Related Experiment Videos
Mapping artificial intelligence in problem-based and case-based medical education: a bibliometric analysis
Qingyuan Tan1, Yukui Ma2, Jichun Zhao2
1West China Centre of Excellence for Pancreatitis, Institute of Integrated Traditional Chinese and Western Medicine, West China Hospital, Sichuan University, Chengdu, China.
Frontiers in Medicine
|August 14, 2026
Summary
Artificial intelligence (AI) is rapidly transforming medical education, with significant growth in research on AI-powered problem-based learning (PBL) and case-based learning (CBL) since 2023. This study maps the emerging landscape of AI in PBL/CBL, identifying key themes and collaborations.
Area of Science:
- Bibliometrics and scientometrics
- Medical education research
- Artificial intelligence in education
Background:
- Problem-based learning (PBL) and case-based learning (CBL) are established pedagogical approaches in medical education.
- The advent of advanced artificial intelligence (AI) tools, such as ChatGPT, has spurred their application in PBL/CBL contexts.
- The research landscape at the intersection of AI and PBL/CBL remains underexplored.
Purpose of the Study:
- To map the growth trajectory, thematic structure, and collaboration networks of research on AI applications in PBL/CBL.
- To characterize the evolution of AI-PBL/CBL research from 2019 to 2026.
- To provide insights for curriculum design and research priorities in AI-enhanced health professions education.
Main Methods:
- A bibliometric review was conducted using Scopus and Web of Science databases, adhering to PRISMA guidelines.
- 735 publications from 2019-2026 were analyzed using VOSviewer, CiteSpace, and Bibliometrix software.
- Methods included keyword co-occurrence, co-authorship, co-citation analysis, citation burst detection, and thematic mapping.
Main Results:
- Publication output demonstrated rapid growth, particularly after 2023, with the United States and China leading in volume.
- Four distinct thematic clusters emerged: AI-focused, medical education/clinical reasoning, nursing/simulation, and educational technology.
- Machine learning was identified as a central theme, with notable collaboration networks led by the US and China, though participation was uneven.
Conclusions:
- This is the first bibliometric study to specifically examine AI in PBL/CBL for health professions education.
- The findings highlight rapid post-2023 growth, distinct research clusters, and evolving international collaboration patterns.
- The study offers valuable insights for shaping future research agendas and integrating AI into medical curricula.
