Development, validation, and cost-effectiveness analysis of an AI-assisted three-tiered glaucoma screening model in a...

Area of Science:

• Ophthalmology
• Public Health
• Artificial Intelligence in Medicine

Background:

• Glaucoma is a leading cause of irreversible blindness globally, with an estimated prevalence of 3.54% in individuals aged 40-80.
• Effective chronic disease management for glaucoma relies on early screening and prevention.
• A recognized glaucoma screening model for the Chinese population is currently lacking.

Purpose of the Study:

• To construct and validate an artificial intelligence (AI)-assisted three-tiered glaucoma screening model for community populations in China.
• To assess the cost-effectiveness of the developed AI-assisted glaucoma screening model.
• To address the gap in glaucoma screening strategies for the Chinese demographic.

Main Methods:

• A community population-based cluster randomized controlled trial with a minimum 6-year follow-up.
• A three-tiered screening strategy: high-risk questionnaire (primary), ophthalmic examinations with AI-assisted interpretation (secondary), and tertiary hospital diagnosis (tertiary).
• Recruitment of 28,275 participants across three groups: no screening, routine screening, and tiered screening.

Main Results:

• Primary outcome: glaucoma detection rate.
• Additional primary outcomes: sensitivity and specificity of the screening model.
• Secondary outcomes: cost-effectiveness analysis of screening strategies and diagnostic accuracy comparison between physician-based and AI-assisted interpretation.

Conclusions:

• The study aims to establish a novel, AI-assisted, tiered glaucoma screening model tailored for the Chinese population.
• Validation and cost-effectiveness assessment will determine the model's utility in early glaucoma detection and management.
• Findings are expected to contribute to improved public health strategies for preventing irreversible blindness from glaucoma.