Leveraging Large Language Models to Generate Multiple-Choice Questions for Ophthalmology Education
In this survey study, results indicate that an LLM could be used to develop ophthalmology board-style MCQs and expand examination banks to further support ophthalmology residency training. Despite most questions having a low similarity score, the quality, novelty, and readability of the LLM-generated questions need to be further assessed.
Authors
- Rahul Dodhia (ORCID: https://orcid.org/0000-0003-3812-3906)
- Juan Lavista Ferres (ORCID: https://orcid.org/0000-0002-9654-3178)
- William B. Weeks (ORCID: https://orcid.org/0000-0002-9918-1360)
- Beth Wilson
- Shahrzad Gholami (ORCID: https://orcid.org/0000-0001-7338-8147)
- Stephen J. Page (ORCID: https://orcid.org/0000-0002-1756-4561)
- Karine Duarte Bojikian (ORCID: https://orcid.org/0000-0003-3010-7549)
- Dale Fajardo
- Daniel B. Mummert
Institutions
- Microsoft (United States) (US)
- American Academy of Ophthalmology (US)
- University of Washington (US)
- Microsoft Research (United Kingdom) (GB)
Publication Details
- Journal
- JAMA Ophthalmology
- Published
- 2025-10-16
- DOI
- https://doi.org/10.1001/jamaophthalmol.2025.3622
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 3.27