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

NCT07069647 | Recruiting DMC

• 3 other identifiers: 202505015DINEFJUH114483CIRB2025003
• Study Type: interventional
• Target: 4,300
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Age-Related Macular Degeneration (AMD); Diabetic Retinopathy (DR)

Keywords

Age-Related Macular Degeneration (AMD); Diabetic Retinopathy (DR); Artificial Intelligence; Randomized Controlled Trial; Fundus Photography

Outcome Measures

Primary Outcomes (1)

• 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.

  From screening to physician-confirmed diagnosis of AMD or DR, an average of 1 month

Secondary Outcomes (1)

• The proportion of screened positive cases requiring treatment, where treatment improves prognosis

  From screening to physician-confirmed diagnosis of AMD or DR, an average of 1 month

Study Arms (2)

AI-Assisted Screening

EXPERIMENTAL

Intervention group (physicians assisted by AI): After the fundus photography is completed, the AI software (VeriSee AMD and VeriSee DR) will automatically retrieve and analyze the image data from Picture Archiving and Communication System (PACS) to generate the results. The research team will immediately provide the AI-generate results to physicians, enabling participants to receive their reports and results during the same visit. If any abnormalities are detected, the physicians will refer the participants for further ophthalmologic evaluation.

Other: VeriSee AI-assisted screening tools for diabetic retinopathy and age-related macular degeneration

Standard Physician Screening

ACTIVE COMPARATOR

Control group (physicians diagnosing without AI assistance): After the fundus photography is completed, participants will need to schedule a follow-up appointment with the attending physicians to receive their report and have preliminary assessment of the possibility of DR or AMD. If the physician detects any abnormalities, the physicians will refer the participants for further ophthalmologic evaluation.

Other: Standard fundus photography with physician interpretation

Interventions

VeriSee AI-assisted screening tools for diabetic retinopathy and age-related macular degeneration OTHER

VeriSee 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).

AI-Assisted Screening

Standard fundus photography with physician interpretation OTHER

The 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.

Standard Physician Screening

Eligibility Criteria

• Age: 20 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• The patient does not agree to participate in the trial or is unable to provide informed consent.

Sponsors & Collaborators

• National Taiwan University Hospital: lead
• Ministry of Health and Welfare, Taiwan: collaborator
• Fu Jen Catholic University Hospital: collaborator
• Min-Sheng General Hospital: collaborator

Study Sites (1)

National Taiwan University Hospital

Taipei, 100225, Taiwan

RECRUITING

MeSH Terms

Conditions

Macular Degeneration; Diabetic Retinopathy

Condition Hierarchy (Ancestors)

Retinal Degeneration; Retinal Diseases; Eye Diseases; Diabetic Angiopathies; Vascular Diseases; Cardiovascular Diseases; Diabetes Complications; Diabetes Mellitus; Endocrine System Diseases

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 14, 2025
• First Posted: July 17, 2025
• Study Start: October 2, 2025
• Primary Completion (Estimated): December 31, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: November 19, 2025

Record last verified: 2025-07

Locations

TW (1)