Scholarlink

<p>Breast cancer remains a significant health concern worldwide, necessitating early detection for optimal treatment outcomes. This paper explores the efficacy of machine learning algorithms for breast cancer detection, utilizing the Wisconsin Diagnostic Breast Cancer dataset (WDBC). Traditional algorithms such as Logistic Regression (LR), Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machines (SVM) are examined, alongside innovative techniques to mitigate class imbalance. Specifically, we introduce a novel approach by integrating synthetic data generation methods, notably CTGAN, to address class imbalance. Our comparative analysis reveals that CTGAN, combined with SVM, achieves an unprecedented accuracy rates of 99.3% on the balanced dataset. This groundbreaking result underscores the potential of synthetic data generation techniques in enhancing machine learning models for breast cancer detection, marking a significant advancement in the realm of diagnostic accuracy in clinical settings.</p>

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

Beyond imbalance: advancing breast cancer diagnosis with synthetic data and ML modeling

  • 期刊论文

  • 发表日期：

    2025年5月21日

查看全文
  • Mohammad Reza Abbaszadeh Bavil Soflaei,
  • Karim Samadzamini,
  • Arash Salehpour

摘要

Breast cancer remains a significant health concern worldwide, necessitating early detection for optimal treatment outcomes. This paper explores the efficacy of machine learning algorithms for breast cancer detection, utilizing the Wisconsin Diagnostic Breast Cancer dataset (WDBC). Traditional algorithms such as Logistic Regression (LR), Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machines (SVM) are examined, alongside innovative techniques to mitigate class imbalance. Specifically, we introduce a novel approach by integrating synthetic data generation methods, notably CTGAN, to address class imbalance. Our comparative analysis reveals that CTGAN, combined with SVM, achieves an unprecedented accuracy rates of 99.3% on the balanced dataset. This groundbreaking result underscores the potential of synthetic data generation techniques in enhancing machine learning models for breast cancer detection, marking a significant advancement in the realm of diagnostic accuracy in clinical settings.