In a new study, artificial intelligence (AI) outperformed glaucoma specialists and matched retina specialists in diagnostic and treatment accuracy.
The study, published in JAMA Ophthalmology, compared a large language model (LLM) chatbot’s responses with those of eye specialists. In 2023, ChatGPT-4 was used as a medical assistant in New York eye clinics to answer glaucoma and retina questions, as well as in de-identified glaucoma and retinal cases.
The combined question-case mean rank for accuracy was 506.2 for the LLM chatbot and 403.4 for glaucoma specialists. Researchers concluded that their findings support the possibility that AI tools could play a pivotal role as both diagnostic and therapeutic adjuncts.
Sign in to continue
Not already a member of the College?
Start enjoying the benefits of College membership today. Take a look at what the College can offer you and view our membership categories and rates.
In this article we will outline the importance of developing standards for affordable and accessible low-vision service delivery that can be applied globally and that are relevant to both the developed and developing world.