Ensemble Meta-Learning using SVM for Improving Cardiovascular Disease Risk Prediction

Abstract

Cardiovascular diseases (CVDs) remain a leading cause of mortality worldwide, posing a significant public health challenge. Early identification of individuals at high risk of CVD is crucial for timely intervention and prevention strategies. Machine learning techniques are increasingly being applied in healthcare for their ability to uncover complex patterns within large, multidimensional datasets. This study introduces a novel ensemble meta-learning framework designed to enhance cardiovascular disease (CVD) risk prediction. The framework strategically combines the predictive power of diverse machine learning algorithms: logistic regression, K nearest neighbors, decision trees, gradient boosting, gaussian Naive Bayes and XGBoost. Predicted probabilities from these base models are integrated using support vector machine as meta-learner. Rigorous performance evaluation over publicly available dataset demonstrates the improved performance of this ensemble approach compared to individual. This research highlights the potential of ensemble meta-learning techniques to improve predictive modeling in healthcare.