Generative AI in medical education: feasibility and educational value of LLM-generated clinical cases with MCQs
LLMs like ChatGPT can rapidly generate clinically relevant case scenarios and MCQs under precise prompts, offering a novel tool for educators and learners. However, expert review remains critical to mitigate risks of AI hallucinations (observed in 16.67% of cases, 2/12) and ensure alignment with curricular standards. Key issues included contradictions in imaging descriptions (e.g., inappropriate use of high-frequency ultrasound for chalazion) and diagnostic logic (e.g., inconsistent gonioscopy findings), underscoring the necessity of human oversight to refine content accuracy and educational utility.
Authors
- Zijing Huang (ORCID: https://orcid.org/0000-0003-2909-2538)
- Kunliang Qiu (ORCID: https://orcid.org/0000-0003-4414-9758)
- Hongxi Wang (ORCID: https://orcid.org/0000-0002-1391-5328)
- Binyao Chen
- Yinglin Cheng
- Qi Zhang (ORCID: https://orcid.org/0000-0002-1914-9695)
- Geng Wang (ORCID: https://orcid.org/0000-0002-5615-4696)
- Haoyu Chen (ORCID: https://orcid.org/0000-0003-0676-4610)
- Jianling Yang (ORCID: https://orcid.org/0000-0003-3260-4346)
- Riping Zhang (ORCID: https://orcid.org/0000-0002-4213-0087)
- Yuqiang Huang (ORCID: https://orcid.org/0000-0003-3290-8243)
Institutions
- Chinese University of Hong Kong (HK)
- Shantou University (CN)
Publication Details
- Journal
- BMC Medical Education
- Published
- 2025-10-27
- DOI
- https://doi.org/10.1186/s12909-025-08085-8
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 3.27