Scholarlink

Heart disease remains a leading cause of morbidity and mortality worldwide, driven by various Behavioral Patterns such as age, smoking habits, and exercise frequency. This study explores the predictive power of these Behavioral Patterns in forecasting heart disease through ensemble learning techniques. Using a comprehensive dataset, we applied multiple machine learning models, including Random Forest, Extra Trees, LightGBM, CatBoost, and XGBoost, to build a robust predictive model. Our analysis revealed significant correlations between lifestyle factors and heart disease, with age, smoking, and exercise being strong predictors. The ensemble approach, particularly the LightGBM model, demonstrated superior performance with an accuracy of 91.86% and the fastest training time. Visualization of the relationships between different Behavioral Patterns and heart disease provided clear insights into the risk factors. This study underscores the potential of leveraging ensemble learning models to enhance predictive accuracy and offers valuable insights for targeted health interventions.

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

Optimizing Heart Disease Prediction with Ensemble Learning and Behavioral Patterns

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Channabasappa Muttal,
  • Padmshree Desai,
  • Prathit Kulkarni

摘要

Heart disease remains a leading cause of morbidity and mortality worldwide, driven by various Behavioral Patterns such as age, smoking habits, and exercise frequency. This study explores the predictive power of these Behavioral Patterns in forecasting heart disease through ensemble learning techniques. Using a comprehensive dataset, we applied multiple machine learning models, including Random Forest, Extra Trees, LightGBM, CatBoost, and XGBoost, to build a robust predictive model. Our analysis revealed significant correlations between lifestyle factors and heart disease, with age, smoking, and exercise being strong predictors. The ensemble approach, particularly the LightGBM model, demonstrated superior performance with an accuracy of 91.86% and the fastest training time. Visualization of the relationships between different Behavioral Patterns and heart disease provided clear insights into the risk factors. This study underscores the potential of leveraging ensemble learning models to enhance predictive accuracy and offers valuable insights for targeted health interventions.