Jul 2026
Comparative performance of chatgpt and gemini in diagnostic classification and clinical reasoning for open-angle glaucoma: a standardized scenario-based study
Error pattern analysis indicated that Gemini was more prone to overdiagnosis and reasoning inconsistency, whereas GPT-5.3 was relatively conservative, and ChatGPT and Gemini both demonstrate certain capabilities in diagnosing POAG, but their stability on borderline cases remains limited.
Zhe-Wen Zhang, Siyu Lu, Zhen-Qiang Xu et al.
· International ophtalmology · 0 citations