Evaluating large language models in answering patient questions about eye removal surgeries
ChatGPT and Gemini showed comparable accuracy and low harm potential when addressing patient questions about eye removal surgeries. Gemini provided more consistent and readable responses, but both LLMs exceeded the recommended readability levels for patient education. These findings highlight the potential of LLMs to assist in patient communication and clinical education while underscoring the need for careful oversight in their implementation.
Authors
- Marissa K. Shoji (ORCID: https://orcid.org/0000-0002-6297-4674)
- Niloufar Bineshfar (ORCID: https://orcid.org/0000-0001-8177-9105)
- Tejus Pradeep (ORCID: https://orcid.org/0000-0002-0506-069X)
- Wendy W. Lee (ORCID: https://orcid.org/0000-0001-7624-777X)
- Sugi Panneerselvam (ORCID: https://orcid.org/0000-0002-9136-6141)
- Natalia Davila
- Chloe Shields
Institutions
- University of Miami (US)
- University of California San Diego (US)
- The University of Texas Medical Branch at Galveston (US)
Publication Details
- Journal
- Orbit
- Published
- 2025-09-30
- DOI
- https://doi.org/10.1080/01676830.2025.2559735
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65