Development and validation of a prognostic model for stage IV breast cancer based on primary tumor resection with machine learning methods: retrospective cohort study

1

The study investigates the association of primary tumor resection with survival outcomes in stage IV breast cancer using machine learning techniques.
2

Cox regression analysis indicated that primary tumor resection positively correlates with overall survival and cancer-specific survival in stage IV patients.
3

Subgroup analysis revealed better survival outcomes for patients with tumors ≤5 cm, N2 status, and HER2 overexpression after primary tumor resection.
4

The Support Vector Machine model demonstrated high accuracy in predicting survival outcomes, with AUC values ranging from 0.921 to 0.945 across different time points.
5

A user-friendly web application was developed to facilitate the clinical use of the prognostic model for identifying surgical candidates in stage IV breast cancer.

Frontiers In Endocrinology

by Yaoling Wang, Jingyu Hou, Xinhai Chen, Hongyi Zhu, Yuan Yao, Wenjing Zhao, Shuangwei Mo, Zhenchong Xiong, Anli Yang, Wei Liu, Yuanhui Lai, Weikai Xiao
July 13, 2026

1