Scholarlink

This research effort will examine the use of machine learning algorithms for breast cancer prediction using large datasets obtained from TCGA and METABRIC. The study compared seven algorithms, including AdaBoost and Logistic Regression, and concluded that AdaBoost scored more successfully with 66.5% accuracy and 65% AUC. With an AUC of 64%, accuracy of the logistic regression was 65.5%. The release of gene mutation profiles revealed the presence of key genes: PIK3CA, CDH1, GATA3, MAP3K1, SYNE1, USH2A, and PTEN. Through discovering the above gene markers, the clinical utility of the model predictions has been improved. In essence, this work illustrates the significance of pooling genomic data to provide better and more customized diagnostics; it additionally demonstrates how machine learning may be used to predict cancer. .

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

Breast Cancer Prediction Using Genetic Expression and Mutation Profiling

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Suresh Limkar,
  • Aditya Patil,
  • Aditya Sanas,
  • Ajinkya Sanas,
  • Aditya Shirke

摘要

This research effort will examine the use of machine learning algorithms for breast cancer prediction using large datasets obtained from TCGA and METABRIC. The study compared seven algorithms, including AdaBoost and Logistic Regression, and concluded that AdaBoost scored more successfully with 66.5% accuracy and 65% AUC. With an AUC of 64%, accuracy of the logistic regression was 65.5%. The release of gene mutation profiles revealed the presence of key genes: PIK3CA, CDH1, GATA3, MAP3K1, SYNE1, USH2A, and PTEN. Through discovering the above gene markers, the clinical utility of the model predictions has been improved. In essence, this work illustrates the significance of pooling genomic data to provide better and more customized diagnostics; it additionally demonstrates how machine learning may be used to predict cancer. .