Scholarlink

Heart disease is the top cause of death worldwide, highlighting the need for improved diagnosis and treatment. Expertise variability in healthcare causes inconsistent outcomes; data mining and machine learning (ML) offer automated, accurate predictions to mitigate this. In our study, algorithms such as extreme gradient boosting (XGBoost), decision tree (DT), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM) and logistic regression (LR) were analyzed using demographic, clinical, and physiological data vital for cardiovascular assessment. Data preprocessing techniques, including Z-score normalization, interquartile range (IQR)-based outlier detection, label encoding, and standard scaling, improved data quality. The RF algorithm achieved 87.83% accuracy, demonstrating its effectiveness in disease prediction. This study highlights ML’s potential for early detection and better patient outcomes.

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

Evaluating the Performance of Machine Learning Models in Cardiovascular Disease Classification

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Aarushi Bhogate,
  • Bithika Roy,
  • Neha Memane,
  • Sanika Sawale,
  • Dhanashri Bhosale,
  • Saguna Ingle

摘要

Heart disease is the top cause of death worldwide, highlighting the need for improved diagnosis and treatment. Expertise variability in healthcare causes inconsistent outcomes; data mining and machine learning (ML) offer automated, accurate predictions to mitigate this. In our study, algorithms such as extreme gradient boosting (XGBoost), decision tree (DT), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM) and logistic regression (LR) were analyzed using demographic, clinical, and physiological data vital for cardiovascular assessment. Data preprocessing techniques, including Z-score normalization, interquartile range (IQR)-based outlier detection, label encoding, and standard scaling, improved data quality. The RF algorithm achieved 87.83% accuracy, demonstrating its effectiveness in disease prediction. This study highlights ML’s potential for early detection and better patient outcomes.