Scholarlink

Cardiovascular disease stands as a significant contributor to global mortality, representing approximately 30% of all deaths worldwide. Most significant issues in the statistical analysis of healthcare is the prediction for cardiopulmonary illness, or heart failure. Algorithms developed using machine learning (ML) can assist in forecasting cardiovascular diseases, musculoskeletal ailments, and other conditions. When anticipated in advance, such knowledge can assist physicians in tailoring patient diagnosis and treatment. This research presents an innovative approach to discovering factors that enhance the prediction of heart attack and stroke. An effective prediction model is presented, resulting in enhanced performance through superior data preprocessing techniques. For predicting of cardiovascular disease, we can perform better using the “Hybrid Random Forest with Linear Model (HRFLM)” model. In conclusion, experiments were carried out on the Heart Disease Dataset and the Cleveland Dataset, demonstrating the effectiveness of the proposed algorithm.

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

Preprocessing Techniques for Heart Disease Prediction Using Machine Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Haneef Khan,
  • Waseem Ahmed,
  • Malik Zaib Alam,
  • Mohammad Saifuddin,
  • Adeel Ahmad,
  • Sarfaraz Ahmed

摘要

Cardiovascular disease stands as a significant contributor to global mortality, representing approximately 30% of all deaths worldwide. Most significant issues in the statistical analysis of healthcare is the prediction for cardiopulmonary illness, or heart failure. Algorithms developed using machine learning (ML) can assist in forecasting cardiovascular diseases, musculoskeletal ailments, and other conditions. When anticipated in advance, such knowledge can assist physicians in tailoring patient diagnosis and treatment. This research presents an innovative approach to discovering factors that enhance the prediction of heart attack and stroke. An effective prediction model is presented, resulting in enhanced performance through superior data preprocessing techniques. For predicting of cardiovascular disease, we can perform better using the “Hybrid Random Forest with Linear Model (HRFLM)” model. In conclusion, experiments were carried out on the Heart Disease Dataset and the Cleveland Dataset, demonstrating the effectiveness of the proposed algorithm.