Effect of Random Under sampling, Oversampling, and SMOTE on the Performance of Cardiovascular Disease Prediction Models

Abstract

Cardiovascular Disease (CVD) or commonly known as Heart Disease is a leading cause of mortality globally, prompting extensive research into predictive models to assess individual risk and plan preventive measures. Machine learning approaches such as Random Forest, Support Vector Machine (SVM), and LASSO Logistic Regression have showed promise. Recent studies have indicated that traditional resampling methods like Random Oversampling, Random Undersampling, and SMOTE may not significantly improve model discrimination. This study aims to evaluate the impact of these techniques on the performance of Cardiovascular Disease (CVD) prediction models, utilizing data from the UCI Machine Learning Heart Disease database. By employing LASSO Logistic Regression, Random Forest, and Support Vector Machine (SVM) with resampling techniques, including Random Oversampling, Random Undersampling, and SMOTE. This research seeks to enhance understanding of model performance in addressing class imbalances within the dataset and contribute to refining cardiovascular disease (CVD) prediction strategies. This study demonstrates that the use of the SMOTE technique significantly enhances the performance of cardiovascular disease (CVD) prediction models. Specifically, when combined with the Random Forest algorithm, SMOTE achieves the best performance in terms of accuracy, sensitivity, and specificity. This highlights the importance of selecting appropriate resampling techniques to handle class imbalance in datasets. Consequently, this research contributes to refining CVD prediction strategies and provides new insights into improving prediction accuracy in imbalanced medical data.