Explainable Ensemble Machine Learning Framework for Predicting Cardiovascular Disease: A Clinical, Behavioral, and Socio-demographic Insights from Bangladesh

Cardiovascular diseases (CVD) continue to be a leading cause of illness and death globally, with increasing prevalence in Bangladesh. Deep learning and machine learning techniques have emerged as highly effective techniques in the medical field, particularly for the prediction of CVDs. The study employs a dataset comprising 1,222 individuals characterized by 19 clinical and demographic features, utilizing sophisticated preprocessing techniques to improve prediction accuracy. We experimented with several algorithms to find the best option for heart disease prediction. These included Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Deep Neural Networks (DNN), and a Stacking Ensemble Classifier. The proposed approach uses a Stacking Ensemble Classifier made up of several base learners and a meta-model. Hyperparameter…