Artificial Intelligence shows surprising proficiency in retina and glaucoma management

(Image Credit: AdobeStock/13FTStudio)

Researchers from New York Eye and Ear Infirmary (NYEE) of Mount Sinai in New York reported in their recent study that artificial intelligence (AI) matched or surpassed human specialists in accuracy and can support clinicians in patient care.¹

Andy Huang, MD, an ophthalmology resident at NYEE, and lead study author, called the results “eye-opening.”

The study pitted 12 attending specialists and 3 senior trainees against the newest AI system, GPT-4 (Generative Pre-Training–Model 4, OpenAI), which is designed to replicate human performance. The participants were all from the Department of Ophthalmology at the Icahn School of Medicine at Mount Sinai.

The physicians answered 10 questions each about glaucoma and retina that were randomly selected from a list of frequently asked questions by patients from the American Academy of Ophthalmology. The participants also were presented with 20 cases from eye clinics that are affiliated with Mt. Sinai. The responses from the AI system and the participants were compared for accuracy and thoroughness.

The investigators commented, “The results showed that AI matched or outperformed human specialists in both accuracy and completeness of its medical advice and assessments. More specifically, AI demonstrated superior performance in response to glaucoma questions and case-management advice, while reflecting a more balanced outcome in retina questions, where AI matched humans in accuracy but exceeded them in completeness.”

Ophthalmology is characterized by high volume of often complex patients and could be a particularly fertile field for AI, giving specialists more time to practice evidence-based medicine.

Huang emphasized the need for more testing but believes that there is a future for AI in ophthalmology. “AI could serve as a reliable assistant to eye specialists by providing diagnostic support and potentially easing their workload, especially in complex cases or areas of high patient volume. For patients, the integration of AI into mainstream ophthalmic practice could result in quicker access to expert advice coupled with more informed decision-making to guide their treatment.”

Senior author Louis R. Pasquale, MD, FARVO, Deputy Chair for Ophthalmology Research for the Department of Ophthalmology, said, “AI was particularly surprising in its proficiency in handling both glaucoma and retina patient cases, matching the accuracy and completeness of diagnoses and treatment suggestions made by human doctors in a clinical note format. GPT-4 can provide valuable guidance on how to be better clinicians, especially in terms of how we document findings of patient exams.”

Reference:

1. Huang AS, Hirabayashi K, Barna L, et al. Assessment of a large language model’s responses to questions and cases about glaucoma and retina management. JAMA Ophthalmol. 2024; published online February 22, 2024; doi:10.1001/jamaophthalmol.2023.6917