FDA clears fully autonomous AI for portable diabetic retinopathy screening
Click Here to Manage Email Alerts
AEYE Health has received the first-ever FDA clearance for a fully autonomous AI that can diagnose referable diabetic retinopathy using retinal images taken by a handheld camera, according to a company-issued press release.
This affordable and accessible solution is especially suited for point-of-care screening at clinics or at home, the company stated, and can help address the leading cause of blindness in working-age adults.
According to the release, AEYE diagnostic screening technology has already received FDA clearance and is commercially available with a tabletop imaging device. It is the only technology that screens patients with just one image per eye with more than 99% imageability and now is the first and only AI solution that provides autonomous screening via the Optomed Aurora portable handheld device.
The new clearance was based on two large-scale, prospective phase 3 studies, which demonstrated the technology’s efficacy and imageability. In both studies, more than 99% of patients received diagnostic results, which were produced using only a single image from each eye and mostly without dilation, the release stated. Diagnostic sensitivity ranged from 92% to 93%, with specificity of 89% to 94%.
“This is the ‘holy grail’ of eye screening — fully autonomous AI, using either portable or tabletop retinal cameras and a procedure that takes a minute to perform, alongside the best-in-class diagnostic efficacy,” Zack Dvey-Aharon, PhD, the company’s cofounder and CEO, said in the release. “In the coming years our fully autonomous screening technology will become standard across points of care in the U.S. We believe this innovation will prevent the blindness of millions of people in the U.S. and around the world.”
Diabetic retinopathy screening with AI serves as a major HEDIS measure for most health plans and is now reimbursable in the U.S., according to the release.