Ipp E, Liljenquist D, Bode B, et al. Pivotal Evaluation of an Artificial Intelligence System for Autonomous Detection of Referrable and Vision-Threatening Diabetic Retinopathy. JAMA Netw Open. 2021;4(11):e2134254. Published 2021 Nov 15. doi:10.1001/jamanetworkopen.2021.34254
OBJECTIVE
To evaluate the safety and accuracy of the EyeArt® autonomous artificial intelligence (AI) diabetic retinopathy (DR) detection system (version 2.1.0) in detecting both more than mild DR (mtmDR) and vision-threatening DR (vtDR).
Design: Prospective multicenter cross-sectional diagnostic study registered with ClinicalTrials.gov (NCT03112005)
Study Population: 942 individuals 18 years or older with diabetes across 15 US study centers (6 primary care, 9 eye care)
Reference Standard: Early Treatment Diabetic Retinopathy Study (ETDRS) grading of 4-wide-field stereoscopic dilated fundus photographs (equivalent to 7-field 30° ETDRS photographs) by the Wisconsin Reading Center (WRC). Two independent certified graders masked to the EyeArt autonomous AI system’s results examined the 4-wide field photographs to establish the reference standard. Between-grader differences exceeding prespecified criteria were adjudicated by a third, more senior grader.
RESULTS
CONCLUSION
The EyeArt autonomous AI System can accurately detect vtDR and mtmDR without physician oversight or need for dilation in most individuals, facilitating diabetic eye examinations at non-specialist facilities and enabling accelerated referral of vtDR.