Harnessing the hybrid machine learning methods for stroke risk classification.

Journal: Computer methods in biomechanics and biomedical engineering
Published Date: May 19, 2025

Abstract

Stroke is a leading global cause of death, with 80% of cases considered preventable through early detection and awareness. This study employs artificial intelligence (AI) and machine learning (ML) to predict stroke risk using a dataset containing 5,110 records and key risk factors such as age, hypertension, and heart disease. Multiple models were evaluated, including Gradient Boosting, Hist Gradient Boosting, AdaBoost, and Decision Trees. A hybrid model integrating Hist Gradient Boosting with optimizer algorithms achieved superior performance, with accuracy, precision, recall, and F1-score all exceeding 0.985, highlighting its potential for effective stroke prediction.

Authors

  • Dongxian Yu
    College of Modern Information Technology, Henan Polytechnic, Zhengzhou, Henan, China.
  • Mingjie Wang
    Shanghai Key Laboratory of Bioactive Small Molecules, School of Basic Medical Science, Fudan University, Shanghai, 200032, People's Republic of China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals