Cardio-Eye Connection: Retinal Eye Imaging for Heart Attack Risk Prediction

Cardiovascular diseases (CVDs) remain a leading cause of global mortality. Early identification of individuals at risk is crucial for effective intervention and prevention. Recent advancements in ophthalmology have revealed a potential link between retinal vascular changes and systemic vascular diseases, particularly coronary artery disease. Retinal imaging, a non-invasive technique, allows for the visualization and analysis of the retinal microvasculature. By examining features such as vessel caliber, tortuosity, and bifurcations, researchers can identify potential indicators of systemic vascular dysfunction. Machine learning models, particularly convolutional neural networks (CNNs), enhance the predictive analysis of these features. This study presents a methodology combining retinal imaging with machine learning to predict heart attack risk, validated through extensive evaluations and demonstrating significant potential for clinical applications.