Logistic Regression to Predict Heart Disease

Abstract

The early diagnosis of cardiovascular disorders can help high risk individuals make decisions about lifestyle adjustments, which can lessen their problems. Using homogeneous data mining approaches, research has sought to identify the most significant risk variables for heart disease as well as reliably estimate the total risk. Recent studies have looked into combining these methods utilizing strategies like hybrid data mining algorithms. In order to offer an accurate model for predicting heart disease, this study suggests a rule-based model to evaluate the accuracy of applying rules to the individual findings of logistic regression, decision trees, and support vector machines on the Cleveland Heart Disease Database. KEYWORDS- Heart disease, support vector machine (SVM), logistic regression, decision trees, and rule based approach