Exploring the possibilities of an artificial intelligence program in the diagnosis of macular diseases

Abstract

BACKGROUND: Macular diseases are a large group of pathological conditions that cause vision loss and visual impairment. Early diagnosis of such changes plays an important role in treatment selection and is one of the crucial factors in predicting outcomes. AIM: To examine the potential of an artificial intelligence program in the diagnosis of macular diseases using structural optical coherence tomography scans. MATERIALS AND METHODS: The study included patients examined and treated at the Federal Research and Clinical Center of Specialized Medical Care and Medical Technologies and Moscow Regional Research and Clinical Institute. In total, 200 eyes with macular diseases were examined, as well as eyes without macular pathologies. A comparative clinical analysis of structural optical coherence tomography scans obtained using an RTVue XR 110-2 tomograph was conducted. The Retina.AI software was used to analyze optical coherence tomography scans. RESULTS: In the analysis of optical coherence tomography scans using Retina.AI, various pathological structures of the macula were identified, and a probable pathology was then determined. The results were compared with the diagnoses made by ophthalmologists. The sensitivity, specificity, and accuracy of the method were 95.16%, 97.76%, and 97.38%, respectively. CONCLUSION: Retina.AI allows ophthalmologists to automatically analyze optical coherence tomography scans and identify various pathological conditions of the fundus.