Prognostic Evaluation Using Nutrition-Inflammation Biomarkers from Routine Blood Tests in Metastatic Breast Cancer: A Boruta Algorithm-Optimized Feature Selection Study

1

The study evaluated 17 nutrition and inflammation indices from blood tests in 163 metastatic breast cancer patients.
2

MLR, SIRI, ALI, AGR, and PA were identified as independent predictors of overall survival in metastatic breast cancer.
3

Patients with higher MLR and SIRI had significantly increased risks of death, while higher ALI, AGR, and PA correlated with reduced mortality risk.
4

Inflammation indices were better for short-term outcomes, while nutrition indices were more predictive of medium-to-long-term survival.
5

ALI and MLR showed consistent prognostic performance across all clinical subgroups, aiding in patient management and survival improvement.

Frontiers In Oncology

by Nong, Wen-xiong , Huang, Sheng-kai , Zhang, Wenhai , Tan, Yang , Wu, Zhi-dong , Liang, Wan-wang , Wu, Rui-zheng
May 13, 2026

1