In focus: AI poses risk and reward conundrum for profession

Developments in artificial intelligence (AI) presented recently at the American Academy of Ophthalmology (AAO) 2019 Annual Meeting in San Francisco have once again thrust the technology, and the impact it may have on their roles in future, into the consciousness of eye care professionals.

Researchers found the automated EyeArt screening system could detect diabetic retinopathy with 95.5% accuracy within 60 seconds, all without the input of an ophthalmologist. Findings that will have certainly grabbed the attention of the industry.

The study was made up of 893 diabetes patients from 15 different international locations. All participants underwent undilated two-field fundus imaging for automated eye-level detection of referable diabetic retinopathy by EyeArt. Researchers defined referable diabetic retinopathy as refractory diabetic retinopathy, clinically significant diabetic macular edema, moderate non-proliferative diabetic retinopathy or higher on the International Clinical Diabetic Retinopathy scale. Patients also underwent wide-field fundus imaging for the adjudicated Early Treatment Diabetic Retinopathy Study (ETDRS) reference standard.