AI-assisted eye screening for diabetic retinopathy and age-related macular degeneration in outpatient clinics
Artificial Intelligence-Aided Screening for Patients With Diabetic Retinopathy and Age-related Macular Degeneration in Family Medicine and Geriatric Medicine Outpatient Clinics: A Randomized Controlled Clinical Trial
NA · National Taiwan University Hospital · NCT07069647
This project will test whether the VeriSee AI software helps doctors find diabetic eye disease and macular degeneration earlier in adults with diabetes or people aged 50 and older.
Quick facts
| Phase | NA |
|---|---|
| Study type | Interventional |
| Enrollment | 4300 (estimated) |
| Ages | 20 Years and up |
| Sex | All |
| Sponsor | National Taiwan University Hospital (other) |
| Locations | 1 site (Taipei) |
| Trial ID | NCT07069647 on ClinicalTrials.gov |
What this trial studies
This is a multicenter, randomized controlled trial at National Taiwan University Hospital comparing AI-assisted fundus-photo screening using VeriSee plus immediate physician explanation versus standard physician-only fundus interpretation. Adults with diabetes (age 20+) and adults aged 50+ who meet AMD screening criteria are randomized to one of the two screening approaches. Primary outcomes include detection rates of diabetic retinopathy and AMD, subsequent ophthalmology referrals and outcomes, patient and physician satisfaction, and a parallel cost-effectiveness analysis. Data collection is planned from April 2025 through December 2027 across the main and Bei-Hu hospital branches.
Who should consider this trial
Good fit: Ideal candidates are adults with diabetes aged 20 and older or adults aged 50 and above who meet AMD screening criteria and can provide informed consent at participating outpatient clinics.
Not a fit: Patients who already have advanced retinal disease under active ophthalmology care, those with ungradable fundus images, or those unable to consent are unlikely to benefit from the screening intervention.
Why it matters
Potential benefit: If successful, the AI-assisted screening could increase early detection of sight-threatening eye disease and reduce late-stage vision loss and related healthcare costs.
How similar studies have performed: Previous studies of AI-based fundus screening have shown good diagnostic accuracy and improved detection rates in primary-care settings, so this trial builds on promising prior work.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * 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. Exclusion Criteria: * The patient does not agree to participate in the trial or is unable to provide informed consent.
Where this trial is running
Taipei
- National Taiwan University Hospital — Taipei, Taiwan (RECRUITING)
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Age-Related Macular Degeneration, Diabetic Retinopathy, Artificial Intelligence, Randomized Controlled Trial, Fundus Photography