An AI-Based OCT System to Detect Diabetic Macular Edema

Can an artificial intelligence (AI)–based optical coherence tomography (AI-OCT) system to detect diabetic macular edema (DME) improve referral performance of diabetic retinopathy screening?In the multicenter noninferiority randomized clinical trial that included individuals with fundus photograph screening reports indicating suspected DME, the false-positive DME referral rate (ie, proportion of referred participants determined to have no DME) was 24.1% in the group that received the addition of the AI-OCT system to standard practice using fundus photographs and 69.1% in the control group that automatically referred all patients based on fundus photographs alone, which satisfied the noninferiority margin of 20%.An AI-based OCT system enhanced referral performance for DME evaluation in diabetic retinopathy screening.

Corresponding Authors: Simon K. H. Szeto, MBChB (simonkhszeto@cuhk.edu.hk), and Carol Y. Cheung, PhD (carolcheung@cuhk.edu.hk), Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, 147K Argyle St, Kowloon, Hong Kong SAR, China.

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.