Scholarlink

Cardiovascular disease (CVD) is the leading cause of morbidity and mortality worldwide. Accurate and premature risk prediction tools are essential for effective prevention and treatment. Many studies have proposed CVD risk prediction models, but most suffer from limited accuracy and a lack of explanation. This paper proposes CVD-ResNet, a residual neural network designed to classify CVD risk. The CVD-ResNet model incorporates residual blocks to improve learning efficiency and predictive performance. Our model achieved 99% accuracy, precision, recall, and F1-score. Furthermore, we employed LIME (Local Interpretable Model-agnostic Explanations) to enhance the interpretability of the model’s predictions.

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

FCVD-ResNet: An Interpretable Deep Residual Network for Cardiovascular Disease Risk Prediction

  • 章节

  • 发表日期：

    2026年

查看全文
  • Rezuana Haque,
  • Fahmida Afroja Hoque Barsha

摘要

Cardiovascular disease (CVD) is the leading cause of morbidity and mortality worldwide. Accurate and premature risk prediction tools are essential for effective prevention and treatment. Many studies have proposed CVD risk prediction models, but most suffer from limited accuracy and a lack of explanation. This paper proposes CVD-ResNet, a residual neural network designed to classify CVD risk. The CVD-ResNet model incorporates residual blocks to improve learning efficiency and predictive performance. Our model achieved 99% accuracy, precision, recall, and F1-score. Furthermore, we employed LIME (Local Interpretable Model-agnostic Explanations) to enhance the interpretability of the model’s predictions.