Scholarlink

In this study, we used a machine learning model based on ensemble learning algorithms to predict and identify stroke-causing factors using a dataset from Hospital 175 in Ho Chi Minh City, Vietnam. We statistically analyzed the data characteristics and correlated parameters affecting strokes. The training results revealed that the Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), and eXtreme Gradient Boosting (XGBoost) models demonstrated outstanding performance, achieving accuracies of 96.59%, 96.92%, and 96.57%, respectively. Additionally, “SHapley Additive exPlanations (SHAP)” were used to quantify each feature's contribution to predictions, helping identify stroke causes. These results can support integrating artificial intelligence into stroke diagnosis and treatment, paving the way for innovative healthcare solutions.

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

Applying Ensemble Machine Learning Model to Explain the Causes of Stroke

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Van Lam Ho,
  • Loan Nguyen Thi Phuc,
  • Ngan Le Thi Thu,
  • V. M. Duy Nguyen,
  • Thao Le Thi Phuong

摘要

In this study, we used a machine learning model based on ensemble learning algorithms to predict and identify stroke-causing factors using a dataset from Hospital 175 in Ho Chi Minh City, Vietnam. We statistically analyzed the data characteristics and correlated parameters affecting strokes. The training results revealed that the Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), and eXtreme Gradient Boosting (XGBoost) models demonstrated outstanding performance, achieving accuracies of 96.59%, 96.92%, and 96.57%, respectively. Additionally, “SHapley Additive exPlanations (SHAP)” were used to quantify each feature's contribution to predictions, helping identify stroke causes. These results can support integrating artificial intelligence into stroke diagnosis and treatment, paving the way for innovative healthcare solutions.