AEYE Health gets FDA clearance to use AI to screen diabetics in hopes of preventing blindness

By hillel fuld

November 15, 2022

It’s long been said the eyes are the window to the soul. If that’s the case, wouldn’t you want to protect them?

The Tel Aviv-based healthtech firm AEYE Health announced on Tuesday it has received clearance from the U.S. Food & Drug Administration to market its diagnostic screening system for diabetic retinopathy, a complication of diabetes caused by high blood sugar levels that can damage the retina and cause blindness if left undiagnosed. The company’s automated, AI-based diagnostic screening technology targets the large and growing diabetic retinopathy market.

“As a team, we are motivated by our mission to prevent unnecessary blindness from millions of people around the world, and this recent FDA clearance will allow us to do exactly that,” says AEYE CEO and cofounder Zack Dvey-Aharon. 

That clearance could be a game-changer for the millions of people who are at high risk of diabetic retinopathy (a condition that remains the top cause of blindness in the working-age population). 

Globally, the number of people with diabetic retinopathy will grow from 126.6 million in 2010 to 191.0 million by 2030. The condition can be treated and prevented if it is detected early. Diabetics should be screened annually, but due to a global shortage of ophthalmologists, high cost, and lack of access, only 25% of those who need it actually receive the screening.

Instead of needing an annual appointment with an ophthalmologist for screening, AEYE patients will be able to receive initial screening from their primary care physician or at other healthcare facilities including retail pharmacies. Only patients for which the AI system detects potential disease need to be referred to a specialist. 

AEYE’s FDA approval is based on pivotal Phase III study results, which redefine both efficacy and usability of autonomous diagnostics in ophthalmology, including best-in-class clinical efficacy with 93% sensitivity and 91.4% specificity, improved usability for primary caregivers with only one image per eye required, and over 99% of patients receiving a diagnostic result in under a minute.

The technology is also unique in that it rarely requires dilation, making it even more practical. AEYE’s AI achieves its results using images captured with an off the shelf camera—no proprietary lens needed.

“The time has finally come for autonomous screening technology to exceed the efficacy of the human expert,” says Tsontcho Ianchulev, a board member at AEYE and an ophthalmology professor at Mount Sinai. “The implications are that it can be practical for deployment on the front lines of population health—the primary care offices, where 99% non-mydriatic imageability and single image diagnostic acquisition are tantamount to market success.” 

AEYE Health has accomplished all of this with minimal funding of under $10 million, but now, following the FDA clearance, the company may be raising additional capital.

If the tech sounds like magic, well, it feels like magic, too. I say that having given it a whirl.

The patient places his or her chin on the device, a photo of the retina is produced by the camera, the photos are uploaded to the cloud for analysis, and a diagnostic result is returned in under a minute.

Like so many medical conditions, early detection is critical to ensure good treatment outcomes. Given this FDA clearance, AEYE aims to make screening for diabetic retinopathy as easy and ubiquitous as checking blood pressure. (As a matter of fact, when I visited their office and tried out the solution, I got diagnostics for 15 different indications.)

While their solution is approved in the U.S. to screen for diabetic retinopathy, their goal is to make an even broader screening solution through the eye available for everyone.

While we might not have found a cure for cancer, we know exactly what is needed to prevent diabetic retinopathy. Now all we need to do is make that screening process easier and more user-friendly. That is exactly what the AEYE team has set out to accomplish.

(40)