Breast cancer remains a major health concern in Morocco and worldwide, with mortality rates steadily increasing, particularly among women. It is the leading cause of death in this population, underscoring the urgent need to improve diagnostic and predictive tools. Developing tailored solutions is essential to enhance early detection and treatment. Advancing medical research in this field could contribute to better patient care. A multidisciplinary approach is required to address this public health challenge. In this context, we conducted a comprehensive analysis of a dataset consisting of 509 patients from the Hassan II Regional Oncology Center in Agadir. The main objective of this study was to predict the presence or absence of metastases in breast cancer patients. Notably, 73.47% of the cases in our dataset were metastatic. We applied 11 different machine learning classification algorithms, with AdaBoost demonstrating the best performance, achieving an AUC of 78%, closely followed by XGBoost with an AUC of 75%. These findings highlight the potential of machine learning to improve early detection and prognosis in breast cancer.