JMIR Publications

ABSTRACT

Background:

Visual impairment (VI) affects over 600 million people globally and significantly reduces quality of life. In Singapore, 20% of adults aged ≥60 years (~180,000) have VI—a figure expected to double by 2030 due to population aging. While half of VI cases is due to uncorrected refractive errors, the rest are caused by age-related diseases. The current traditional screening model is a two-visit, labor-intensive approach with low follow-up rates and frequent unnecessary referrals. AVIRI, a deep learning model using retinal images to detect disease-related VI, has shown strong performance (AUC = 0.942) but has yet to be evaluated in real-world settings.

Objective:

This study aims to evaluate the referral accuracy, operational efficiency, acceptability, feasibility, and cost of an AI-assisted screening model compared to the current vision screening model.

Methods:

This study aims to recruit 900 participants aged ≥50 years using a two-arm pragmatic randomized controlled trial (pRCT) design. Participants with presenting visual acuity (VA) worse than 6/12 (L2) will be randomized 1:1 into either the AI-assisted or traditional screening arms. In the AI-assisted arm, AI model will analyze retinal photos on-site, with positive cases referred to an optometrist for secondary evaluation. The AI model, previously developed with high diagnostic accuracy and further validated using community-acquired data, has been integrated with a custom user interface for use in this study. Traditional screening will include pinhole VA, intraocular pressure, slit lamp examination, auto refraction, and retinal photography. All L2 participants will complete a patient-acceptance questionnaire and undergo gold standard assessments.

Results:

As of 14 September 2025, 487 participants have been recruited. Recruitment is ongoing.

Conclusions:

This study will provide critical evidence on the clinical utility, feasibility, and cost analysis of AI-assisted VI screening. Our findings may contribute real-world evidence to inform scalable, sustainable screening strategies that enhance efficiency, accuracy, and health system outcomes. Clinical Trial: This study has been registered on ClinicalTrials.gov [NCT06877988].