Breast cancer is one of the most common types of cancer among women. This disease poses serious clinical challenges due to its variable response to treatment and biological heterogeneity. Therefore, conventional therapies fail to complement the characteristics of specific tumors, limiting the effectiveness of treatment even in personalized therapies. In recent years, powerful tools such as artificial intelligence(AI), have emerged to advance personalized medicine, especially in the field of breast cancer, with the help of which complex biomedical data can be better analyzed.
In this article, we aim to provide a comprehensive review of the impact of AI on early detection, prognosis and recurrence assessment, response prediction, biomarker discovery, and clinical decision-making in breast cancer. We will also explore how AI-based imaging analysis can help improve diagnostic accuracy, while integrated multi-omics models can enhance treatment decision-making and risk stratification. Emerging approaches such as explainable AI, radiogenomics, and AI-based multi-omics integration are also highlighted as key drivers in this field.
Despite encouraging results, significant challenges remain, including data heterogeneity, limited external and prospective validation, algorithmic bias, interpretability concerns, and ethical and regulatory barriers. Addressing these limitations through standardized data protocols, transparent and explainable models, and multi-center validation studies is essential for safe and equitable implementation. Overall, AI holds substantial potential to transform breast cancer management toward a more predictive, preventive, and patient-centered paradigm, provided that technological innovation is aligned with robust clinical validation and interdisciplinary collaboration.