Prashant D Tailor, Timothy T Xu, Blake H Fortes, Raymond Iezzi, Timothy W Olsen, Matthew R Starr, Sophie J Bakri, Brittni A Scruggs, Andrew J Barkmeier, Sanjay V Patel, Keith H Baratz, Ashlie A Bernhisel, Lilly H Wagner, Andrea A Tooley, Gavin W Roddy, Arthur J Sit, Kristi Y Wu, Erick D Bothun, Sasha A Mansukhani, Brian G Mohney, John J Chen, Michael C Brodsky, Deena A Tajfirouz, Kevin D Chodnicki, Wendy M Smith, Lauren A Dalvin
OBJECTIVE: To determine the appropriateness of ophthalmology recommendations from an online chat-based artificial intelligence model to ophthalmology questions. PATIENTS AND METHODS: Cross-sectional qualitative study from April 1, 2023, to April 30, 2023. A total of 192 questions were generated spanning all ophthalmic subspecialties. Each question was posed to a large language model (LLM) 3 times. The responses were graded by appropriate subspecialists as appropriate, inappropriate, or unreliable in 2 grading contexts...
March 2024: Mayo Clin Proc Digit Health