Deep Learning for Cardiac Risk Detection via Retinal Imaging

Cardiovascular diseases (CVDs) continue to be the primary cause of morbidity and mortality around the world. Early detection and management are critical to improving patient outcomes and minimizing the load on healthcare systems. Recent study reveals an association between retinal vascular alterations and cardiovascular health. Retinal scans provide a non-invasive method of assessing micro vascular anomalies, making them a valuable source of data for predictive modeling. This research aims to create a machine learning model that employs Recurrent Neural Networks (RNNs) to scan retinal images and detect patterns associated with heart disease. RNNs are well-suited for processing sequential data, thus they can capture temporal dependencies in retinal pictures and improve the model's predictive accuracy. Key Words: Cardiovascular diseases, Recurrent Neural Networks light, micro vascular anomalies, non-invasive