Breast cancer diagnosis using machine learning is a well-established research area that leverages computational models to improve early detection, prognosis, and treatment planning. Traditional diagnostic methods, such as mammography, ultrasound, and histopathology, often require expert interpretation and are prone to variability, whereas machine learning models automate feature extraction and classification, improving accuracy and consistency. Early approaches used classical machine learning algorithms like support vector machines (SVM), decision trees, k-nearest neighbors (KNN), and random forests on handcrafted features extracted from imaging or clinical data. Recent advances incorporate deep learning architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention mechanisms, and hybrid models, enabling automated analysis of mammograms, histopathological slides, MRI scans, and multi-omics data. Applications include early tumor detection, malignancy classification, segmentation of lesions, and prognosis prediction. Current research also explores transfer learning, data augmentation, explainable AI for interpretability, ensemble learning, and integration with multi-modal clinical datasets, establishing machine learning as a transformative approach for improving the accuracy, efficiency, and scalability of breast cancer diagnosis.