A Machine Learning Ensemble Classifier for Cardiovascular Disease Taxonomy

Abstract

This Paper presents an application of Machine Learning in cardiology and the role of ensemble classifiers for Cardiovascular Disease (CVD) taxonomy. The dataset from Kaggle on CVD was used. Data was cleaned and 5 feature reduction techniques were investigated. Furthermore, a statistical unbiased ensemble feature reduction is proposed by imposing a unitary weight on intersecting features. Considering only 7 features, the Recurrent Feature Elimination and the proposed unbiased-ensemble feature reduction techniques were effective for reducing variables. Here, 6 feature reduction methods are considered. Hence, from each feature reduction method; the diverse selected features are then fed into a set of 5 independent ML techniques to compose a corresponding classifier. This ML approach in turn considers the 5 resultant classifiers and one additional proposed Ensemble Classifier based on those 5 classifiers. This proposed Ensemble Classifier consisted of: Multi-Layer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR) and k-Nearest Neighbor (KNN), classifiers. The output of the Machine Learning (ML) Classifiers approach is a classification/taxonomy to determine an individual with cardiovascular disease; or an individual that is free from cardiovascular disease. By considering the effective Recursive Feature Elimination method and the proposed Ensemble Classifier it was demonstrated that the body weight of an individual, systolic and diastolic blood pressure, cholesterol level, glucose level, level of physical activity, and the age are decisive in diagnosing the CVD condition of an individual. It is relevant to mention that a genetic feature was not available from the considered database; therefore, this potentially important factor was not considered in this study.