A new AI-powered retina tracker can help doctors screen for a vision-destroying diabetic eye disease, researchers say.
The Simple Mobile AI Retina Tracker (SMART) program achieved greater than 99% accuracy in screening for diabetic retinopathy, researchers reported Monday at the annual meeting of The Endocrine Society in San Francisco.
The program “uses cutting-edge deep learning algorithms to analyze retinal fundus images quickly and accurately, on internet-powered devices including basic smartphones,” researcher Jansi Rani Sethuraj of the University of Texas Health Sciences Center in Houston said in a news release.
“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,” Sethuraj added.
Diabetic retinopathy is a condition in which leaky blood vessels damage a patient’s retina, the light-sensing wall of tissue that lines the back of the eye.
It’s a leading cause of preventable blindness that affects more than 100 million people around the world, researchers said in background notes.
To create the program, researchers trained an artificial intelligence (AI) model on several thousand retinal images from a diverse group of patients spanning six continents.
Researchers then tested the AI on another set of images and found it could detect diabetic retinopathy nearly all the time, with a processing speed of less than one second per image.
The tracker also was able to distinguish diabetic retinopathy from other eye diseases, researchers added.
“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,” researcher Dr. Elangovan Krishnan with AIM Doctor in Houston said in a news release.
“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,” he added.
Findings presented at medical meetings should be considered preliminary until published in a peer-reviewed journal.