Previously submitted to: Journal of Medical Internet Research (no longer under consideration since Mar 19, 2025)
Date Submitted: Jan 2, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
The Promise of ChatGPT in Medical Education: a systematic review
ABSTRACT
Purpose: This systematic review examines the potential of ChatGPT as a tool in medical education, focusing on its role in enhancing learning experiences, student performance, and critical thinking skills. ChatGPT's integration aims to address the shortage of faculty resources and create personalized, interactive learning experiences for medical students.
Methods:
Following PRISMA and AMSTAR guidelines, we conducted a systematic review across four databases (Embase, PubMed, Web of Science, Cochrane Library) up to October 2024. Data from seven studies across various medical disciplines and educational levels were included, analyzed descriptively, and evaluated for quality.
Results:
Seven studies demonstrated that ChatGPT-assisted education improves academic performance, clinical skills, and SDL capabilities. Notably, students using ChatGPT showed higher scores in short-term assessments and final exams. ChatGPT 4.0, compared to version 3.5, provided enhanced case generation and communication skills training. Additionally, ChatGPT-supported learning boosted students' SDL, critical thinking, and engagement levels, while helping educators manage instructional workload. Conclusion: This study highlights ChatGPT’s strong potential in medical education, significantly enhancing student performance, self-directed learning, and critical thinking. It underscores ChatGPT’s role in personalized learning, supporting the development of essential competencies. ChatGPT 4.0 outperforms version 3.5 with improved case generation and interactive abilities.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.