Scholarlink

Breast cancer is still one of the most common causes of death in women around the world, making it even more important to get a diagnosis as soon as possible. Using the Wisconsin Breast Cancer (Diagnostic) Dataset, this work suggests an Explainable Boosting Classifier (EBC), which is a glass-box machine learning model based on Generalized Additive Models (GAM). It can predict and classify breast tumors as malignant or benign. The EBC not only makes very accurate predictions, but it also makes them clear and easy to understand by modeling the contributions of each feature and each pair of features. The results of the experiment show that EBC is better than classic classifiers such as KNN, Decision Tree, and K-Means, with an accuracy of 96.49%. This shows that the paradigm works well for making fair and fact-based medical decisions.

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 Explainable Boosting Classifier

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Thatikonda Radhika,
  • Sridhar Chintala,
  • A. Soujanya,
  • Payal Bhardwaj

摘要

Breast cancer is still one of the most common causes of death in women around the world, making it even more important to get a diagnosis as soon as possible. Using the Wisconsin Breast Cancer (Diagnostic) Dataset, this work suggests an Explainable Boosting Classifier (EBC), which is a glass-box machine learning model based on Generalized Additive Models (GAM). It can predict and classify breast tumors as malignant or benign. The EBC not only makes very accurate predictions, but it also makes them clear and easy to understand by modeling the contributions of each feature and each pair of features. The results of the experiment show that EBC is better than classic classifiers such as KNN, Decision Tree, and K-Means, with an accuracy of 96.49%. This shows that the paradigm works well for making fair and fact-based medical decisions.