Abstract
The most prevalent malignancy among women is breast cancer; hence, treatment approaches are needed in consideration of tumor characteristics and disease stage but also patient preference. Two surgical options, Mastectomy and Breast Conserving Surgery (BCS), share the same survival outcomes, clinical or molecular factors; and explainable Machine Learning (ML) techniques like SHapley Additive exPlanations (SHAP) offer further insights. To compare the overall survival status of breast cancer patients undergoing Mastectomy versus BCS using ML models and SHAP values, identifying key predictors for survival. This study used the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset, which contains 2509 patients with clinical and molecular features. The preprocessing steps included imputation of missing values, class balancing using Synthetic Minority Over-sampling Technique (SMOTE), and feature selection. Gradient Boosting was identified as the best model, considering metrics such as accuracy, precision, and Area Under the Receiver Operating Characteristic Curve (ROC-AUC). SHAP values were used for feature importance, detailing the contribution of predictors to survival outcomes in both surgical groups. Gradient Boosting achieved a training accuracy of 95.4% and test accuracy of 86.4% for Mastectomy, and 94.6% and 82.8% respectively for BCS. Strong predictors included Relapse Free Status, Nottingham Prognostic Index and Age at Diagnosis. SHAP analysis indicated that the Relapse Free Status was an important predictor across both surgeries though there were specific influences of Age and Menopausal State. Younger patients benefited more with BCS while older ones faced higher risks from Mastectomy. The performance for BCS was significantly higher-3.73 than the performance of Mastectomy-1.21. The SHAP-driven insights pointed toward a more personalized approach to treatment, depending on both clinical and molecular predictors. This will justify tailored surgical and adjuvant therapies in achieving optimized survival.