INTELLIGENT ML-BASED CARDIOVASCULAR RISK PREDICTION FRAMEWORK FOR PREVENTIVE DIGITAL HEALTHCARE

Abstract

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, highlighting the increasing need for proactive and intelligent healthcare solutions. Early risk prediction enables timely intervention and reduces severe health outcomes. This research proposes an Intelligent Machine Learning (ML)- Based Cardiovascular Risk Prediction Framework designed to analyze clinical and lifestyle attributes to accurately forecast patient risk levels. Multiple ML models such as Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient Boosting are evaluated to determine the most reliable predictor for CVD risk forecasting, based on accuracy, sensitivity, specificity, and AUC-ROC metrics. A simulated healthcare dataset is used to validate the framework under real-world data conditions. Experimental analysis demonstrates that ensemble-based models deliver superior performance and robustness in identifying highrisk patients compared to traditional classifiers. The results confirm that ML-driven predictive analytics can play a significant role in preventive cardiology, improving early diagnosis, personalized treatment planning, and overall clinical decision-making in digital healthcare ecosystems.