Abstract

Breast cancer is one of the leading causes of mortality among women worldwide, and early detection plays a crucial role in improving survival rates. In recent years, machine learning techniques have shown significant potential in assisting medical diagnosis by providing accurate and efficient prediction models. This study focuses on the optimization of breast cancer prediction and diagnosis using a hybrid machine learning approach that combines K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms. The proposed methodology involves preprocessing the dataset to handle missing values, normalize features, and select the most relevant attributes for classification. Initially, individual models based on KNN and SVM are developed and evaluated in terms of accuracy, precision, recall, and F1-score. While KNN is effective in capturing local data patterns, SVM provides robust classification by maximizing the margin between different classes. However, each method has its own limitations when used independently. To overcome these limitations, a hybrid KNN+SVM model is proposed, which integrates the strengths of both algorithms. The hybrid approach enhances classification performance by improving decision boundaries and reducing misclassification rates. The optimized model is expected to achieve higher accuracy and better generalization compared to individual classifiers. The experimental results demonstrate that the hybrid model outperforms traditional methods in predicting breast cancer with improved reliability and efficiency. This approach can assist healthcare professionals in early diagnosis and decision-making, ultimately contributing to better patient outcomes and reduced mortality rates.

References

• C. Bista, A. M, S. Slimanzay, M. S. Sheikh and P. Srinivasa Rao, "Breast Cancer Prediction System Utilizing Machine Learning Algorithms," 2024 IEEE AITU: Digital Generation, Astana, Kazakhstan, 2024, pp. 80-84.
• T. Matsuda, M. Matsuda, H. Haque et al., “Diagnostic accuracy of a machine learning model using radiomics features from breast synthetic MRI,” BMC Med. Imaging, vol. 25, art. no. 399, pp. 1–11, Sept. 2025.
• J. Zhang, Q. Wu, P. Lei et al., “Diagnostic accuracy of machine learning-based magnetic resonance imaging models in breast cancer classification: A systematic review and meta-analysis,” World J. Surg. Onc., vol. 23, art. no. 231, pp. 1–13, Jun. 2025.
• C. F. Lee, J. Lin, Y.-L. Huang et al., “Deep learning-based breast MRI for predicting axillary lymph node metastasis: A systematic review and meta-analysis,” Cancer Imaging, vol. 25, art. no. 44, pp. 1–15, Mar. 2025.
• R. Liang, F. Li, J. Yao et al., “Predictive value of MRI-based deep learning model for lymphovascular invasion status in node-negative invasive breast cancer,” Sci. Rep., vol. 14, art. no. 16204, pp. 1–12, Jul. 2024.
• G. Houssami, M. Turner and R. Morrow, “Machine Learning for Breast MRI: Current Applications and Future Directions,” European Radiology, vol. 31, no. 6, pp. 3752–3764, 2021.
• Y. Zheng, B. Liu and S. Chen, “Comparative Study of Machine Learning Techniques for Breast Cancer Classification Using MRI Images,” Biomedical Signal Processing and Control, vol. 68, Article ID 102645, 2021.
• X. Zhang, Y. Chen and Z. Wang, “Breast Cancer Diagnosis Using Transfer Learning with Pretrained CNN Models on MRI,” Computers in Biology and Medicine, vol. 115, Article ID 103498, 2019.
• Khurma RA, Aljarah I, Sharieh A, Elaziz MA, Damaševičius R, Krilavičius T. A review of the modifcation strategies of nature inspired algorithms for feature selection problem. Mathematics. 2022;10(3):1–45.
• Jain AK. Data clustering: 50 years beyond K-means. Pattern Recogn Lett. 2010;31(8):651–66.
• Murtagh F, Contreras P. Algorithms for hierarchical clustering: an overview. Wiley Interdiscip Rev Data Min Knowl Discov. 2012;2(1):86–97.
• Dabhi DP, Patel MR, Dipak MRP, Dabhi P. Extensive survey on hierarchical clustering methods in data mining. Int Res J Eng Technol, 2016; 03(11):659–665.
• Kriegel HP, Kröger P, Sander J, Zimek A. Density-based clustering. Wiley Interdiscip Rev Data Min Knowl Discov. 2011;1(3):231–40.
• Moulavi D, Jaskowiak PA, Campello RJGB, Zimek A, Sander J. Density-based clustering validation. SIAM Int Conf Data Min 2014, SDM 2014. 2014; 2(i):839–847.
• Aziz R, Verma CK, Srivastava N. A novel approach for dimension reduction of microarray. Comput Biol Chem. 2017; 71:161–169.