The rise in breast cancer (BC) cases globally has created a huge threat to women’s lives. This highlights the significance of precise and trustworthy diagnostic techniques. Traditional diagnostic methods, like mammography and biopsy, are often time-consuming and liable to human error. Recently, machine learning (ML) has emerged as a powerful tool for BC detection and decision-making processes. However, the lack of transparency in decision-making has hampered ML’s adoption in clinical settings. This study investigates ways to enhance breast cancer diagnosis interpretability and predictive accuracy by combining explainable AI (XAI) methods with machine learning (ML) algorithms. The Wisconsin diagnosis breast cancer dataset is used, preprocessed, and transformed to facilitate effective machine learning algorithms for analysis and prediction. A range of machine learning techniques, such as decision tree classifier, k-nearest neighbors (KNN), support vector classifier (SVC), and naïve Bayes, are evaluated using significant performance metrics like accuracy and speed. To enhance interpretability and mitigate the “black-box” nature of these models, explainability techniques such as local interpretable model-agnostic explanations (LIME) are applied. These techniques help doctors comprehend and have faith in AI-driven diagnoses by offering insights on feature significance and decision-making procedures. The suggested method increases clinical acceptance of AI-based treatments by improving diagnostic performance and maintaining transparency. This research aids in developing reliable decision-support tools by improving interpretability and providing medical practitioners with data-driven information to make more accurate breast cancer diagnoses.