Scholarlink

Breast cancer, a condition characterized by the uncontrolled growth of damaged cells in the tissues of the breast is a major concern to societies in the world today. For this study, we selected Wisconsin Breast Cancer dataset analyzing patterns and risk factors using Decision Tree, Random Forest, AdaBoost, XGBoost and Gradient Boosting techniques. Through examination of the measures such as size, shape, margin and cellular attributes of tumors, it becomes the focal point to enhance the diagnostic accuracy, early detection and subsequent treatment. As suggested in this approach, it offers fundamental instruments to help clinical personnel in expanding diagnoses of illnesses and determinations of the most pertinent remedy plans. Through these supervised machine learning methods, it is aimed to increase the understanding of breast cancer, and therefore, contribute to the extension of diagnostic procedures and therapeutic approaches in clinical practice. However, the XGBoost Algorithm had a better accuracy of 93.20%. It furthers clinical practice by offering reliable prediction models to aid in predicting breast cancer diagnosis and the knowledge gathered on the 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

Breast Cancer Diagnosis Using Machine Learning and Knowledge Discovery in Data

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mayank Arora,
  • Poonam Saini,
  • Kanu Goel

摘要

Breast cancer, a condition characterized by the uncontrolled growth of damaged cells in the tissues of the breast is a major concern to societies in the world today. For this study, we selected Wisconsin Breast Cancer dataset analyzing patterns and risk factors using Decision Tree, Random Forest, AdaBoost, XGBoost and Gradient Boosting techniques. Through examination of the measures such as size, shape, margin and cellular attributes of tumors, it becomes the focal point to enhance the diagnostic accuracy, early detection and subsequent treatment. As suggested in this approach, it offers fundamental instruments to help clinical personnel in expanding diagnoses of illnesses and determinations of the most pertinent remedy plans. Through these supervised machine learning methods, it is aimed to increase the understanding of breast cancer, and therefore, contribute to the extension of diagnostic procedures and therapeutic approaches in clinical practice. However, the XGBoost Algorithm had a better accuracy of 93.20%. It furthers clinical practice by offering reliable prediction models to aid in predicting breast cancer diagnosis and the knowledge gathered on the disease.