Study Finds Eyenuk Artificial Intelligence Detects Diabetic Retinopathy with Greater Sensitivity than Dilated Exams

Eyenuk announced the publication of EyeArt validation results in Ophthalmology Science, a peer-reviewed journal of the American Academy of Ophthalmology.

In a the titled “Artificial Intelligence Detection of Diabetic Retinopathy: Subgroup Comparison of the EyeArt System with Ophthalmologists' Dilated Exams,” Eyenuk evaluated general ophthalmologists, retina specialists, and its EyeArt AI system for detecting diabetic retinopathy (DR).

Professor Jennifer I. Lim MD, Vice Chair of Ophthalmology, UIC Distinguished Professor of Ophthalmology and Director of the Retina Service at The University of Illinois at Chicago and the first author on the publication commented on the results.

“As compared to the Reading Center grading, which was the reference standard, the sensitivity for detection of more than mild DR was significantly greater with the EyeArt AI system than with either a general ophthalmologist or a retina specialist clinical examination. Unlike a few instances in which general ophthalmologists missed some cases of vision-threatening diabetic retinopathy, the EyeArt AI system did not miss any cases of vision-threatening DR. The AI system is a significant tool to help us tackle the burden of DR screening and detection of DR in a timely manner.”

Results of the study

The study assessed the sensitivity and specificity of the EyeArt system and dilated eye exams conducted by general ophthalmologists and retina specialists against the clinical reference standard from the Early Treatment Diabetic Retinopathy Study (ETDRS). 521 people participated in the study.

Sensitivity, a measure of safety (percentage of patients with disease identified correctly), was 96.4% for the EyeArt system in identifying more than mild DR (mtmDR), while that of ophthalmologists’ dilated exams was 27.7% on the identical cohort of study participants. Specificity, a measure of effectiveness (percentage of patients without disease identified correctly), was 99.6% by ophthalmologists’ dilated exams compared to 88.4% with the EyeArt system.

This result demonstrates that dilated exams by ophthalmologists are better at ruling out disease as evidenced by their high specificity. The EyeArt system, on the other hand, is significantly better at identifying patients with disease (at the frontlines of care) thanks to its outstanding sensitivity, which is crucial in a screening situation where patients are being identified for referral and further examination.

According to the study, the EyeArt system generated actionable results for more than 97% of eyes with most (85.3%) not requiring dilation. In contrast, dilated exams provided actionable results for 99.9% of eyes but required all patients to be dilated.

Prof. Lim and co-authors concluded the paper by stating that, “Given the current low rate of compliance with the recommendation for an annual diabetic retina examination, this system can be a useful adjunct in the detection of mtmDR and appears to be more accurate than clinical ophthalmoscopy for routine retinal screening.” 

The EyeArt system, which received FDA clearance in 2020, is currently being used to scan more than 60,000 patients at more than 200 locations across 18 countries, including 14 U.S. states. It is the first and only technology that has received FDA approval for the autonomous diagnosis of diabetic retinopathy that is both referable and vision-threatening.

Source: Ophthalmology Science