Retinal Age as Disease Biomarker
Fundus-based AI screening can indicate “retinal age” of patients, as well as flag systemic disease risks, says new study
Clinical Scorecard: Retinal Age as Disease Biomarker
At a Glance
Category Detail
Condition Biological aging and systemic disease risk assessment Key Mechanisms AI-predicted retinal age compared to chronological age (retinal age gap) Target Population Individuals undergoing retinal imaging, particularly those at risk for systemic diseases Care Setting Routine clinical workflows utilizing fundus photography
Key Highlights
AI model trained on over 50,000 fundus images from 27,000 healthy individuals Achieved mean absolute error of 2.78 years in internal validation Retinal age gaps linked to diabetes, cardiac disease, and stroke history Focus on optic disc, macula, and major vascular arcades for predictions Guideline-Based Recommendations
Diagnosis
Utilize retinal imaging to estimate biological aging and assess disease risk Management
Flag patients with high retinal age gaps for further cardiovascular or metabolic evaluation Monitoring & Follow-up
Consider retinal age as a metric in routine screenings for systemic health Risks
Performance may decline in diverse datasets and is influenced by image quality Patient & Prescribing Data
Predominantly Asian individuals
Integration of AI-based retinal age outputs into existing screening programs
Clinical Best Practices
Incorporate AI-driven retinal age assessments into routine eye care Ensure high-quality fundus images to improve accuracy of predictions Related Resources & Content
