AI versus human-generated multiple-choice questions for medical education: a cohort study in a high-stakes examination
ChatGPT-4o demonstrates the potential for efficiently generating MCQs but lacks the depth needed for complex assessments. Human review remains essential to ensure quality. Combining AI efficiency with expert oversight could optimise question creation for high-stakes exams, offering a scalable model for medical education that balances time efficiency and content quality.
Authors
- Chun Tat Lui (ORCID: https://orcid.org/0000-0002-2913-5772)
- Colin A. Graham (ORCID: https://orcid.org/0000-0002-4381-7470)
- Kevin Kei Ching Hung (ORCID: https://orcid.org/0000-0001-8706-7758)
- Alex Kwok-Keung Law (ORCID: https://orcid.org/0000-0002-6218-949X)
- Koon Ho Cheung
- Yu Fai Choi
- Jerome Lok Tsun So
Institutions
- Chinese University of Hong Kong (HK)
- Hong Kong College of Technology (CN)
- Tseung Kwan O Hospital (CN)
- Prince of Wales Hospital (CN)
Publication Details
- Journal
- BMC Medical Education
- Published
- 2025-02-08
- DOI
- https://doi.org/10.1186/s12909-025-06796-6
- Citations
- 50
- Primary Topic
- Clinical Reasoning and Diagnostic Skills
- Type
- article
- Field-Weighted Citation Impact
- 75.79
Funders
- College of Emergency Medicine