Sophie Chen '23

Titile of Research: Feasibility of Artificial Intelligence based Telemedicine in Age-Related Macular Degeneration (AMD)

Mentor: Dr. Grace Vernon & Dr. R. Theodore Smith 

Abstract: Age-related macular degeneration (AMD) is an eye disease that damages the macula, which is the center of the retina, a light-sensitive tissue that lines the back of the eye. AMD is the leading cause of blindness, and it impairs central vision, causing people to lose their ability to perform tasks like driving and reading. We aim to prevent blindness by allowing for large-scale screening through a telemedicine platform to identify people with AMD. An FDA-approved camera and computer software program is developed to conduct automatic non-fundus photos in individuals 50 years and above, the age group that is most susceptible to developing AMD. Captured retinal images are uploaded securely to an AI software program called iPredictHealth and analyzed by a deep learning algorithm. Referable AMD included intermediate AMD (drusen >125 μm and/or pigmentary abnormalities) and late AMD (geographic atrophy or neovascularization), while non-referable AMD included eyes with a normal macula or early AMD (drusen >63 to ≤125 μm). Ophthalmologists grade the images, and the performance of the AI-based system is evaluated by comparing its results with the ophthalmologists' analyses. Analyses showed that the AI-based platform had 88.67% accuracy, 86.57% sensitivity, and 90.36% specificity.