Scholarlink

Nowadays, heart illness is highly common if there is substantial damage to the heart’s tissue. With early monitoring, appropriate care, and dietary alterations, many potential hamstring difficulties can be minimized or avoided following a heart attack and other injuries. This paper uses various techniques to assess the possibility of getting a heart attack, such as different supervised machine learning algorithms like logistic regression, naive Bayes, extreme gradient boost (XGB classifier), etc. In order to identify the ideal procedure, this work also offers confusion matrices, feature visualization, and the receiver operating characteristics curve (ROC). In this case, a random forest classifier might be the best choice because of its 98.53% accuracy.

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

Effective Optimized Detection of Cardiovascular Disease by Supervised Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rojalin Mohapatra,
  • Parimal Kumar Giri,
  • Bijaylaxmi Panda

摘要

Nowadays, heart illness is highly common if there is substantial damage to the heart’s tissue. With early monitoring, appropriate care, and dietary alterations, many potential hamstring difficulties can be minimized or avoided following a heart attack and other injuries. This paper uses various techniques to assess the possibility of getting a heart attack, such as different supervised machine learning algorithms like logistic regression, naive Bayes, extreme gradient boost (XGB classifier), etc. In order to identify the ideal procedure, this work also offers confusion matrices, feature visualization, and the receiver operating characteristics curve (ROC). In this case, a random forest classifier might be the best choice because of its 98.53% accuracy.