Predicting the risk of systemic diseases using eye images: Clinical and Cost-Effectiveness

Chronic diseases like diabetes, cardiovascular disease, chronic kidney disease and dementia pose significant healthcare challenges and costs, underscoring the importance of early detection for effective intervention and cost reduction. The retina, a neurovascular structure with shared origins and anatomical resemblances to crucial organs like the heart, brain, and kidneys, offers a non-invasive means of health assessment. Previous research has shown promise in using deep learning-based biomarkers derived from retinal images to predict systemic diseases and mortality. However, its performance in predicting clinical outcomes across diverse populations, particularly in Singaporeans, remains unverified.

By linking the de-identified ocular data from over 10,000 individuals in the population-based Singapore Epidemiology of Eye Disease study and the disease progression and healthcare costs data from the TRUST platform, this project will evaluate the clinical and cost-effectiveness of ocular image-based biomarkers in predicting systemic diseases such as diabetes, chronic kidney disease, dementia, cancer, and mortality.

Findings from this study hold the potential to enable the early detection of high-risk individuals, paving the way for tailored interventions and optimized resource allocation. Consequently, this project could inform a more individualized and cost-effective approach to disease prevention and management, ultimately enhancing both clinical practice and healthcare efficiency in Singapore.