Scholarlink

With two million fatalities each year, liver disease accounts for approximately 4% of all deaths worldwide. Early diagnosis of liver disease is essential for implementing effective control measures and saving lives. The advancement of machine learning has made it possible to predict illnesses and prevent potentially fatal outcomes. Various statistical and machine learning methods have been used to create several prediction models for liver disease. These techniques are applied to datasets to extract valuable insights or build models. In this study, we utilized machine learning methods on the ILPD (Indian Liver Patient Dataset) to develop an intelligent model. Based on experimental results, our proposed approach outperformed seven other supervised machine learning algorithms, achieving the highest accuracy rate of 98.00%.

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

A Novel Approach to Liver Disease Diagnosis Classification Using Non-smooth SVM

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Z. Khoudi,
  • N. Hafidi,
  • M. Johri,
  • M. Nachaoui,
  • S. Lyaqini

摘要

With two million fatalities each year, liver disease accounts for approximately 4% of all deaths worldwide. Early diagnosis of liver disease is essential for implementing effective control measures and saving lives. The advancement of machine learning has made it possible to predict illnesses and prevent potentially fatal outcomes. Various statistical and machine learning methods have been used to create several prediction models for liver disease. These techniques are applied to datasets to extract valuable insights or build models. In this study, we utilized machine learning methods on the ILPD (Indian Liver Patient Dataset) to develop an intelligent model. Based on experimental results, our proposed approach outperformed seven other supervised machine learning algorithms, achieving the highest accuracy rate of 98.00%.