Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report.According to news reporting out of Toronto,Canada,by NewsRx editors,research stated,"Ophthalmology is reliant on effective int erpretation of multimodal imaging to ensure diagnostic accuracy.The new ability of ChatGPT-4 (OpenAI) to interpret ophthalmic images has not yet been explored." Our news journalists obtained a quote from the research from the University of T oronto,"To evaluate the performance of the novel release of an artificial intel ligence chatbot that is capable of processing imaging data.This cross-sectional study used a publicly available dataset of ophthalmic cases from OCTCases,a me dical education platform based out of the Department of Ophthalmology and Vision Sciences at the University of Toronto,with accompanying clinical multimodal im aging and multiple-choice questions.Across 137 available cases,136 contained m ultiple-choice questions (99%).The chatbot answered questions requ iring multimodal input from October 16 to October 23,2023.The primary outcome was the accuracy of the chatbot in answering multiple-choice questions pertainin g to image recognition in ophthalmic cases,measured as the proportion of correc t responses.ch2 Tests were conducted to compare the proportion of correct respo nses across different ophthalmic subspecialties.A total of 429 multiplechoice questions from 136 ophthalmic cases and 448 images were included in the analysis .The chatbot answered 299 of multiple-choice questions correctly across all cas es (70%).The chatbot's performance was better on retina questions than neuro-ophthalmology questions (77% vs 58%; diffe rence = 18%; 95% CI,7.5%-29.4% ; ch21 = 11.4; P<.001).The chatbot achieved a better perf ormance on nonimage-based questions compared with image-based questions (82% vs 65%; difference = 17%; 95% CI,7.8% -25.1%; ch21 = 12.2; P<.001).The chatbot perf ormed best on questions in the retina category (77% correct) and p oorest in the neuro-ophthalmology category (58% correct).The chat bot demonstrated intermediate performance on questions from the ocular oncology (72% correct),pediatric ophthalmology (68% correct),uveitis (67% correct),and glaucoma (61% correct) categories.In this study,the recent version of the chatbot accurately responde d to approximately two-thirds of multiple-choice questions pertaining to ophthal mic cases based on imaging interpretation.The multimodal chatbot performed bett er on questions that did not rely on the interpretation of imaging modalities."
NETL
NSTL