Scholarlink

This research evaluates the effectiveness of various machine learning algorithms in predicting and categorizing liver cirrhosis, a severe liver disease characterized by extensive scarring due to chronic infections or prolonged alcohol use. The study focuses on six algorithms: Logistic Regression (parametric), and CatBoost, CART, Gradient Boost, KNN, and Random Forest (nonparametric). Random Forest achieved the highest accuracy (78%) and F1 score (84%). Gradient Boost and CatBoost also performed well, with accuracies of 77% and F1 scores of 83% and 82%, respectively. Logistic Regression and KNN performed poorly, with accuracies of 46% and 39%. The results emphasize Random Forest’s ability to handle complex medical data and accurately predict liver cirrhosis progression. This research underscores the importance of selecting appropriate machine learning models to improve diagnostic accuracy and patient outcomes in liver disease.

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

Optimizing Liver Cirrhosis Stage Prediction Using Random Forest Classifier

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Perugu Ridhi,
  • C. Kishor Kumar Reddy,
  • Srinath Doss,
  • Kari Lippert

摘要

This research evaluates the effectiveness of various machine learning algorithms in predicting and categorizing liver cirrhosis, a severe liver disease characterized by extensive scarring due to chronic infections or prolonged alcohol use. The study focuses on six algorithms: Logistic Regression (parametric), and CatBoost, CART, Gradient Boost, KNN, and Random Forest (nonparametric). Random Forest achieved the highest accuracy (78%) and F1 score (84%). Gradient Boost and CatBoost also performed well, with accuracies of 77% and F1 scores of 83% and 82%, respectively. Logistic Regression and KNN performed poorly, with accuracies of 46% and 39%. The results emphasize Random Forest’s ability to handle complex medical data and accurately predict liver cirrhosis progression. This research underscores the importance of selecting appropriate machine learning models to improve diagnostic accuracy and patient outcomes in liver disease.