Scholarlink

Liver cancer, particularly hepatocellular carcinoma (HCC), is a major global health concern with constant increase in rates of mortality. Early diagnosis and prognosis are crucial for effective treatment and improved patient outcomes. This study aims to identify biomarkers for liver cancer using gene expression data to facilitate early diagnosis and prognosis of the disease. We conducted a comprehensive analysis of gene expression profiles from HCC patients and healthy individuals to identify differentially expressed genes (DEGs) associated with liver cancer. Machine learning algorithms, Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, Random Forest, and Decision Tree were employed to prioritize potential biomarkers based on their diagnostic and prognostic significance. Our results reveal a panel of DEGs with promising potential as biomarkers for early identification and prognosis of liver cancer. Further validation of these biomarkers in clinical settings could lead to the development of novel diagnosis and prognosis tools for liver cancer, ultimately improving patient care and 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

Identification of Hepatocellular Carcinoma Biomarkers Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Freny Babaria,
  • Yojna Vare,
  • Sakshi Wagh,
  • Gajanan Nagare,
  • Komal Lawand Shinde

摘要

Liver cancer, particularly hepatocellular carcinoma (HCC), is a major global health concern with constant increase in rates of mortality. Early diagnosis and prognosis are crucial for effective treatment and improved patient outcomes. This study aims to identify biomarkers for liver cancer using gene expression data to facilitate early diagnosis and prognosis of the disease. We conducted a comprehensive analysis of gene expression profiles from HCC patients and healthy individuals to identify differentially expressed genes (DEGs) associated with liver cancer. Machine learning algorithms, Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, Random Forest, and Decision Tree were employed to prioritize potential biomarkers based on their diagnostic and prognostic significance. Our results reveal a panel of DEGs with promising potential as biomarkers for early identification and prognosis of liver cancer. Further validation of these biomarkers in clinical settings could lead to the development of novel diagnosis and prognosis tools for liver cancer, ultimately improving patient care and outcomes.