A novel AI-powered retina tracker can analyze retinal images with near-perfect accuracy in under one second, according to a study being presented Monday at ENDO 2025, the Endocrine Society’s annual meeting in San Francisco, Calif. The researchers say the findings offer hope for sight-saving screenings for diabetic retinopathy and other eye diseases that are fast, affordable and accessible worldwide.
“The application, an AI-based model integrated into Simple Mobile AI Retina Tracker (SMART), uses cutting-edge deep learning algorithms to analyze retinal fundus images quickly and accurately, on internet-powered devices including basic smartphones,” according to presenting author Jansi Rani Sethuraj, B.S.N., R.N., C.C.R.N., of the University of Texas Health Sciences Center in Houston, Texas. “The SMART AI application enables ophthalmologists to streamline patient screening, empowers primary care providers to incorporate eye exams into routine visits, and expands access to high-quality retinal assessments in regions lacking specialized ophthalmic care."
Diabetic retinopathy, a leading cause of preventable blindness, affects over 100 million people globally as the incidence and prevalence of diabetes continue to rise worldwide.
Two young researchers, Ramya Elangovan and Kavin Elangovan of AIM Doctor in Houston, Texas, sourced several thousand anonymized retinal images from multiple datasets representing diverse populations spanning six continents. These images were used to train and validate deep learning models capable of detecting and staging diabetic retinopathy with over 99% accuracy in under one second. The tracker was also able to differentiate diabetic retinopathy from similar eye pathologies. Healthcare professionals from multiple international institutions independently validated the application’s reliability and usability, underscoring its global applicability.
“By democratizing eye care through universally accessible mobile technology, this innovation has the potential to screen billions globally, reducing vision loss from diabetic retinopathy while transforming healthcare delivery systems,” said the chief mentor of this project, Elangovan Krishnan, M.B., B.S., P.G.D.H.M., M.Tech., M.S., Ph.D., of AIM Doctor. “This research proves that AI can be a force for good, bridging gaps in care and bringing hope to millions at risk of losing their sight.”
About Endocrine Society
Endocrinologists are at the core of solving the most pressing health problems of our time, from diabetes and obesity to infertility, bone health, and hormone-related cancers. The Endocrine Society is the world’s oldest and largest organization of scientists devoted to hormone research and physicians who care for people with hormone-related conditions.
The Society has more than 18,000 members, including scientists, physicians, educators, nurses, and students in 122 countries. To learn more about the Society and the field of endocrinology, visit our site at www.endocrine.org. Follow us on X (formerly Twitter) at @TheEndoSociety and @EndoMedia.
Colleen Williams Associate Director, Communications and Media Relations Phone: (202)-971-3611 [email protected]
Jenni Glenn Gingery Director, Communications and Media Relations Phone: (202)-971-3655 [email protected]
The Endocrine News podcast brings you the latest research and clinical advances from experts in the field, whether you are in your car, office, or out for a run.
Our top-ranked peer-reviewed journals are among the first to publish major developments and discovery milestones.
