Cardiovascular Disease Prediction in Retinal Fundus Images Using ERNN Technique

Abstract

In recent years, heart disease increases the humanity rate transversely the world. So, it is required to extend a model to envisage the heart disease incident as early as feasible with an elevated rate of accuracy. In this study, cardiovascular disease is predicted by a novel method with the retinal image data. In this system, the retinal fundus image data are used to indicate heart disease occurrence. The cardiovascular disease gets detected from the changes in the microvasculature, which is imaged from the retina. The prediction of disease is by considering features like age, gender, smoking status, systolic blood pressure, diastolic blood pressure, and HbA1c that can be extracted using Improved GLCM approach. Then the pointed features can be selected using the ICA algorithm. Risk factors for heart disease occurrence are detected from the microvasculature of ERNN-classified retinal fundus image using MATLAB. The input image is taken from the UCI machine learning repository based on Cleveland datasets. The main objective of the proposed system is to predict the occurrence of heart disease from retinal fundus image with a higher rate of accuracy.