Eyenuk AI detects diabetic retinopathy more sensitively than dilation scans

During the 2022 American Academy of Ophthalmology Annual Meeting, Eyenuk Inc. About strong version EyeArt Result from validation Ophthalmology sciencesa peer-reviewed journal of the American Academy of Ophthalmology.

According to a press release, the study is titled “AI discovery of diabetic retinopathy: Comparing EyeArt subgroups with expanded ophthalmologists’ examinationsEvaluation of general ophthalmologists, retina specialists and Eyenuk’s EyeArt An artificial intelligence system to detect diabetic retinopathy (DR), a major cause of blindness among working-age adults.

Jennifer I. Lim, MD, vice chair of ophthalmology, UIC Distinguished Professor of Ophthalmology and Director of Retinal Service at the University of Illinois at Chicago and first author of the publication, offered her assessment of the findings.

Compared with the reading center rating, which was the reference standard, the sensitivity of detection over light DR was significantly greater with EyeArt The AI ​​system is not with a general ophthalmologist or clinical examination specialist in the retina,” she said in the press release. “Unlike the few cases where general ophthalmologists missed some cases of vision-threatening diabetic retinopathy, EyeArt The artificial intelligence system did not miss any cases that threaten the vision of Dr. An AI system is an important tool to help us handle the burden of DR screening and DR detection in a timely manner. “

According to a company press release, the study evaluated sensitivity and privacy EyeArt System and dilated eye examinations by ophthalmologists and retinologists against the strict clinical reference standard for the Early Treatment of Diabetic Retinopathy Study (ETDRS) on the same group of 521 study participants. The ETDRS reference standard was developed by experts at the University of Wisconsin Reading Center using 10 images of the fundus taken after dilation by certified photographers, while the EyeArt The system analyzed only two images of each eye, usually without dilation.

The company also noted that sensitivity, a measure of safety (the proportion of patients correctly identified), was 96.4%. EyeArt system in determining more than moderate DR (mtmDR), while ophthalmologists’ extended testing was 27.7% in a similar group of study participants. Specificity, a measure of efficacy (percentage of patients for whom disease is not correctly identified), was 99.6% with expansive examinations of ophthalmologists compared with 88.4% with EyeArt the system.

Moreover, the company indicated that this result demonstrates that invasive examinations by ophthalmologists are better at ruling out disease as evidenced by their higher specificity. However, the EyeArt system, with its excellent sensitivity, is much better at identifying patients with disease (on the front lines of care), which is a critical factor for the screening scenario in which patients are identified for referral and further evaluation.

Moreover, the company noted that the study also stated that EyeArt The system achieved actionable results for more than 97% of eyes and most (85.3%) did not require dilation. In contrast, dilatational examinations provided actionable results for 99.9% of eyes but required dilatation for all patients.

“Given the current low rate of compliance with the recommendation for annual diabetic retinal examination, this system could be a useful adjunct in detecting mtmDR and appears to be more accurate than clinical ophthalmoscopy for routine examination of the retina,” the authors concluded.

FDA approved in 2020, and EyeArt The system is now used at more than 200 sites in 18 countries, including 14 US states, to screen more than 60,000 patients and the number is growing. It is the first and only technology approved by the Food and Drug Administration (FDA) to self-screen for vision-threatening referral diabetic retinopathy.

AAO 2022 Symposium to Review Realistic Results of Using EyeArt

Eyenuk will showcase its AI technologies for eye screening of diabetic patients at AAO 2022. On October 2, Eyenuk AI technologies will be showcased at an AAO live industry demonstration seminar titled “Health System Adoption of FDA-Approved AI Technology for Screening Diabetic Retinopathy.” in primary care.”

Ophthalmology leaders from many academic medical centers will discuss their vision and progress in adopting Eyenuk AI technologies to improve diabetic eye care and population health.

The speakers at the symposium are:

  • RV Paul Chan MD, MSc, MBA, FACS, Chair, Division of Ophthalmology and Visual Sciences, University of Illinois at Chicago
  • Eric D. Hansen, assistant professor of ophthalmology and visual sciences, University of Utah
  • Jeffrey D. Hender, chair of the department of ophthalmology, Lewis Katz School of Medicine at Temple University
  • Stephen Yeh, MD, president and director, Retina and Uveitis, University of Nebraska Medical Center

The AAO Industry Showcase Seminar will take place on Sunday, October 2nd at 2:10pm CET, at McCormick Venue (Suite #1026). October 1-3, AAO 2022 attendees can watch a demo of EyeArt Artificial intelligence system and other Eyenuk technologies by visiting booth No. 2033.

Leave a Comment