SAN FRANCISCO – A new AI-powered retinal tracker can analyze retinal images with near perfect accuracy in less than a second, according to a survey, the annual meeting of the Endocrine Society, the Endocrine Society's annual meeting in San Francisco, California.
“The application is an AI-based model integrated into a simple mobile AI Retina tracker (SMART), which uses cutting-edge deep learning algorithms to quickly and accurately analyze fundus images of the retina on internet-powered devices, including basic smartphones.” “The SMART AI application allows ophthalmologists to streamline patient screening, enable primary care providers to incorporate the eyes into their daily visits, and expand access to high-quality retinal assessments in areas lacking specialized ophthalmic care.”
Diabetic retinopathy, the leading cause of preventable blindness, affects more than 100 million people worldwide as the incidence and prevalence of diabetes continues to rise worldwide.
Two researchers, Ramya Elangovan and Kavin Elangovan of AIM Doctor in Houston, Texas, have sourced thousands of anonymized retinal images from multiple datasets representing diverse populations across six continents. These images were used to train and validate deep learning models that could detect and stage diabetic retinopathy with an accuracy of over 99% in less than 1 second. Trackers were also able to distinguish diabetic retinopathy from similar ocular pathology. Health professionals from multiple international organizations independently validated the reliability and ease of use of applications, highlighting global applicability.
“By democratizing eye care through universally accessible mobile technology, this innovation could screen billions worldwide, reducing vision loss from diabetic retinopathy while transforming healthcare delivery systems,” said the project's main leaders, MB, BS, PGDHM, M.Tech. “This study demonstrates that AI is a power for good, can bridge gaps in care and bring hope to millions of people at risk of losing their eyesight.”
/Public release. This material of the Organization of Origin/Author is a point-in-time nature and may be edited for clarity, style and length. Mirage.news does not take any institutional position or aspect, and all views, positions and conclusions expressed here are the views of the authors alone.
