Scholarlink

Heart disease is a global threat due to which a million of lives are lost each year. Heart attack and strokes remains the prominent reasons of premature deaths. This happens due to unhealthy lifestyle, no physical activities, stress and many reasons due to which increased blood pressure, raised cholesterol levels and many more medical problems occur and lead to this heart disease problems. Early detection of this disease will play a crucial role in decreasing the death rate of the deaths caused by heart disease each year. Developing a system based on machine learning model that would take some medical records as input and provide the output as the risk of getting heart disease which would really help the medical field to analyse heart disease in a different way. In this paper data is collected from authenticate sources and the data is pre-processed to make it ready for giving it to a machine learning model to train the model and test the model. This paper reveals that Random Forest comes out to be the best model with the highest accuracy of 96.35%, Recall of 99.87%, Precision of 93.31% and F1score of 96.48% among the other evaluated models that could revolutionize the preventive healthcare practices and improve patient outcomes in management of heart diseases.

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

Early Risk Prediction of Heart Disease in Patients Using Classification Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Bali Gupta,
  • Akshay Jadhav,
  • Vishal Gautam,
  • Mudit Shrivastava

摘要

Heart disease is a global threat due to which a million of lives are lost each year. Heart attack and strokes remains the prominent reasons of premature deaths. This happens due to unhealthy lifestyle, no physical activities, stress and many reasons due to which increased blood pressure, raised cholesterol levels and many more medical problems occur and lead to this heart disease problems. Early detection of this disease will play a crucial role in decreasing the death rate of the deaths caused by heart disease each year. Developing a system based on machine learning model that would take some medical records as input and provide the output as the risk of getting heart disease which would really help the medical field to analyse heart disease in a different way. In this paper data is collected from authenticate sources and the data is pre-processed to make it ready for giving it to a machine learning model to train the model and test the model. This paper reveals that Random Forest comes out to be the best model with the highest accuracy of 96.35%, Recall of 99.87%, Precision of 93.31% and F1score of 96.48% among the other evaluated models that could revolutionize the preventive healthcare practices and improve patient outcomes in management of heart diseases.