Scholarlink

The heart is widely regarded as the most vital organ within the human body. Cardiovascular diseases are prevalent in contemporary society; hence it is imperative to anticipate and forecast these conditions in advance. The accurate prognosis and prediction of coronary heart diseases necessitate a high level of precision and efficiency, since even a minor error might result in fatality for the individual. In order to address this condition, it is imperative to develop a model that possesses the capability to forecast and generate awareness pertaining to certain illnesses. Determining the disease manually based solely on indications and risk factors presents a significant challenge. However, machine learning techniques can address this issue. This work implements and evaluates the efficiency of machine learning algorithms in predicting cardiovascular diseases. The algorithms used in this work are K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) and the data set used is the UCI repository data. The experimental results prove that the KNN and SVM models exhibit the highest levels of suitability, as evidenced by their respective accuracies of 88% and 84% respectively.

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

Feature Based Machine Learning Models for Cardiovascular Disease Diagnosis: An Experimental Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Alok Kumar Agrawal,
  • Amit Vajpayee,
  • Merry Saxena,
  • Pradeepta Kumar Sarangi,
  • Karan Bajaj,
  • Ashok Kumar Sahoo

摘要

The heart is widely regarded as the most vital organ within the human body. Cardiovascular diseases are prevalent in contemporary society; hence it is imperative to anticipate and forecast these conditions in advance. The accurate prognosis and prediction of coronary heart diseases necessitate a high level of precision and efficiency, since even a minor error might result in fatality for the individual. In order to address this condition, it is imperative to develop a model that possesses the capability to forecast and generate awareness pertaining to certain illnesses. Determining the disease manually based solely on indications and risk factors presents a significant challenge. However, machine learning techniques can address this issue. This work implements and evaluates the efficiency of machine learning algorithms in predicting cardiovascular diseases. The algorithms used in this work are K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) and the data set used is the UCI repository data. The experimental results prove that the KNN and SVM models exhibit the highest levels of suitability, as evidenced by their respective accuracies of 88% and 84% respectively.