AI platform screens for diabetic retinopathy in 60 seconds

An artificial intelligence software platform is able to provide automated real-time screening for quick detection of diabetic retinopathy, without the help of an expert ophthalmologist.

The AI platform, called EyeArt from vendor Eyenuk, was used to screen 893 patients with diabetes at 15 different medical locations as part of a new study.

Results of the study, which compared EyeArt against experts using the gold standard for visual acuity testing, were presented on Tuesday at the Annual Meeting of the American Academy of Ophthalmology.

What researchers found was that the AI platform accurately detected diabetic retinopathy 95.5 percent of the time, using images of patients’ undilated pupils.

“The system doesn’t require the input of an expert ophthalmologist, and it can provide a reading in 60 seconds, making real-time screening possible for primary care practices and diabetes centers,” according to the American Academy of Ophthalmology. “Accurate, automated screening is an important development for millions of patients living with diabetes who need to be screened yearly for vision-threatening diabetic retinopathy.”

artificial_intelligence_DR_screening.jpg

Diabetic retinopathy is a condition that can lead to permanent vision loss if not caught early by clinicians trained to recognize signs of the disease. However, ophthalmic screening is time consuming and requires expert readers.

“Diabetic patients already outnumber practicing ophthalmologists in the United States, and unfortunately, that imbalance is only expected to grow,” says SriniVas Sadda, MD, president and chief scientific officer of UCLA’s Doheny Eye Institute. “Accurate, real-time diagnosis holds great promise for the millions of patients living with diabetes. In addition to increased accessibility, a prompt diagnosis made possible with AI means identifying those at risk of blindness and getting them in front of an ophthalmologist for treatment before it is too late.”

While EyeArt has been cleared for sales as a Class IIa medical device by the EU and as a Class 2 medical device by Health Canada, it is limited by federal law in the United States to investigational use only and is not available for sale.

Nonetheless, Eyenuk contends that EyeArt is the “most extensively validated AI technology for autonomous detection of diabetic retinopathy, tested in the real-world on more than half million patients and nearly two million retinal images globally."

For reprint and licensing requests for this article, click here.