Prediction of Cardiovascular Diseases Through Machine Learning Algorithms: A Supervised Model

Abstract

Heart disease is the leading cause of mortality worldwide, ranking as the number one killer of humans. Machine learning (ML) algorithms are not just employed to detect the presence or absence of cardiac disease. However, it is also useful in forecasting the various stages of cardiovascular disease, beginning with stage 1 and progressing to stages 2, 3, and 4 (severe heart disease), respectively. In the current study, three supervised machine algorithms are employed to determine which approach has the greatest accuracy. Models such as Logistic Regression (LR), Super Vector Machine (SVM), and Random Forest (RF) are employed with hyper parameters to optimize classifier performance and determine which one is best for detecting the stage at which the individual is suspected of having disease. The experimental findings suggest that Logistic Regression (LR) has higher Accuracy, Precision, Recall and F-Measure i.e. 82%, 91%, 80%, 85% respectively.