Heart Disease Prediction Using Eye Retinal Images

Cardiovascular disease (CVD) remains the leading cause of morbidity and mortality worldwide. Early detection and risk assessment of cardiovascular diseases are important for effective prevention and timely intervention. An analysis of deep learning methods used for prediction of CVR based on RFI. Since it is an extension of central nervous system, the retina gives an exceptional chance for safe medical diagnosis. Using multiple types of retinal fundus images together with the patient and clinical data, we developed a new deep learning model for prediction of several vital parameters for cardiovascular diseases. With CNN, it is possible to extract relevant features from retinal images without involving any manual procedures. The main aim of our study is to predict hypertension, diabetes and hyperlipidemia, which are risk factors for cardiovascular diseases. Our deep learning model achieves incredible accuracy in identifying high-risk individuals by identifying changes in brain vessels, microaneurysms, and other signs of pathology. Additionally, the model provides good information about the relationship between the visibility of the eye and the severity of these problems. We also consider ways of interpreting predictive models which help us understand how retinal changes relate to CV risk based on pathophysiological mechanism. Such research can lead the doctors on how to improve themselves if possible and intervene earlier for the sake of preventing this health condition.