Comparative Evaluation of Machine Learning Techniques for Breast Cancer Prediction and Clinical Applications

Recent advances in machine learning (ML) and digital technologies have significantly transformed breast cancer detection. These innovations enhance diagnostic efficiency, accuracy, and accessibility. A variety of ML algorithms—such as Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (K-NN), Logistic Regression (LR), and Decision Tree (DT) are commonly applied to improve both early prediction and recurrence monitoring of breast cancer. By integrating data from diverse diagnostic tools, including mammography and ultrasound, ML-based systems have demonstrated improved precision and robustness, even in cases complicated by dense breast tissue or tumor heterogeneity. Artificial intelligence–driven pre-screening approaches further assist clinicians by reducing diagnostic workload and supporting earlier identification, particularly in settings with limited resources. Additionally, ultrasound-based deep learning models provide a noninvasive and widely accessible complementary technique, contributing to broader breast cancer screening practices. Emerging strategies like federated learning promote multi-institutional data sharing without compromising patient privacy, which enhances the generalizability of classifiers, for instance, Logistic Regression models achieving up to 95% accuracy. Overall, the integration of ML in breast cancer diagnosis offers not only more individualized treatment plans and improved patient outcomes but also meaningful cost reductions for healthcare systems.