Survival Prediction in Breast Cancer Patients Based on Stacking Methods
Chaochao Miao, Peijiang Chen · 2024
Breast cancer is one of the most common cancers among women, and accurately predicting its survival rate is crucial for personalized treatment and improved prognosis. We developed a breast cancer survival rate prediction model based on the Stacking method to improve prediction accuracy. We integrated traditional machine learning models such as logistic regression, support vector machines, random forests, and gradient-boosting decision trees. The Stacking model outperformed other models in terms of accuracy, precision, recall, F1 score, and AVC. The Stacking method predicted the five-year survival rate of breast cancer accurately, enhancing prediction performance and generalization capability. Thus, the model is an effective solution for prognosis management.