Table-based language models for ophthalmology assessment in the emergency department
GPT-4o could accurately synthesize tabular data and provide assessments and diagnoses in real-world ophthalmology encounters, in addition to identify encounters with documentation that did not support the final ED encounter diagnosis. This capability has the potential to support the clinician's diagnosis.
Authors
- Lauren Lee (ORCID: https://orcid.org/0009-0007-6330-0448)
- Juan Lavista Ferres (ORCID: https://orcid.org/0000-0002-9654-3178)
- Shu Feng (ORCID: https://orcid.org/0000-0002-8372-6063)
- Kathryn L. Moore (ORCID: https://orcid.org/0000-0002-0792-1537)
- Karine Duarte Bojikian (ORCID: https://orcid.org/0000-0003-3010-7549)
- Minji Kim (ORCID: https://orcid.org/0000-0001-9044-7145)
- Nadia Popovici
Institutions
- Microsoft (United States) (US)
- University of Washington (US)
- University of Washington Applied Physics Laboratory (US)
Publication Details
- Journal
- Graefe s Archive for Clinical and Experimental Ophthalmology
- Published
- 2025-10-13
- DOI
- https://doi.org/10.1007/s00417-025-06972-w
- Primary Topic
- Clinical Reasoning and Diagnostic Skills
- Type
- article
- Field-Weighted Citation Impact
- 0.00