Heart disease risk prediction using machine learning techniques

Abstract

We are living in the modern age and our daily life is undergoing multiple changes that directly have positive and negative effects on our health. Different types of diseases are greatly increased for this changing nature where heart disease has become more prevalent. As a consequence, people's lives are at risk. The changes in blood pressure, cholesterol, pulse rate, etc. can lead to heart diseases that include narrowed or blocked blood vessels. It may cause Heart failure, Congenital heart disease, Coronary artery disease, Myocardial infarction (Heart attack), Hypertrophic cardiomyopathy, Pulmonary stenosis, and even sudden cardiac arrest. Many forms of heart disease can be detected or diagnosed with different medical tests by considering the family medical history and other factors. But it is quite hard to predict heart disease without any medical exams. But "Machine Learning" is making it a little simpler nowadays. The purpose of the current study is to predict the risk of heart diseases and to make people aware of their daily routine with high accuracy. For the prediction of heart disease risk, we use five ‘Machine Learning’ classification algorithms such as Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB), Artificial Neural Network (ANN) and Random Forest (RF). Our finding demonstrates that DT with greater precision (97.83%) outperforms the SVM, NB, ANN, and RF. Finally, the research has been completed by developing an app (application system) named HeartCare which can predict the symptoms of heart disease