Predicting nodal response to neoadjuvant treatment in breast cancer with core biopsy biomarkers of tumor microenvironment using data mining

Purpose: To generate a model for predicting nodal response to neoadjuvant systemic treatment (NAST) in biopsy-proven node-positive breast cancer patients (cN+) that incorporates tumor microenvironment (TME) characteristics and could be used for planning the axillary surgical staging procedure.

Methods: Clinical and pathologic features were retrospectively collected for 437 patients. Core biopsy (CB) samples were reviewed for stromal content and tumor-infiltrating lymphocytes (TIL). Orange Datamining Toolbox was used for model generation and assessment.

Results: 151/437 (34.6%) patients achieved nodal pCR (ypN0). The following 5 variables were included in the prediction model: ER, Her-2, grade, stroma content and TILs. After stratified tenfold cross-validation, the logistic regression algorithm achieved and area under the ROC curve (AUC) of 0.86 and F1 score of 0.72. Nomogram was used for visualization.

Conclusions: We developed a clinical tool to predict nodal pCR for cN+ patients after NAST that includes biomarkers of TME and achieves an AUC of 0.86 after tenfold cross-validation.