Heart Disease Classification Using Machine Learning Models

Abstract

AbstractHeart Disease (HD) is a candidate for the utmost communal death-recording diseases in history and an early detection is a herculean task for countless physicians. This paper aims at developing a precise and efficient machine learning (ML) classification model for HD. The HD dataset was subjected to seven different machine learning models, including k-Nearest Neighbour (k-NN), eXtreme Gradient Boosting (XGBoost), Extra Trees (ET), Decision Tree (DT), Light Gradient Boosting Machine (LGBM), Support Vector Machine (SVM), and Random Forest (RF). Recall, precision, F1-Score, accuracy, ROC, and RPC were all used to evaluate the proposed models. The results obtained based on the aforementioned metrics in comparison to other models indicate that ET performed better. ET achieved 87% accuracy, precision (0.88), RPC (0.86), Recall (0.87), ROC (0.94), and F1-score (0.935) respectively. The outcomes indicates that ML models can classify HD patients effectively.KeywordsHeart diseaseMachine learningBoostingClassificationDecision treeRandom ForestExtra treeLight gradient boosting method