Objective:

To evaluate whether an integrated immune-inflammatory phenotype can improve disease-free survival (DFS) stratification in breast cancer, enhancing current prognostic methods.

Approach:

Key Findings:

• 107 patients (21.3%) experienced a DFS event during follow-up.
• RSF achieved the best performance with time-dependent AUCs reaching 0.911 at 60 months.
• Pathological N stage was the most important predictor in the RSF model.
• High SII and poor integrated immune phenotype were associated with significantly worse DFS (p < 0.05).
• The poor phenotype was independently associated with worse DFS compared to the favorable phenotype (hazard ratio 2.53, 95% CI 1.39–4.60).
• Immunohistochemical validation showed differences in CD8+ and CD163+ cell densities between phenotypes.

Interpretation:

The integrated immune phenotype and SII emerged as clinically relevant predictors of DFS, supported by tissue-level biological findings, suggesting potential for improved clinical decision-making.

Limitations:

• Single-center study may limit generalizability.
• Retrospective design may introduce selection bias.
• Potential confounding factors not accounted for due to the observational nature of the study.

Conclusion:

Combining machine learning-based survival modeling with immune-inflammatory markers may enhance recurrence risk stratification in breast cancer.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.