An Intelligent Clinical Decision Support System Based on Artificial Neural Network for Early Diagnosis of Cardiovascular Diseases in Rural Areas

Abstract

Deaths due to cardiovascular diseases are increasing at an alarming rate. It led to nearly 2.1 million deaths in India in 2015. Being one of the deadliest reasons of death worldwide, heart diseases have majorly affected the lives of rural people. According to a recent study, it was found that deaths due to cardiovascular disease among rural Indians have surpassed those among urban Indians. Such figures are concerning, especially when 68% of the Indian population lives in rural areas having poor access to quality healthcare. This paper aims to provide a solution to this problem by introducing a new model*of a clinical*decision*support*system abbreviated as CDSS that*incorporates machine learning algorithms for the diagnoses of cardiovascular diseases. The CDSS is intelligent enough to diagnose a patient’s*disease*and help the physician to prescribe*proper medication to them thereby reducing the costs and effort required to prescribe unnecessary treatments. *In this work, we have used Correlation-based feature selection (CFS) and Multilayer Perceptron classifier over a large-dataset of heart-disease. The dataset used in this study is the “Cleveland Clinic Foundation Heart Disease Dataset” available at UCI Machine Learning Repository. Our proposed model produced greater accuracy as compared to other existing models used in this study. This system can be incorporated in a public healthcare setting to help the rural people get proper, timely cost-effective diagnosis.