Predicting pathologic complete response in locally advanced breast cancer post-neoadjuvant chemotherapy: a novel nomogram integrating immune-inflammation indices and clinicopathological data

Pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) is a critical prognostic indicator for locally advanced breast cancer (LABC; defined as clinical stage III and high-risk stage IIB). pCR rates vary substantially across molecular subtypes—highest in triple-negative and HER2-positive tumors (> 30–45%) and lowest in HR-positive/HER2-negative subtypes (2–12%). Accurate pretreatment prediction of pCR remains challenging. This study aimed to develop and validate a nomogram integrating immune-inflammation indices and clinicopathological data to predict pCR in LABC patients receiving NAC. This retrospective analysis included 360 LABC patients from the training/internal validation cohort (GHWTC, 2020–2024) and 124 from an external cohort (DYPH, 2021–2025). Independent predictors were identified via LASSO and multivariable logistic regression. A nomogram was constructed and validated using AUC, calibration curves, and decision curve analysis. An individualized pCR prediction model was constructed and illustrated as a nomogram, which was internally and externally validated. Seven independent predictors were identified: cT, cN, PR status, HER2 status, NLR, SIRI, and SII. The nomogram integrating these seven factors showed excellent discrimination, with AUC‑ROC values of 0.880 (95% CI: 0.834–0.926) in the training set, 0.960 (95% CI: 0.904–0.988) in the internal validation set, and 0.935 (95% CI: 0.876–0.971) in the external validation set. Calibration curves indicated good agreement. The optimal cutoff value was 0.372 (~ 324 points). Decision curve analysis confirmed the clinical utility of the nomogram. This validated nomogram provides an accurate, individualized tool for predicting pCR in LABC patients, facilitating personalized NAC decision-making in clinical practice. Not applicable