Enhancing Detection of Breast Cancer Through a Novel Framework: A Machine Learning Approach with Explainable AI Interpretation

Breast cancer, the most prevalent cancer among women, significantly contributes to increased mortality rates and ranks as the second leading cause of cancer-related deaths in women. Early detection is crucial for effective treatment, yet traditional diagnostic approaches often involve multiple laboratory tests supervised by medical experts. To mitigate human error and expedite breast cancer detection, there is a pressing need for automated systems capable of accurate and timely diagnosis. This study aims to investigate the application of machine learning (ML) techniques in classifying breast cancer using features from digitized images of fine-needle aspiration (FNA) breast mass samples. Machine learning methods are instrumental in addressing this imperative. The study conducts a comparative analysis of various ML classification methods, including Logistic Regression, Support Vector Machine (SVM), K Nearest Neighbor (KNN), Decision Trees, Bagging-Boosting, and ensemble models, using a breast cancer dataset to establish a novel framework. The performance of each algorithm is assessed based on metrics such as accuracy, precision, recall, and F1 score. The findings underscore the effectiveness of ensemble classifier models, achieving a notable accuracy rate of 98.87%. Additionally, the integration of explainable Artificial Intelligence enhances the interpretability of the models by providing valuable insights into their decision-making processes.