Artificial Intelligence (AI) - Assisted Visual Impairment Screening Model: Community-based Implementation and Evaluation of Performance, Feasibility and Costs.

NCT06877988 | Active Not Recruiting

• 1 other identifier: 2024/2297
• Study Type: interventional
• Target: 400
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to evaluate the performance, operational efficiency, acceptability, feasibility, and cost-effectiveness of an AI-assisted screening model for visual impairment in a community setting. The main questions it aims to answer are:

• Can the AI-assisted screening model improve screening and referral accuracy compared to the current traditional screening approach?
• Does the AI-assisted model enhance operational efficiency and reduce healthcare costs in a community setting? Researchers will compare the AI-assisted model with the current traditional screening approach to assess its impact on screening accuracy, operational efficiency, and cost-effectiveness. Participants will:
• Undergo vision screening using either the AI-assisted model or the traditional model.
• Provide feedback on the acceptability of the screening approach.
• Contribute to evaluating the feasibility and costs associated with each screening method.

Conditions

Visual Impairment

Keywords

Visual impairment; Community Screening; Randomized Controlled Trial (RCT); Artificial Intelligence (AI)

Outcome Measures

Primary Outcomes (1)

• Performance of AVIRI on the detection of visual impairment

  The primary outcome is the detection performance for VI (refractive error-related and disease-related VI) and the rate of correct referral, with reference to the expert panels' diagnosis . To assess whether the new AI-assisted model has better referral accuracy than the current traditional model, the accuracy, AUC values, sensitivity, specificity and other performance metrics of the two models will be calculated and compared.

  through study completion, an average 1 year

Secondary Outcomes (4)

• Operational efficiency

  through study completion, an average 1 year

• Patient acceptability

  through study completion, an average 1 year

• Perceptions of feasibility

  through study completion, an average 1 year

• Cost savings of implementing the AI-assisted screening model

  through study completion, an average 1 year

Study Arms (2)

AI-assisted

EXPERIMENTAL

Participants will undergo visual impairment screening using AVIRI model (AI for Disease-related Visual Impairment Screening Using Retinal Imaging). This intervention involves automated fundus image analysis through artificial intelligence to screen and identify individuals with high probability of visual impairment.

Device: AI

Traditional

NO INTERVENTION

Participants will receive visual impairment screening using the traditional screening model, which involves optometrists performing initial assessments, followed by referral decisions based on manual fundus image evaluation.

Interventions

AI DEVICE

Retinal photography-based deep learning algorithm for detection of disease-related visual impairment cases

Also known as: AVIRI (AI for Disease-related Visual Impairment Screening Using Retinal Imaging)

AI-assisted

Eligibility Criteria

• Age: 50 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Individuals aged 50 years old and above.

You may not qualify if:

• Individuals aged below 50 years old.

Sponsors & Collaborators

• Institute of High Performance Computing (IHPC), A*STAR Research Institutes: collaborator
• National University Polyclinics, Singapore: collaborator
• Singapore Eye Research Institute: lead

Study Sites (1)

Pioneer Polyclinic

Singapore, Singapore, 648201, Singapore

Location

MeSH Terms

Conditions

Vision Disorders

Condition Hierarchy (Ancestors)

Sensation Disorders; Neurologic Manifestations; Nervous System Diseases; Eye Diseases; Signs and Symptoms; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, OUTCOMES ASSESSOR
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: March 7, 2025
• First Posted: March 14, 2025
• Study Start: June 27, 2024
• Primary Completion: February 27, 2026
• Study Completion: March 31, 2026
• Last Updated: March 11, 2026

Record last verified: 2026-03

Locations

SG (1)