A recent study conducted at the New York Eye and Ear Infirmary of Mount Sinai (NYEE) has revealed groundbreaking findings in the field of eye care. The study compared the performance of a large language model (LLM) artificial intelligence (AI) system named GPT-4 with human ophthalmologists in diagnosing and treating patients with glaucoma and retina diseases.
Published in JAMA Ophthalmology, the study demonstrated that the AI system was able to match or even outperform human specialists in terms of accuracy and completeness of medical advice and assessments. This suggests that advanced AI tools, trained on extensive data, text, and images, have the potential to significantly enhance decision-making support in the field of ophthalmology.
Lead author of the study, Dr. Andy Huang, highlighted the remarkable performance of the AI system, stating that GPT-4 could not only assist but in some cases surpass the expertise of seasoned ophthalmic specialists. The study involved comparing responses from the AI system and human specialists to a set of questions and patient cases, with AI demonstrating superior performance in handling both glaucoma and retina cases.
Senior author of the study, Dr. Louis R. Pasquale, emphasized the potential of AI in revolutionizing the diagnosis and treatment of eye conditions, noting that the AI system could provide valuable guidance to clinicians in documenting patient findings and improving clinical practice.
The Mount Sinai team recruited 12 attending specialists and three senior trainees to participate in the study, with AI consistently matching or exceeding the accuracy and completeness of diagnoses and treatment suggestions made by human doctors.
Dr. Huang believes that the integration of AI into mainstream ophthalmic practice could lead to quicker access to expert advice for patients and support eye specialists in managing complex cases and high patient volumes. While further testing is needed, the study points to a promising future for AI in ophthalmology and the potential for AI to serve as a reliable assistant to eye specialists.
The findings of this study open up new possibilities for leveraging AI in the field of eye care, highlighting the potential of advanced technology to enhance medical decision-making and improve patient outcomes.
