Scholarlink

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, underscoring the need for accurate early diagnosis and prevention. This study evaluates ensemble machine learning algorithms for CVD prediction using the 2015 Behavioral Risk Factor Surveillance System dataset, which includes demographic, lifestyle, and medical history features. The modeling pipeline involved preprocessing, feature selection, and evaluation of K-Nearest Neighbors (KNN), Random Forest, XGBoost, AdaBoost, and Gradient Boosting. Performance was assessed using Accuracy and Log Loss. Gradient Boosting achieved the best results with 90.79% accuracy and a log loss of 3.32, closely followed by AdaBoost. These findings confirm the superiority of boosting algorithms over traditional classifiers and highlight the potential of ML to support preventive healthcare and clinical decision-making.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ensemble Machine Learning Approaches for Predictive Modeling of Cardiovascular Disease

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Gerasimos Vonitsanos,
  • Andreas Kanavos,
  • Khalil Al-Hussaeni,
  • Ioannis Karamitsos,
  • Vassilis C. Gerogiannis

摘要

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, underscoring the need for accurate early diagnosis and prevention. This study evaluates ensemble machine learning algorithms for CVD prediction using the 2015 Behavioral Risk Factor Surveillance System dataset, which includes demographic, lifestyle, and medical history features. The modeling pipeline involved preprocessing, feature selection, and evaluation of K-Nearest Neighbors (KNN), Random Forest, XGBoost, AdaBoost, and Gradient Boosting. Performance was assessed using Accuracy and Log Loss. Gradient Boosting achieved the best results with 90.79% accuracy and a log loss of 3.32, closely followed by AdaBoost. These findings confirm the superiority of boosting algorithms over traditional classifiers and highlight the potential of ML to support preventive healthcare and clinical decision-making.