This document explores the possibility of the prediction whether a person is susceptible to various heart diseases like Coronary Artery Disease (CAD), Heart Arrhythmias, Heart Failure, Heart Valve Disease, Pericardial Disease, Cardiomyopathy (Heart Muscle Disease), Congenital Heart Disease and many more which has put a great threat to human beings given how our lives and schedules are evolving into more sedentary ones with the advent of technologies originally made to make our lives easier. A passive lifestyle puts not only our heart at risk, but also is a direct cause of more physical and mental illnesses and diseases like osteoporosis, lipid disorders diabetes, depression and anxiety, and increase the risks of different types of cancer and a higher blood pressure. In this article, we have aimed to study the various different factors that may or may not be in direct correlation of heart diseases. These factors are as follows: Age, sex, chest pain type, resting blood pressure, cholesterol in mg/dl, fasting blood sugar, resting electrocardiography results, maximum heart rate achieved, exercise induced angina, ST depression induced by exercise, slope of the peak exercise ST segment, number of major vessels and maximum heart rate. We have also compared the correlation of these factors with the possibility of a heart related illness. These factors are elaborated in a more detailed way in this paper. And for the same, we have used multiple algorithms (logistic regression, naïve bayes, Support vector machine, KNN, decision tree, random forest and artificial neural network) and compare the results to find out the most accurate one. We are using dataset from kaggle.com.

Keywords : angina, heart diseases, random forest, heart diseases prediction, classification, ensemble.