Machine Learning for Cardiovascular Disease Risk Assessment: A Systematic Review

Abstract

Accurate diagnosis and early detection of heart disease can help save lives because it is the primary cause of mortality. If a forecast is inaccurate, patients could potentially suffer significant harm. Today, it is challenging to predict and identify heart disease. 24 hour monitoring is not practical due to the extensive equipment and time required. Heart disease treatments can be both expensive and challenging. In order to obtain the data from databases and use this information to successfully forecast cardiac illness, a variety of data mining techniques and machine learning algorithms are now accessible. We have used every technique to put the heart disease prognosis into practise. The algorithms used in SVM, NAIVE BAYER, REGRESSION, KNN, ADABOOST, DECISION TREE, and XG-BOOST And Voting Ensemble Method.