Scholarlink

This study evaluates the performance of three supervised machine learning algorithms—Naïve Bayes, Support Vector Machines (SVM), and Artificial Neural Networks (ANN)—in classifying breast tumors as benign or malignant using features extracted from a clinical dataset. The objective was to determine each model’s effectiveness in aiding early breast cancer diagnosis. Among the models, the ANN achieved the highest classification accuracy at 97.72%, demonstrating exceptional capability in differentiating malignant from benign tumors. The SVM model also produced robust results, with an accuracy of 93.68%, making it a strong alternative. While the Naïve Bayes model reported the lowest accuracy at 92.80%, it outperformed the others in computational efficiency, highlighting its suitability for scenarios with limited processing resources. These findings underscore the potential of machine learning, particularly neural networks, as a valuable tool for improving the speed and precision of breast cancer detection, potentially supporting clinicians in critical diagnostic decisions. Future research may explore integrating multiple models or hybrid approaches to further enhance predictive performance in medical contexts.

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

Predicting Breast Tumor Malignancy Using Machine Learning Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Luisa Itzel Olivas Evangelista,
  • Sofia Paulina Medina Domínguez,
  • Karla Georgina Espinoza Chávez,
  • Carlos Eduardo Cañedo Figueroa

摘要

This study evaluates the performance of three supervised machine learning algorithms—Naïve Bayes, Support Vector Machines (SVM), and Artificial Neural Networks (ANN)—in classifying breast tumors as benign or malignant using features extracted from a clinical dataset. The objective was to determine each model’s effectiveness in aiding early breast cancer diagnosis. Among the models, the ANN achieved the highest classification accuracy at 97.72%, demonstrating exceptional capability in differentiating malignant from benign tumors. The SVM model also produced robust results, with an accuracy of 93.68%, making it a strong alternative. While the Naïve Bayes model reported the lowest accuracy at 92.80%, it outperformed the others in computational efficiency, highlighting its suitability for scenarios with limited processing resources. These findings underscore the potential of machine learning, particularly neural networks, as a valuable tool for improving the speed and precision of breast cancer detection, potentially supporting clinicians in critical diagnostic decisions. Future research may explore integrating multiple models or hybrid approaches to further enhance predictive performance in medical contexts.