Objective:

To evaluate inflammatory-nutritional indices in relation to breast cancer (BC) risk and mortality and develop a cross-ethnically validated prediction model.

Approach:

• Study Design: Analysis of NHANES data from 2005-2018, including 485 BC patients and 16,838 female controls, with mortality follow-up through 2019.
• Statistical Analysis: Weighted multivariate logistic and Cox regression assessed associations between inflammatory indices and BC risk/mortality.
• Machine Learning: Multiple ML algorithms, including XGBoost, were used to construct risk models, which were externally validated.

Key Findings:

• In fully adjusted models, the Advanced Lung Cancer Inflammation Index (ALI) was inversely associated with BC risk and all-cause mortality (highest vs. lowest tertile: odds ratio [OR] 0.64, 95% CI 0.45–0.91; hazard ratio [HR] 0.41, 95% CI 0.18–0.90).
• Conversely, neutrophil percentage-to-albumin ratio (NPAR), systemic inflammation response index (SIRI), and neutrophil-to-lymphocyte ratio (NLR) showed positive associations.
• XGBoost identified NPAR as the top predictive feature; the model incorporating inflammatory indices and age achieved an AUC of 0.832 on the test set.

Interpretation:

Limitations:

• Cross-ethnic validation highlighted the need for population-specific calibration.
• The study's reliance on NHANES data may limit generalizability to other populations.

Conclusion: