Predicting Cardiovascular Disease with Machine Learning Algorithms: A Review

Abstract

Early detection of cardiovascular disease symptoms is one of the hardest things for professionals to do. Cardiovascular disease comes in many forms, including stroke, congenital heart disease (CHD), peripheral artery disease (PAD), and coronary artery disease (CAD). Comparing several feature selection methods to accurately predict cardiovascular disease is the main objective of this study. The renowned random forest, support vector classifier, k-nearest neighbors, Naive Bayes, and gradient boosting model have been taken into consideration in order to support the comparative accuracy and define the best predictive analytics. These algorithms use data analysis to forecast when heart failure will occur. This study processes the data to predict coronary illness. Finding more effective datasets, however, is essential to the effectiveness of the machine learning model. We have reviewed several machine learning algorithms that are currently in use, together with their benefits and drawbacks, in this work. We have also talked about a few outstanding research questions that will support future studies in this area.

Keywords

• svm
• random forest
• knn
• naïve bayes
• gradient boosting