The study that led the FDA to approve an AI system for diagnosing diabetic retinopathy came out today, revealing how one of the leading causes of blindness can be detected in a primary care physician’s office.

Published in the journal Nature Digital Medicine, the pivotal study of IDx-DR on 900 adults with diabetes showed 87% sensitivity, 90% specificity, and a 96% imageability rate, demonstrating the AI system’s ability to bring specialty-level diagnostics to primary care settings. Primary care staff at the 10 study sites received four hours of training on IDx-DR.

Diabetic retinopathy occurs when high levels of blood sugar lead to damage in the blood vessels of the retina, the light-sensitive tissue in the back of the eye. It is the most common cause of vision loss among the more than 30 million Americans living with diabetes and the leading cause of vision impairment and blindness among working-age adults. Early detection and treatment of the condition have been shown to prevent vision loss, according to the American Academy of Ophthalmology, yet less than 50% of people with diabetes visit an eye care provider for a retinal exam.

The study compared the accuracy of IDx-DR to the most rigorous determination of the severity of diabetic retinopathy using advanced imaging techniques – wide-field stereo fundus imaging and optical coherence tomography (OCT) evaluated by the Wisconsin Fundus Photograph Reading Center. The Early Treatment of Diabetic Retinopathy Treatment Study (ETDRS) severity scale was used as the reference standard.

“This is formerly uncharted territory in healthcare, making it especially critical that we ensure the highest level of safety before introducing autonomous AI into patient care,” said Dr. Michael D. Abràmoff, the study’s principal investigator and the founder and president of IDx, in a prepared statement. “That’s why it was so important for us to develop an exceptionally rigorous study that was reviewed by independent physician-scientists. Now that the results have been published in Nature Digital Medicine, scientists, physicians and patients can all evaluate the scientific evidence for the safety and effectiveness of an autonomous AI like IDx-DR.”

IDx-DR is indicated for use with the Topcon NW400 retinal camera. Coralville, Iowa-based IDx is also developing AI-based diagnostic algorithms for the detection of macular degeneration, glaucoma, Alzheimer’s disease, cardiovascular disease, and stroke risk.