Scholarlink

"Cardiovascular diseases (CVDs)" are one of the most common causes of death around the world, so it is important to get correct and quick diagnoses to lower the risks. This study uses advanced "Deep learning (DL) and machine learning (ML)" methods to make diagnoses more accurate. Traditional ML methods rely largely on manual feature engineering, but DL methods are great at automatically extracting features, which makes them perfect for working with complicated datasets. This paper uses the heart disease Dataset to deal with class imbalance through "Adaptive synthetic (Adasyn)" Oversampling and suggests a new ensemble-based detection approach. Overall tests show that "the voting Classifier is better than any one model, with an accuracy of 91.7%, a precision of 92.0%, a recall of 91.7%, and an F1-score of 91.8%". These results show that ensemble methods work well with a wide range of data types and achieve excellent diagnostic accuracy. This shows that they could help improve CVD diagnoses.

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

Heart Disease Prediction Using Novel Ensemble and Blending Based Cardiovascular Disease Detection Networks EnsCVDD-Net and BlCVDD-Net

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ravi Teja Kunchala,
  • G. Venkateswarlu,
  • Devendra Sai Tammana,
  • Vivek Machaboina,
  • Vinod Lunavath,
  • Tiruvayipati Praneeth

摘要

"Cardiovascular diseases (CVDs)" are one of the most common causes of death around the world, so it is important to get correct and quick diagnoses to lower the risks. This study uses advanced "Deep learning (DL) and machine learning (ML)" methods to make diagnoses more accurate. Traditional ML methods rely largely on manual feature engineering, but DL methods are great at automatically extracting features, which makes them perfect for working with complicated datasets. This paper uses the heart disease Dataset to deal with class imbalance through "Adaptive synthetic (Adasyn)" Oversampling and suggests a new ensemble-based detection approach. Overall tests show that "the voting Classifier is better than any one model, with an accuracy of 91.7%, a precision of 92.0%, a recall of 91.7%, and an F1-score of 91.8%". These results show that ensemble methods work well with a wide range of data types and achieve excellent diagnostic accuracy. This shows that they could help improve CVD diagnoses.