Efficacious Cardiovascular Disease Estimation Using Machine Learning

Abstract

We live in a modern era when our daily lives are undergoing numerous changes that have direct and indirect consequences on our health, which can be positive or negative. For this changing nature, where heart disease has grown more frequent, different forms of illnesses have substantially increased. Heart disease has been the most frequent cause of mortality throughout past years. The number of fatalities on heart among both men and women rises by the day. Changes in blood pressure, cholesterol, pulse rate, and other factors can contribute to cardiac disorders such as restricted or blocked blood arteries. Because most heart problems are identified at the very end, a precise forecast may lessen the tragedy associated with heart diseases. Because of this In this context, we use five machine learning algorithms, including Linear Regression, Decision Tree, Random Forest, Support Vector Machine, and Naive Nayes to three heart disease datasets combined to compare their performance in terms of attaining accurate prediction. The dataset comprises sixteen health characteristics that have been linked to heart disease. We also proposed combining these three datasets to produce a unique prediction that might discover a new accuracy point by offering a good forecast on the data of 5730 persons.