Comparative Analysis of Machine Learning Models for Breast Cancer Patients’ Survival Prediction

Breast cancer (BC) is one of the most frequently diagnosed neoplasms worldwide and remains the leading cause of mortality among women. The recent application of machine learning methods has successfully predicted BC survival. In this study, we conducted a comparative analysis of specific survival analysis models applied to clinical data. Ensemble models, Gradient Boosting Survival (GBS), and Random Survival Forest (RSF) outperformed traditional approaches. The results of this study reinforce the promising potential of machine learning methods in analyzing the survival of breast cancer patients, with GBS and RSF models standing out as highly effective approaches to enhance the prediction of these patients’ survival. This advancement is relevant in oncology, making substantial contributions to clinical decision-making and therapeutic planning.