Scholarlink

In the present day, individuals often find themselves engrossed in their daily routines, focusing on work and various activities, while inadvertently neglecting their well-being. As a consequence of this demanding lifestyle and lack of attention to health, there is a rapid increase in the number of people falling ill. Furthermore, a substantial portion of the population is grappling with health issues, particularly heart disease. Cardiovascular diseases, claiming 17.9 million lives annually, rank as the foremost cause of death globally, as reported by the WHO. Hence early stage detection of cardiac disease through early-stage signs is a major need in today's world. A system that can aid in the early diagnosis of cardiac disease is suggested. This method aims to develop a ML model to detect cardiac disease in its early stages. The different ML algorithms such as RF, KNN, LR, DT and SVM are used to attain the maximum accuracy. UCI repositories dataset was used for performing the experiments. In this study the accuracy of 80.33% is obtained with SVM.

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 Model Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Bipin Kumar Rai,
  • Aparna Jha,
  • Shreyal Srivastava,
  • Aman Bind

摘要

In the present day, individuals often find themselves engrossed in their daily routines, focusing on work and various activities, while inadvertently neglecting their well-being. As a consequence of this demanding lifestyle and lack of attention to health, there is a rapid increase in the number of people falling ill. Furthermore, a substantial portion of the population is grappling with health issues, particularly heart disease. Cardiovascular diseases, claiming 17.9 million lives annually, rank as the foremost cause of death globally, as reported by the WHO. Hence early stage detection of cardiac disease through early-stage signs is a major need in today's world. A system that can aid in the early diagnosis of cardiac disease is suggested. This method aims to develop a ML model to detect cardiac disease in its early stages. The different ML algorithms such as RF, KNN, LR, DT and SVM are used to attain the maximum accuracy. UCI repositories dataset was used for performing the experiments. In this study the accuracy of 80.33% is obtained with SVM.