Comprehensive Methodologies for Breast Cancer Classification: Leveraging XAI LIME, SHAP Bagging Boosting, and Diverse Single Classifiers
Dhruvi T Avlani, Abhijna MB, Sai Disha GS, Ashwini Kodipalli, Trupthi Rao · 2024
Breast cancer is one of the most common causes for deaths owed to cancer. It is very crucial and necessary to detect cancer at early phases. There are various Machine Learning techniques and computational techniques available for the aim of diagnosis of breast cancer data. This paper offers a Machine Learning model to perform automated diagnosis for the classification of breast cancer. This method employs single classifier model and bagging boosting for feature selection. Also, four algorithms SVM, Decision Tree, KNN and Logistic Regression which gives the highest accuracy of 88%. The system was trailed on BCGENES Dataset. The performance of the system is measured on the basis of accuracy and precision. The incorporation of XAI methods, such as SHAP values and LIME, provides a nuanced understanding of feature importance and individual predictions, elevating model interpretability. The amalgamation of machine learning classifiers, hyperparameter tuning, and XAI techniques contributes to advanced screening tools, fostering trust among clinicians and researchers.