Eyenuk has gained regulatory clearance to market its autonomous AI system, EyeArt, for detecting diabetic retinopathy (DR).
According to the press release, the system is indicated for use by healthcare providers to automatically detect more than mild DR and vision-threatening DR in adults who not have been previously diagnosed with more than mild DR. EyeArt is already approved in Canada and Europe, and is the second AI-based DR screening platform to receive the FDA’s green light after the IDx-DR system in April 2018.
In the United States, the platform is designed for use with 2 non-mydriatic fundus cameras: Canon CR-2 AF and Canon CR-2 Plus AF. Once images are uploaded, EyeArt returns a report in under 60 seconds and indicates the presence or absence of referable or vision-threatening DR.
The FDA’s decision was based on a prospective, multicenter clinical trial comprising 915 participants. Each underwent 2-field retinal photography followed by dilated 4-widefield stereo retinal photography, later assessed by expert graders, for the reference standard. For mild DR, the system achieved a 96% sensitivity and 88% specificity; vision-threatening DR was detected with a 92% sensitivity and 94% specificity.
Eyenuk claims that novice operators can be trained to obtain medical grade retinal images. Even at sites where most operators did not have prior ophthalmic imaging experience, 97% of images were deemed gradable.
“This is great news to over 30 million Americans living with diabetes, especially those who may have vision-threatening diabetic retinopathy. The EyeArt autonomous AI System can now enable safe, effective, and equitable diabetic eye screening at convenient point-of-care locations, with AI results available in less than 1 minute,” said Kaushal Solanki, PhD, founder and CEO of Eyenuk. “This historical FDA clearance is our first major milestone enabled by our prospective, multicenter pivotal clinical trial which took us years to plan and complete.”