{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T13:37:42Z","timestamp":1770385062730,"version":"3.49.0"},"posted":{"date-parts":[[2025,7,6]]},"group-title":"Ophthalmology","reference-count":25,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,2,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>In the world of Artificial Intelligence (AI), Generative Pretrained Transformer-3 (GPT-3), has gained significant popularity for its demonstrated potential in medical education and diagnostics.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Rationale<\/jats:title>\n                  <jats:p>While AI has shown promising results in healthcare thus far, its understanding of ocular urgencies, particularly uveitis, demands a focused investigation.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>This study explored the application of ChatGPT, a language model derived from GPT-3, in delineating uveitis based on patient presentations and investigations. We analyzed ChatGPT\u2019s communication quality through 14 qualitative metrics by computing patient data at four different levels to act as prompts. These included patient history, drug history, examination findings, and clinical investigations.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    Our results showed that at the initial prompt, ChatGPT\u2019s responses were comprehensive for most (8 out of 14) variables and correct but inadequate for some (3 out of 14) variables in the majority (&gt;50.0%) of uveitis cases.\n                    <jats:italic>Ethical considerations<\/jats:italic>\n                    was the only variable in terms of which responses consistently showed mixed accuracy and outdated data across all prompts in most (95.8%) uveitis cases. Also, none of the ChatGPT responses were completely inaccurate in terms of any variable at any prompt for any uveitis case.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The results reveal ChatGPT\u2019s strengths and limitations in answering queries for patients with uveitis or its differential diagnosis while emphasizing the indispensable role of physicians in ethical decision-making.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.07.05.25330926","type":"posted-content","created":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T16:35:22Z","timestamp":1751819722000},"source":"Crossref","is-referenced-by-count":0,"title":["Assessing ChatGPT\u2019s Performance in Delineating Uveitis: An analysis of responses to real-world case presentations"],"prefix":"10.64898","author":[{"given":"Muhammad Sohail","family":"Halim","sequence":"first","affiliation":[{"name":"Byers Eye Institute, Stanford University, Palo Alto, California"},{"name":"Ocular Imaging Research and Reading Center, Sunnyvale, California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aly Hamza","family":"Khowaja","sequence":"additional","affiliation":[{"name":"Aga Khan University Medical College, Karachi, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zoha Zahid","family":"Fazal","sequence":"additional","affiliation":[{"name":"Byers Eye Institute, Stanford University, Palo Alto, California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanya","family":"Jain","sequence":"additional","affiliation":[{"name":"Byers Eye Institute, Stanford University, Palo Alto, California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kholood","family":"Janjua","sequence":"additional","affiliation":[{"name":"Byers Eye Institute, Stanford University, Palo Alto, California"},{"name":"Ocular Imaging Research and Reading Center, Sunnyvale, California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ammar Aamir","family":"Khan","sequence":"additional","affiliation":[{"name":"Ocular Imaging Research and Reading Center, Sunnyvale, California"},{"name":"University of California, Davis, California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh Ngoc","family":"Tram Tran","sequence":"additional","affiliation":[{"name":"Byers Eye Institute, Stanford University, Palo Alto, California"},{"name":"Ocular Imaging Research and Reading Center, Sunnyvale, California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasir J","family":"Sepah","sequence":"additional","affiliation":[{"name":"Byers Eye Institute, Stanford University, Palo Alto, California"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"issue":"8","key":"2026020515250671000_2025.07.05.25330926v2.1","doi-asserted-by":"crossref","first-page":"1412","DOI":"10.1038\/s41433-024-02958-w","article-title":"Google DeepMind\u2019s gemini AI versus ChatGPT: a comparative analysis in ophthalmology","volume":"38","year":"2024","journal-title":"Eye (Lond)"},{"key":"2026020515250671000_2025.07.05.25330926v2.2","doi-asserted-by":"crossref","unstructured":"Mavrych V , Yaqinuddin A , Bolgova O. Claude, ChatGPT, Copilot, and Gemini Performance versus Students in Different Topics of Neuroscience. Adv Physiol Educ. 2025 Jan 17;","DOI":"10.1152\/advan.00093.2024"},{"key":"2026020515250671000_2025.07.05.25330926v2.3","doi-asserted-by":"crossref","first-page":"3917","DOI":"10.2147\/JMDH.S473680","article-title":"Comparison of the Performance of ChatGPT, Claude and Bard in Support of Myopia Prevention and Control","volume":"17","year":"2024","journal-title":"J Multidiscip Healthc"},{"key":"2026020515250671000_2025.07.05.25330926v2.4","unstructured":"Frontiers | Exploring the opportunities and challenges of NLP models in higher education: is Chat GPT a blessing or a curse? [Internet]. [cited 2025 Jan 19]. Available from: https:\/\/www.frontiersin.org\/journals\/education\/articles\/10.3389\/feduc.2023.1166682\/full"},{"key":"2026020515250671000_2025.07.05.25330926v2.5","doi-asserted-by":"crossref","first-page":"645232","DOI":"10.3389\/fdgth.2021.645232","article-title":"Accessing Artificial Intelligence for Clinical Decision-Making","volume":"3","year":"2021","journal-title":"Front Digit Health"},{"issue":"8","key":"2026020515250671000_2025.07.05.25330926v2.6","doi-asserted-by":"crossref","first-page":"e555","DOI":"10.1016\/S2589-7500(24)00097-9","article-title":"The diagnostic and triage accuracy of the GPT-3 artificial intelligence model: an observational study","volume":"6","year":"2024","journal-title":"Lancet Digit Health"},{"issue":"4","key":"2026020515250671000_2025.07.05.25330926v2.7","doi-asserted-by":"crossref","first-page":"3378","DOI":"10.3390\/ijerph20043378","article-title":"Diagnostic Accuracy of Differential-Diagnosis Lists Generated by Generative Pretrained Transformer 3 Chatbot for Clinical Vignettes with Common Chief Complaints: A Pilot Study","volume":"20","year":"2023","journal-title":"Int J Environ Res Public Health"},{"key":"2026020515250671000_2025.07.05.25330926v2.8","doi-asserted-by":"crossref","unstructured":"David D , Zloto O , Katz G , Huna-Baron R , Vishnevskia-Dai V , Armarnik S , et al. The use of artificial intelligence based chat bots in ophthalmology triage. Eye. 2024 Nov 26;1\u20135.","DOI":"10.21203\/rs.3.rs-4406223\/v1"},{"issue":"4","key":"2026020515250671000_2025.07.05.25330926v2.9","doi-asserted-by":"crossref","first-page":"e301","DOI":"10.1016\/j.jcjo.2023.07.016","article-title":"Artificial intelligence chatbot performance in triage of ophthalmic conditions","volume":"59","year":"2024","journal-title":"Can J Ophthalmol"},{"key":"2026020515250671000_2025.07.05.25330926v2.10","first-page":"695904","article-title":"Epidemiology and Risk Factors in Non-infectious Uveitis: A Systematic Review","volume":"8","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"2026020515250671000_2025.07.05.25330926v2.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2017.03.006"},{"issue":"11","key":"2026020515250671000_2025.07.05.25330926v2.12","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.18240\/ijo.2023.11.13","article-title":"First contact investigations and compliance to treatment in patients with uveitis","volume":"16","year":"2023","journal-title":"Int J Ophthalmol"},{"issue":"2","key":"2026020515250671000_2025.07.05.25330926v2.13","doi-asserted-by":"crossref","first-page":"e187","DOI":"10.1055\/s-0042-1755581","article-title":"Current Landscape of Uveitis Specialists in the United States","volume":"14","year":"2022","journal-title":"J Acad Ophthalmol (2017)"},{"issue":"4","key":"2026020515250671000_2025.07.05.25330926v2.14","doi-asserted-by":"crossref","first-page":"100082","DOI":"10.1016\/j.apjo.2024.100082","article-title":"Managing a patient with uveitis in the era of artificial intelligence: Current approaches, emerging trends, and future perspectives","volume":"13","year":"2024","journal-title":"Asia-Pacific Journal of Ophthalmology"},{"key":"2026020515250671000_2025.07.05.25330926v2.15","doi-asserted-by":"publisher","DOI":"10.1080\/09273948.2023.2253471"},{"issue":"8","key":"2026020515250671000_2025.07.05.25330926v2.16","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1080\/09273948.2023.2266730","article-title":"Chatbots Vs. Human Experts: Evaluating Diagnostic Performance of Chatbots in Uveitis and the Perspectives on AI Adoption in Ophthalmology","volume":"32","year":"2024","journal-title":"Ocular Immunology and Inflammation"},{"key":"2026020515250671000_2025.07.05.25330926v2.17","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad072"},{"key":"2026020515250671000_2025.07.05.25330926v2.18","doi-asserted-by":"crossref","unstructured":"Mohammadi SS , Khatri A , Jain T , Thng ZX , Yoo W sun , Yavari N , et al. Evaluation of the Appropriateness and Readability of ChatGPT-4 Responses to Patient Queries on Uveitis. Ophthalmology Science [Internet]. 2025 Jan 1 [cited 2025 Jan 24];5(1). Available from: https:\/\/www.ophthalmologyscience.org\/article\/S2666-9145(24)00130-1\/fulltext","DOI":"10.1016\/j.xops.2024.100594"},{"issue":"1","key":"2026020515250671000_2025.07.05.25330926v2.19","first-page":"100600","article-title":"Analysis of ChatGPT Responses to Ophthalmic Cases: Can ChatGPT Think like an Ophthalmologist?","volume":"5","year":"2024","journal-title":"Ophthalmol Sci"},{"key":"2026020515250671000_2025.07.05.25330926v2.20","doi-asserted-by":"publisher","DOI":"10.2196\/48009"},{"issue":"7","key":"2026020515250671000_2025.07.05.25330926v2.21","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.1038\/s41433-023-02906-0","article-title":"Reliability and accuracy of artificial intelligence ChatGPT in providing information on ophthalmic diseases and management to patients","volume":"38","year":"2024","journal-title":"Eye (Lond)"},{"issue":"4","key":"2026020515250671000_2025.07.05.25330926v2.22","doi-asserted-by":"crossref","first-page":"100324","DOI":"10.1016\/j.xops.2023.100324","article-title":"Evaluating the Performance of ChatGPT in Ophthalmology","volume":"3","year":"2023","journal-title":"Ophthalmol Sci"},{"key":"2026020515250671000_2025.07.05.25330926v2.23","unstructured":"Hatem R , Simmons B , Thornton JE . A Call to Address AI \u201cHallucinations\u201d and How Healthcare Professionals Can Mitigate Their Risks. Cureus. 15(9):e44720."},{"key":"2026020515250671000_2025.07.05.25330926v2.24","unstructured":"Can ChatGPT Help in the Awareness of Diabetes? | Annals of Biomedical Engineering [Internet]. [cited 2025 Jan 19]. Available from: https:\/\/link.springer.com\/article\/10.1007\/s10439-023-03356-1"},{"key":"2026020515250671000_2025.07.05.25330926v2.25","unstructured":"Artificial Intelligence in Global Health: Defining a Collective Path Forward | Global Health | U.S. Agency for International Development [Internet]. [cited 2025 Jan 19]. Available from: https:\/\/www.usaid.gov\/cii\/ai-in-global-health"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.05.25330926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:25:16Z","timestamp":1770333916000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.07.05.25330926"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1101\/2025.07.05.25330926","relation":{},"subject":[],"published":{"date-parts":[[2025,7,6]]},"subtype":"preprint"}}