Prediction of Cardiovascular Disease Based on Voting Ensemble Model and SHAP Analysis

Abstract

Cardiovascular Diseases (CVD) or heart diseases cardiovascular diseases lead the list of fatal diseases. However, the treatment of this disease involves a time-consuming process. Therefore, new approaches are being developed for the detection of such diseases. Machine learning methods are one of these new approaches. In particular, these algorithms contribute significantly to solving problems such as predictions in various fields. Given the amount of clinical data currently available in the medical field, it is useful to use these algorithms in areas such as CVD prediction. This study proposes a prediction model based on voting ensemble learning for the prediction of CVD. Furthermore, the SHAP technique is utilized to interpret the suggested prediction model including the risk factors contributing to the detection of this disease. As a result, the suggested model depicted an accuracy of 0.9534 and 0.954 AUC-ROC score for CVD prediction. Compared to similar studies in the literature, the proposed prediction model provides a good classification rate.