Scholarlink

With heart disease remaining one of the leading causes of death globally, there is a growing need for interpretable and efficient tools for early prediction. This paper presents a logistic regression framework using the UCI Heart Disease dataset, emphasizing interpretable feature scaling and clinically meaningful risk stratification. Features are normalized to a [1–5] range, producing a continuous risk factor score further stratified into five categories. The model achieves an accuracy of 80.11%, precision of 78.30%, recall of 88.61%, F1-score of 83.13%, and AUC of 0.7910. These results highlight the model’s balance between performance and interpretability, making it suitable for integration into electronic health record (EHR) systems and mobile triage tools.

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 Attack Risk Prediction Using Logistic Regression and Risk Factor Modelling

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Aastha Bhimani,
  • Jiju Gillariose,
  • R. Sivakumar

摘要

With heart disease remaining one of the leading causes of death globally, there is a growing need for interpretable and efficient tools for early prediction. This paper presents a logistic regression framework using the UCI Heart Disease dataset, emphasizing interpretable feature scaling and clinically meaningful risk stratification. Features are normalized to a [1–5] range, producing a continuous risk factor score further stratified into five categories. The model achieves an accuracy of 80.11%, precision of 78.30%, recall of 88.61%, F1-score of 83.13%, and AUC of 0.7910. These results highlight the model’s balance between performance and interpretability, making it suitable for integration into electronic health record (EHR) systems and mobile triage tools.