difference between the two. The prediction accuracy of the model by GbyE in \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{l}}}\) (Fig. S1 G) and \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{h}}}\) (Fig. S1 I) is significantly higher than that by Mean value method when the heritability is set to be high. On the contrary, when the genetic correlation is set to medium, there is no significant difference between GbyE and Mean value method in improving the prediction accuracy of the model, and the overall mean of GbyE is lower than Mean. When GbyE has relatively high heritability and low genetic correlation, its prediction accuracy is significantly higher than the mean method, such as \({{\text{h}}}_{{\text{m}}}^{2}{{\text{R}}}_{{\text{l}}}\) (Fig. S1 D), \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{l}}}\) (Fig. S1 G), and \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{m}}}\) (Fig. S1 H). Therefore, GbyE is more suitable for situations with high heritability and low genetic correlation.

Adaptability of Bayesian models

Next, we tested a more complex Bayesian model. The GbyE algorithm and Mean value method were combined with five Bayesian algorithms in BGLR for GS analysis, and the computing R script was used for phenotypic simulation test, where heritability and genetic correlation were both set to 0.5. The results indicate that among the three Bayesian models of RRB, BayesA, and BayesLASSO, the predictive accuracy of GbyE is significantly higher than that of Mean value method (Fig.  5 ). In contrast, under the Bayesian models of BayesB and BayesCpi, the prediction accuracy of GbyE is lower than that of the Mean value method. The GbyE algorithm improves the prediction accuracy of the three Bayesian models BRR, BayesA, and BayesLASSO using information from G × E and increases the prediction accuracy by 9.4%, 9.1%, and 11%, respectively, relative to the Mean value method. However, the predictive accuracy of the BayesB model decreased by 11.3%, while the BayescCpi model decreased by 6%.

Relative prediction accuracy histogram for different Bayesian models. The X-axis is the Bayesian approach based on BGLR, and the Y-axis is the relative prediction accuracy. Where we normalize the prediction accuracy of Mean (the prediction accuracy is all adjusted to 1); the prediction accuracy of GbyE is the increase or decrease value relative to Mean in the same group of models

Impact of all and partial environmental missing

We tested missing the environmental by using simulated data. In the case of the simulated data, we simulated a total of nine situations with different heritability and genetic correlations (Fig.  6 ) and conducted tests on single and dual environment missing. The improvement in prediction accuracy by the GbyE algorithm was found to be significantly higher than the Mean value method in single environment deletion, regardless of the combination of heritability and genetic correlation. In the case of \({{\text{h}}}_{{\text{h}}}^{2}{{\text{R}}}_{{\text{h}}}\) , the prediction accuracy of GbyE is higher than 0.5, which is the highest value among all simulated combinations. When GbyE estimates the phenotypic values of Environment 1 and Environment 2 separately, its predictive accuracy seems too accurate. On the other hand, when the phenotypic values of both environments are missing on the same genotype, the predictive accuracy of GbyE does not show a significant decrease, and even maintains accuracy comparable to that of a single environment missing. However, when GbyE estimates Environment 1 and Environment 2 separately, the prediction accuracy significantly decreases compared to when a single environment is missing, and the prediction accuracy of Environment 1 and Environment 2 in \({{\text{h}}}_{{\text{l}}}^{2}{{\text{R}}}_{{\text{m}}}\) is extremely low (Fig.  6 B). In addition, the prediction accuracy of GbyE is lower than Mean values only in \({{\text{h}}}_{{\text{l}}}^{2}{{\text{R}}}_{{\text{h}}}\) , whether it is missing in a single or dual environment.

Prediction accuracy of simulated data in single and dual environment absence. The prediction effect of GbyE was divided into two parts, environment 1 and environment 2, to compare the prediction accuracy of GbyE when predicting these two parts separately. This includes simulations with missing phenotypes and genotypes in environment 1 only ( A ) and simulations with missing in both environments ( B ). The horizontal coordinates of the graph indicate the different combinations of heritabilities and genetic correlations of the simulations

The phenotype of organisms is usually controlled by multiple factors, mainly genetic [ 23 ] and environmental factors [ 24 ], and their interactive factors. The phenotype of quantitative traits is often influenced by these three factors [ 25 , 26 ]. However, based on the computing limitation and lack of special tool, the interactive effect always was ignored in most GWAS and GS research, and it is difficult to distinguish additive and interactive effects. The rate between all additive genetic variance and phenotype variance was named as narrow sense heritability. The accuracy square of prediction of additive GS model is considered that can not surpass narrow sense heritability. In this study, the additive effects in GbyE are essentially equivalent to the detectability of traditional models, the key advantage of GbyE is the interactive section. More significant markers with interactive effects were detected. Detecting two genetic effects (additive and interactive sections) in GWAS and GS is a boost to computational complexity, while obtaining genotypes for genetic interactions by Kronecker product is an efficient means. This allows the estimation of additive and interactive genetic effects separately during the analysis, and ultimately the estimated genetic effects for each GbyE genotype (including additive and interactive genetic effect markers) are placed in a t-distribution for p -value calculation, and the significance of each genotype is considered by multiple testing. The GbyE also expanded the estimated heritability as generalized heritability which could be explained as the rate between total genetics variance and phenotype variance.

The genetic correlation among traits in multiple environments is the major immanent cause of GbyE. When the genetic correlation level is high, then additive genetic effects will play primary impact in the total genetic effect, and interactive genetic effects with different traits or environments are often at lower levels [ 27 ]. Therefore, the statistical power of the GbyE algorithm did not improve significantly compared with the traditional method (Mean value) when simulating high levels of genetic correlation. On the contrary, in the case of low levels of genetic correlation, the genetic variance of additive effects is relatively low and the genetic variance of interactive effects is major. At this time, GbyE utilizes multiple environments or traits to highlight the statistical power. Since the GbyE algorithm obtains additive, environmental, and interactive information by encoding numerical genotypes, it only increases the volume of SNP data and can be applied to any traditional GWAS association statistical model. However, this may slightly increase the correlation operation time of the GWAS model, but compared to other multi environment or trait models [ 28 , 29 ], GbyE only needs to perform a complete traditional GWAS once to obtain the results.

In GS, rrBLUP algorithm is a linear mixed model-based prediction method that assumes all markers provide genetic effects and their values following a normal distribution [ 30 ]. In contrast, the BGLR model is a linear mixed model, which assumes that gene effects are randomly drawn from a multivariate normal distribution and genotype effects are randomly drawn from a multivariate Gaussian process, which takes into account potential pleiotropy and polygenic effects and allows inferring the effects of single gene while estimating genomic values [ 31 ]. The algorithm typically uses Markov Chain Monte Carlo methods for estimation of the ratio between genetic variances and residual variances [ 32 , 33 ]. The model has been able to take into account more biological features and complexity, and therefore the overall improvement of the GbyE algorithm under BGLR is smaller than Mean method. In addition, the length of the Markov chain set on the BGLR package is often above 20,000 to obtain stable parameters and to undergo longer iterations to make the chain stable [ 34 ]. GbyE is effective in improving the statistical power of the model under most Bayesian statistical models. In the case of the phenotypes we simulated, more iterations cannot be provided for the BayesB and BayesCpi models because of the limitation of computation time, which causes low prediction accuracy. It is worth noting that the prediction accuracy of BayesCpi may also be influenced by the number of QTLs [ 35 ], and the prediction accuracy of BayesB is often related to the distribution of different allele frequencies (from rare to common variants) at random loci [ 36 ].

The overall statistical power of GbyE was significantly higher in missing single environment than in missing double environment, because in the case of missing single environment, GbyE can take full advantage of the information from the phenotype in the second environment. And the correlation between two environments can also affect the detectability of the GbyE algorithm in different ways. On the one hand, a high correlation between two environments can improve the predictive accuracy of the GbyE algorithm by using the information from one environment to predict the breeding values in the other environment, even if there is only few relationship with that environment [ 37 , 38 ]. On the other hand, when two environments are extremely uncorrelated, GbyE algorithm trained in one environment may not export well to another environment, which may lead to a decrease in prediction accuracy [ 39 ]. In the testing, we found that when the GbyE algorithm uses a GS model trained in one environment and tested in another environment, the high correlation between environments may result to the model capturing similarities between environments unrelated to G × E information [ 40 ]. However, when estimating the breeding values for each environment separately, GbyE still made effective predictions using the genotypes in that environment and maintained high prediction accuracy. As expected, the additive effect calculates the average genetic effect between environments, and its predictive effect does not differ much from the mean method. The interactive effect, however, has one less column than the number of environments, and it calculates the relative values between environments, a component that has a direct impact on the predictive effect. The correlation between the two environments may have both positive and negative effects on the detectability of the GbyE, so it is important to carefully consider the relationship between the two environments in subsequent in development and testing.

A key advantage of the GbyE algorithm is that it can be applied to almost all current genome-wide association and prediction. However, the focus of GbyE is still on estimating additive and interactive effects separately, so that it is easy to determine which portion of the is playing a role in the computational estimation.. The GbyE algorithm may have implications for the design of future GS studies. For example, the model could be used to identify the best environments or traits to include in GS studies in order to maximize prediction accuracy. It is particularly important to test the model on large datasets with different genetic backgrounds and environmental conditions to ensure that it can accurately predict genome-wide effects in a variety of contexts.

GbyE can simulate the effects of gene-environment interactions by building genotype files for multiple environments or multiple traits, normalizing the effects of multiple environments and multiple traits on marker effects. It also enables higher statistical power and prediction accuracy for GWAS and GS. The additive and interactive effects of genes under genetic roles could be revealed clearly, which makes it possible to utilize environmental information to improve the statistical power and prediction accuracy of traditional models, thus helping us to better understand the interactions between genes and the environment.

Availability of data and materials

The GbyE source code, demo script, and demo data are freely available on the GitHub website ( https://github.com/liu-xinrui/GbyE ).

Abbreviations

• Genome-widely association study

Genome selection

Genetic by environmental interaction

Genome association and prediction integrated tool

Mixed linear model

Bayesian generalized linear regression

Ridge regression best linear unbiased prediction

False discovery rate

Principal component analysis

Genomic estimated breeding value

Maazi H, Hartiala JA, Suzuki Y, Crow AL, Shafiei Jahani P, Lam J, Patel N, Rigas D, Han Y, Huang P. A GWAS approach identifies Dapp1 as a determinant of air pollution-induced airway hyperreactivity. PLoS Genet. 2019;15(12):e1008528.

Article   PubMed   PubMed Central   Google Scholar  

Simonds NI, Ghazarian AA, Pimentel CB, Schully SD, Ellison GL, Gillanders EM, Mechanic LE. Review of the gene-environment interaction literature in cancer: what do we know? Genet Epidemiol. 2016;40(5):356–65.

Wang X, Chen H, Kapoor PM, Su Y-R, Bolla MK, Dennis J, Dunning AM, Lush M, Wang Q, Michailidou K. A Genome-Wide Gene-Based Gene-Environment Interaction Study of Breast Cancer in More than 90,000 Women. Cancer research communications. 2022;2(4):211–9.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Chen R-X, Dai M-D, Zhang Q-Z, Lu M-P, Wang M-L, Yin M, Zhu X-J, Wu Z-F, Zhang Z-D, Cheng L. TLR Signaling Pathway Gene Polymorphisms, Gene-Gene and Gene-Environment Interactions in Allergic Rhinitis. Journal of Inflammation Research. 2022;15:3613–30.

Zhao M-Z, Song X-S, Ma J-S. Gene× environment interaction in major depressive disorder. World Journal of Clinical Cases. 2021;9(31):9368.

Falconer DS. The problem of environment and selection. Am Nat. 1952;86(830):293–8.

Article   Google Scholar  

Kim J, Zhang Y, Pan W. Powerful and adaptive testing for multi-trait and multi-SNP associations with GWAS and sequencing data. Genetics. 2016;203(2):715–31.

Visscher PM, Wray NR, Zhang Q, Sklar P, McCarthy MI, Brown MA, Yang J. 10 years of GWAS discovery: biology, function, and translation. The American Journal of Human Genetics. 2017;101(1):5–22.

Article   CAS   PubMed   Google Scholar  

van Os J, Rutten BP. Gene-environment-wide interaction studies in psychiatry. Am J Psychiatry. 2009;166(9):964–6.

Article   PubMed   Google Scholar  

Winham SJ, Biernacka JM. Gene–environment interactions in genome-wide association studies: current approaches and new directions. Journal of Child Psychology Psychiatry. 2013;54(10):1120–34.

Windhausen VS, Atlin GN, Hickey JM, Crossa J, Jannink J-L, Sorrells ME, Raman B, Cairns JE, Tarekegne A, Semagn K. Effectiveness of genomic prediction of maize hybrid performance in different breeding populations and environments. G3: Genes|Genomes|Genetics. 2012;2(11):1427–36.

Xu S, Zhu D, Zhang Q. Predicting hybrid performance in rice using genomic best linear unbiased prediction. Proc Natl Acad Sci. 2014;111(34):12456–61.

Zhao Y, Mette M, Gowda M, Longin C, Reif J. Bridging the gap between marker-assisted and genomic selection of heading time and plant height in hybrid wheat. Heredity. 2014;112(6):638–45.

Crossa J, Perez P, Hickey J, Burgueno J, Ornella L, Cerón-Rojas J, Zhang X, Dreisigacker S, Babu R, Li Y. Genomic prediction in CIMMYT maize and wheat breeding programs. Heredity. 2014;112(1):48–60.

Crossa J, Pérez-Rodríguez P, Cuevas J, Montesinos-López O, Jarquín D, De Los CG, Burgueño J, González-Camacho JM, Pérez-Elizalde S, Beyene Y. Genomic selection in plant breeding: methods, models, and perspectives. Trends Plant Sci. 2017;22(11):961–75.

Roorkiwal M, Jarquin D, Singh MK, Gaur PM, Bharadwaj C, Rathore A, Howard R, Srinivasan S, Jain A, Garg V. Genomic-enabled prediction models using multi-environment trials to estimate the effect of genotype× environment interaction on prediction accuracy in chickpea. Sci Rep. 2018;8(1):11701.

Burgueño J, de los Campos G, Weigel K, Crossa J. Genomic prediction of breeding values when modeling genotype× environment interaction using pedigree and dense molecular markers. Crop Science. 2012;52(2):707–19.

Jarquín D, Crossa J, Lacaze X, Du Cheyron P, Daucourt J, Lorgeou J, Piraux F, Guerreiro L, Pérez P, Calus M. A reaction norm model for genomic selection using high-dimensional genomic and environmental data. Theoretical applied genetics. 2014;127:595–607.

Wang JB, Zhang ZW. GAPIT Version 3: boosting power and accuracy for genomic association and prediction. Genomics Proteomics Bioinformatics. 2021;19(4):629–40.

Pérez P, de Los CG. Genome-wide regression and prediction with the BGLR statistical package. Genetics. 2014;198(2):483–95.

Endelman JB. Ridge Regression and other kernels for genomic selection with R package rrBLUP. Plant Genome J. 2011;4:250–5.

Turley P, Walters RK, Maghzian O, Okbay A, Lee JJ, Fontana MA, Nguyen-Viet TA, Wedow R, Zacher M. Furlotte NAJNg. Multi-trait analysis of genome-wide association summary statistics using MTAG. 2018;50(2):229–37.

CAS   Google Scholar  

Falconer DS. Introduction to quantitative genetics. Pearson Education India; 1996.

Google Scholar  

Lynch M, Walsh B. Genetics and analysis of quantitative traits, vol. 1: Sinauer Sunderland, MA. 1998.

Mackay TF. The genetic architecture of quantitative traits. Annu Rev Genet. 2001;35(1):303–39.

Visscher PM, Hill WG, Wray NR. Heritability in the genomics era—concepts and misconceptions. Nat Rev Genet. 2008;9(4):255–66.

Van der Sluis S, Posthuma D, Dolan CV. TATES: efficient multivariate genotype-phenotype analysis for genome-wide association studies. PLoS Genet. 2013;9(1):e1003235.

O’Reilly PF, Hoggart CJ, Pomyen Y, Calboli FC, Elliott P, Jarvelin M-R, Coin LJ. MultiPhen: joint model of multiple phenotypes can increase discovery in GWAS. PLoS ONE. 2012;7(5):e34861.

Chung J, Jun GR, Dupuis J, Farrer LA. Comparison of methods for multivariate gene-based association tests for complex diseases using common variants. Eur J Hum Genet. 2019;27(5):811–23.

Pérez-Rodríguez P, Gianola D, González-Camacho JM, Crossa J, Manès Y, Dreisigacker S. Comparison between linear and non-parametric regression models for genome-enabled prediction in wheat. G3: Genes|Genomes|Genetics. 2012;2(12):1595–16605.

VanRaden PM. Efficient methods to compute genomic predictions. J Dairy Sci. 2008;91(11):4414–23.

Meuwissen TH, Hayes BJ, Goddard M. Prediction of total genetic value using genome-wide dense marker maps. Genetics. 2001;157(4):1819–29.

de Los CG, Hickey JM, Pong-Wong R, Daetwyler HD, Calus MP. Whole-genome regression and prediction methods applied to plant and animal breeding. Genetics. 2013;193(2):327–45.

Andrieu C, De Freitas N, Doucet A, Jordan MI. An introduction to MCMC for machine learning. Mach Learn. 2003;50:5–43.

Daetwyler HD, Pong-Wong R, Villanueva B, Woolliams JA. The impact of genetic architecture on genome-wide evaluation methods. Genetics. 2010;185(3):1021–31.

Clark SA, Hickey JM, Van der Werf JH. Different models of genetic variation and their effect on genomic evaluation. Genet Sel Evol. 2011;43(1):1–9.

Yang J, Benyamin B, McEvoy BP, Gordon S, Henders AK, Nyholt DR, Madden PA, Heath AC, Martin NG, Montgomery GW. Common SNPs explain a large proportion of the heritability for human height. Nat Genet. 2010;42(7):565–9.

González-Recio O, Forni S. Genome-wide prediction of discrete traits using Bayesian regressions and machine learning. Genet Sel Evol. 2011;43:1–12.

Korte A, Farlow A. The advantages and limitations of trait analysis with GWAS: a review. Plant Methods. 2013;9(1):1–9.

Gauderman WJ. Sample size requirements for matched case-control studies of gene–environment interaction. Stat Med. 2002;21(1):35–50.

Download references

Acknowledgements

Thank you to all colleagues in the laboratory for their continuous help.

This project was partially funded by the National Key Research and Development Project of China, China (2022YFD1601601), the Heilongjiang Province Key Research and Development Project, China (2022ZX02B09), the Qinghai Science and Technology Program, China (2022-NK-110), Sichuan Science and Technology Program, China (Award #s 2021YJ0269 and 2021YJ0266), the Program of Chinese National Beef Cattle and Yak Industrial Technology System, China (Award #s CARS-37), and Fundamental Research Funds for the Central Universities, China (Southwest Minzu University, Award #s ZYN2023097).

Author information

Authors and affiliations.

Key Laboratory of Qinghai-Tibetan Plateau Animal Genetic Resource Reservation and Utilization, Sichuan Province and Ministry of Education, Southwest Minzu University, Chengdu, 6110041, China

Xinrui Liu, Mingxiu Wang, Jie Qin, Yaxin Liu, Shikai Wang, Shiyu Wu, Ming Zhang, Jincheng Zhong & Jiabo Wang

Nanchong Academy of Agricultural Sciences, Nanchong, 637000, China

You can also search for this author in PubMed   Google Scholar

Contributions

JW and XL conceived and designed the project. XL managed the entire trial, conducted software code development, software testing, and visualization. MW, JQ, YL, SW, MZ and SW helped with data collection and analysis. JQ, and YL assisted with laboratory analyses. JW, and XL had primary responsibility for the content in the final manuscript. JZ supervised the research. JW designed software and project methodology. All authors approved the final manuscript. All authors have reviewed the manuscript.

Corresponding author

Correspondence to Jiabo Wang .

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Competing interests.

The authors have declared no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary material 1., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Liu, X., Wang, M., Qin, J. et al. GbyE: an integrated tool for genome widely association study and genome selection based on genetic by environmental interaction. BMC Genomics 25 , 386 (2024). https://doi.org/10.1186/s12864-024-10310-5

Download citation

Received : 27 December 2023

Accepted : 15 April 2024

Published : 19 April 2024

DOI : https://doi.org/10.1186/s12864-024-10310-5

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Genomic selection

BMC Genomics

ISSN: 1471-2164

• Submission enquiries: [email protected]
• General enquiries: [email protected]