FDA approves AI technology for diabetic retinopathy screening
The EyeArt system could help efforts to deal with the COVID-19 backlog
Eyenuk received FDA approval for its screening system following a trial involving 915 patients at seven primary care sites and four ophthalmology sites.
The technology displayed 96% sensitivity and 88% specificity for the detection of more than minor diabetic retinopathy, and 92% sensitivity and 94% specificity for the detection of vision-threatening diabetic retinopathy.
The system can be used with Canon CR-2 AF and Canon CR-2 Plus AF fundus cameras. Eyenuk intends on expanding the range of devices the technology is compatible with.
UK scientists have previously published research using the system to analyse 120,000 images from 30,000 patient scans in the English Diabetic Eye Screening Programme.
Professor Alicja Rudnicka, from St George’s, University of London, has previously said that using machine learning technology could safely halve the number of images that need to be assessed by humans.
“If this technology is rolled out on a national level, it could immediately reduce the backlog of cases created due to the coronavirus pandemic, potentially saving unnecessary vision loss in the diabetic population,” she emphasised.