Diabetic retinopathy (DR) and age-related macular degeneration (AMD) are leading causes of vision loss, with rising incidence due to aging populations and increasing diabetes prevalence. However, delayed diagnoses are common due to low disease literacy and lack of dedicated screening tools in internal medicine. This multi-center RCT at National Taiwan University Hospital evaluates the clinical effectiveness and cost-effectiveness of the VeriSee AI-assisted diagnostic software for DR and AMD screening. Participants include adults with diabetes and individuals aged 50 and above meeting AMD screening criteria, randomized to AI-assisted screening with immediate physician explanation or standard physician-only screening. Primary outcomes include detection rates of DR and AMD, ophthalmology referral outcomes, and patient/physician satisfaction. Data collection will occur from April 2025 to December 2027. This study aims to provide evidence on the clinical utility of AI-assisted ophthalmic screening in improving early detection, facilitating timely treatment, and reducing severe visual impairment and healthcare burdens in real-world clinical settings.
VeriSee AMD is used in non-retinal subspecialty ophthalmology clinics for adults aged 50 and above.
VeriSee DR is used in non-retinal subspecialty clinics for diabetic patients aged 20 and above.
The patient does not agree to participate in the trial or is unable to provide informed consent.
Parallel
VeriSee AI-assisted screening tools for diabetic retinopathy and age-related macular degeneration
Other interventionVeriSee DR is an AI-assisted diagnosis screening tool for diabetic retinopathy, the software received medical device license approval from the TFDA in 2020 (MOHW-MD-No.006966). VeriSee AMD is an AI-assisted diagnosis screening tool for age-related macular degeneration, the software also received medical device license approval from the TFDA in 2022 (MOHW-MD-No.007652).
Standard fundus photography with physician interpretation
Other interventionThe control group will undergo the fundus photography without AI-functionality, with reports interpreted solely by physicians. Participants must schedule a follow-up visit to receive their results.
The proportion of confirmed cases requiring injection or laser treatment
Number of participants who require injection or laser treatment after diagnosis divided by the total number of confirmed participants.
The proportion of screened positive cases requiring treatment, where treatment improves prognosis
Number of screen-positive participants who require treatment and are likely to benefit from the treatment divided by the total number of screen-positive participants.
Click on the lead sponsor to view all of their trials.
National Taiwan University Hospital
Lead sponsor
Ministry of Health and Welfare, Taiwan
Collaborator
Fu Jen Catholic University Hospital
Collaborator
Min-Sheng General Hospital
Collaborator
