Artificial Intelligence-Aided Screening for Patients With Diabetic Retinopathy and Age-related Macular Degeneration in Family and Geriatric Medicine Clinics: A Randomized Controlled Trial

What this Trial Is About

Diabetic retinopathy (DR) and age-related macular degeneration (AMD) are leading causes of vision loss, with their incidence rising due to aging populations and increasing diabetes prevalence. This trial evaluates the clinical and cost-effectiveness of VeriSee, an AI-assisted diagnostic software, for screening DR and AMD in adults with diabetes and individuals aged 50 and above. Conducted as a multi-center randomized controlled trial at National Taiwan University Hospital, the study aims to improve early detection and reduce severe visual impairment and healthcare burdens in real-world clinical settings. Participants are randomly assigned to one of two groups: the intervention group receives AI-assisted fundus image analysis using VeriSee software with immediate explanation of results by physicians during the same visit, and the control group undergoes standard fundus photography interpreted solely by physicians, with results given at a follow-up visit. If abnormalities are detected in either group, participants are referred for further ophthalmologic evaluation. Data collection will occur from April 2025 to December 2027. Throughout the study, researchers will track referral outcomes, diagnostic results, and gather patient and physician satisfaction surveys to assess feasibility and acceptance of AI-assisted screening. The primary outcome measures include the proportion of confirmed cases requiring injection or laser treatment within about one month from screening to diagnosis. This study seeks to provide evidence on the clinical value and impact of AI in ophthalmic screening for earlier diagnosis and timely treatment.

Artificial Intelligence-Aided Screening for Patients With Diabetic Retinopathy and Age-related Macular Degeneration in Family Medicine and Geriatric Medicine Outpatient Clinics