Heart Disease Risk Prediction Using Hybrid Deep Learning on Retinal Fundus Images

Abstract

Early detection of individuals at high risk of cardiovascular disease remains a major challenge in preventive healthcare, particularly in regions with limited access to advanced diagnostic facilities. Traditional risk assessment methods rely on laboratory tests and invasive procedures, which restrict large-scale screening.This paper proposes a hybrid deep learning framework for heart disease risk prediction using retinal fundus images. The proposed model integrates deep visual features extracted using convolutional neural networks with handcrafted retinal vascular features such as vessel density, tortuosity, and fractal dimension. While deep learning captures complex spatial patterns, handcrafted features provide clinically interpretable insights. A feature-level fusion strategy is employed to combine both representations and classify individuals into low-, medium-, and high-risk categories. Experimental results demonstrate that the proposed model achieves superior performance compared to standard deep learning models, particularly in identifying highrisk cases. The proposed framework offers a scalable, noninvasive, and interpretable solution for early cardiovascular risk screening.