Optimizing Cardiovascular Disease Risk Assessment with Machine Learning Models

Abstract

Cardiovascular disease is the leading cause of death in the world and is responsible for approximately 31% of all deaths. Therefore, CVD risk prediction is imperative but challenging due to the complex interactions among genetic markers, lifestyle habits, and metabolic indicators. Traditional clinical and statistical methods struggle to capture these complexities. This study evaluates multiple Machine Learning (ML) models, including Logistic Regression, Support Vector Machine (SVM), Random Forest, Neural Networks, Gradient Boosting, and XGBoost, on a public dataset with age, blood pressure, cholesterol, and lifestyle attributes. Accuracy, precision, recall, F1-score, and ROC-AUC were compared. XGBoost achieved the best performance with 77% accuracy and 0.8434 ROC-AUC, highlighting the potential of ensemble ML methods in early CVD risk detection for personalized healthcare interventions.

Ähnliche Arbeiten