A CAD System Based On a Stacked Ensemble Model and ML Techniques for Breast Cancer Prognosis

breast cancer is the most spread cancer globally. The disease symptoms and treatments differ from one patient to another. Early detection can considerably alter the outcome for breast cancer patients. CAD systems playa fundamental role in the prognosis of the disease. In this paper, a proposed ensemble model based on the stacking technique uses logistic regression LR as a Meta-model and four machine learning algorithms Decision Tree DT, Random Forest RF, extreme gradient boosting XGboost, and adaptive boosting Adaboost as base models. The data used in this study is the breast cancer Wisconsin dataset. After preprocessing and features selection, the models were trained and then tested. Evaluation metrics were calculated to evaluate the system's global performance. Results indicate that the stacking techniques can enhance the performance of the system. The ensemble model outperformed the base models with an accuracy of over 98% and a precision of 100% which makes it of service for radiologists in breast tumor classification tasks.