Cover
Volume 7, Special Issue 4 (2026)

Published: August 25, 2026

Pages: 210-220

Research Article

Modeling and classification of breast cancer using machine learning techniques: A comparative analysis of Bayesian Networks and XGBoost

Suzan S. Haydar 1 Farhad A. Ahmed 1
1Department of Statistics and Informatics, College of Administration and Economics, Sulamani University, Sulamani, Iraq
History
  • Received: June 13, 2026
  • Available Online: August 25, 2026
DOI

https://doi.org/10.56967/ejfb2026931

Abstract

Breast cancer is one of the most prevalent and life-threatening diseases worldwide, making early and accurate diagnosis essential for improving patient outcomes. This study aims to evaluate the performance of two machine learning models, Extreme Gradient Boosting (XGBoost) and Gaussian Naive Bayes, for breast cancer classification using the Breast Cancer Wisconsin Diagnostic dataset. A comparative analysis was conducted based on several performance metrics, including Accuracy, Precision, Recall, F1-score, Specificity, Receiver Operating Characteristic (ROC) curve, Area Under the Curve (AUC), Balanced Accuracy, and Confusion Matrix. In addition, feature importance analysis was performed to identify the most influential variables contributing to the classification process. The experimental results demonstrated that both models achieved high classification performance. However, the Gaussian Naive Bayes model showed slightly superior performance, achieving an Accuracy of 96.5% and an AUC of 0.997, compared with 96.0% and 0.993, respectively, for the XGBoost model. Furthermore, the analysis revealed that features related to tumor morphology, particularly concave points mean, perimeter worst, and radius worst, were among the most influential predictors of breast cancer classification. The findings indicate that both machine learning models provide reliable and effective tools for supporting early breast cancer diagnosis, with Gaussian Naive Bayes demonstrating a slight advantage for the dataset used in this study. These results highlight the potential of machine learning techniques to enhance diagnostic accuracy and support clinical decision-making.

Keywords

References

  1. Wang, Y., Zhang, H., & Liu, J. (2024). Breast cancer classification using gradient boosting-based machine learning models. Journal of Medical Artificial Intelligence, 12(3), 145–158.
  2. Li, X., Chen, M., & Zhao, L. (2024). Probabilistic graphical models for clinical decision-making: A Bayesian network approach in breast cancer analysis. Computational Biology and Medicine, 156, 106–118.
  3. Khan, M. A., Ahmed, S., & Rehman, A. (2025). Predictive modeling of breast cancer using XGBoost and genomic data analysis. IEEE Access, 13, 22145–22160.
  4. Alvarez, R., Gomez, P., & Martinez, J. (2024). Comparative analysis of machine learning algorithms for breast cancer diagnosis. Expert Systems with Applications, 238, 122–134.
  5. Chen, Y., Wang, L., & Huang, X. (2025). Hybrid deep learning and Bayesian models for interpretable medical diagnosis systems. Artificial Intelligence in Medicine, 148, 102–115.
  6. Wolberg, W. H., Street, W. N., & Mangasarian, O. L. (1995). Breast cancer Wisconsin (diagnostic) dataset. UCI Machine Learning Repository.
  7. Patel, R., Singh, K., & Mehta, D. (2024). Explainable AI approaches for breast cancer classification using ensemble learning methods. Biomedical Signal Processing and Control, 89, 105612.
  8. Zhou, Q., Li, H., & Sun, Y. (2024). Machine learning-based diagnostic systems for breast cancer prediction: A comparative study. Computers in Biology and Medicine, 170, 108214.
  9. Rahman, F., & Kim, J. (2025). Integrating Bayesian inference with machine learning for robust medical diagnosis. IEEE Transactions on Computational Biology and Bioinformatics, 22(1), 88–101.
  10. Garcia, M., Lopez, A., & Hernandez, S. (2024). Feature selection and importance analysis in breast cancer datasets using tree-based models. Knowledge-Based Systems, 285, 111345.
  11. Singh, P., & Verma, R. (2025). Comparative performance analysis of XGBoost and machine learning classifiers in healthcare applications. Expert Systems with Applications, 250, 123456.
  12. Hassan, M., Ali, N., & Khan, S. (2024). Interpretable machine learning for cancer diagnosis using clinical and imaging data. Artificial Intelligence in Medicine, 145, 102789.
  13. Wang, H., Liu, Z., & Zhang, T. (2025). Advanced ensemble learning techniques for medical image-based breast cancer detection. IEEE Access, 13, 98765–98780.
  14. El-Sayed, A., & Mahmoud, H. (2024). Bayesian approaches for uncertainty modeling in medical classification problems. Journal of Biomedical Informatics, 150, 104512.
  15. Kim, D., Park, J., & Lee, S. (2025). Performance evaluation of machine learning models for cancer diagnosis using ROC-AUC analysis. Computational and Structural Biotechnology Journal, 23, 456–468.
  16. Brown, T., Williams, J., & Davis, R. (2024). Machine learning interpretability in healthcare: A focus on feature importance methods. Health Informatics Journal, 30(2), 789–805.