Enhancing Cardiovascular Disease Risk Prediction Using Resampling and Machine Learning

Cardiovascular Disease (CVD) remains a critical health concern around the globe, requiring precise risk prediction approaches for timely intervention. The primary motive of this study is to enhance CVD risk prediction through innovative techniques, just like resampling the imbalanced datasets using random oversampling and employing advanced Machine Learning (ML). In this study, different robust ML algorithms such as Random Forest Classifier, Decision Tree Classifier, XGBoost Classifier and Logistic Regression were trained on a diverse dataset encompassing demographic, clinical and lifestyle factors related to CVD. By addressing class imbalance through oversampling, the models showed significant performance improvements, showcasing the effectiveness of our ML algorithms in accurately forecasting CVD risks. Specifically, the Random Forest model with an accuracy score of 96% and AUC-ROC score of 99%. This study emphasizes the potentialof modern approaches to improve CVD risk assessment by leveraging cutting-edge technologies for enhanced healthcare outcomes. Enfolding these approaches and tools, it becomes easy to pave the way for more personalized risk assessment and early intervention strategies, eventually aiming to alleviate the global burden of CVD