A Post-processing Ensemble Machine Learning Approach for Prediction and Classification of Cardiovascular Disease

Cardiovascular Disease (CVD) is one of the dangerous diseases which affecting the human health. CVD is the significant cause of mortality as well as morbidity in the population of the world. The prediction and diagnosis of CVD is challenging in clinical data analysis as well as health care providers to avert the patient from diminishing like disease as well as preserve lives. An automatic detection for the classification of arrhythmia performs a significant role in managing as well as curing the cardiovascular diseases. Therefore, this research proposes the post-processing ensemble Machine Learning (ML) approach for the prediction and classification of CVD. Initially, this research collected the publicly available Kaggle dataset of CVD for validate the effectiveness of the model. Then, handling missing values as well as data unbalancing techniques are used for the data pre-processing. After that, Principal Component Analysis (PCA) is used for the selection of relevant features. Finally, post-processing ensemble ML approach is used for the classification of CVD. The proposed method is estimated by various performance metrices and it achieves the accuracy of 99.56% when compared to the previous approaches such as Support Vector Machine (SVM) and Gradient Boosting (GB).