Development of a multiparametric model for predicting the response to neoadjuvant chemotherapy in breast cancer

Choosing the appropriate treatment early and predicting the efficacy of neoadjuvant chemotherapy (NAC) for locally advanced breast cancer patients are of particular importance for clinicians. Developing and validating a multiparametric model for predicting NAC would be very meaningful for clinical practice.

This study included 91 patients with locally advanced breast cancer treated from 2016 to 2020. The correlation between multiparametric characteristics and the efficacy of NAC was examined. The data were randomly divided into training and validation sets. A least absolute shrinkage and selection operator (LASSO) regression analysis was used for the variable screening. A multivariable logistic regression analysis was used to construct the model. Calibration and decision curves were used to assess the performance of the established model.

Lymph node metastasis, the first standard apparent diffusion coefficient (ADC) at the baseline, the change in the standard ADC at the first follow-up, the change in tumor volume at the first follow-up, and the clinical stage of the tumor at the baseline were selected for inclusion in the model. In the receiver operating characteristic (ROC) analysis, the areas under the curve (AUCs) were 0.984 [95% confidence interval (CI): 0.958-1] and 0.815 (95% CI: 0.509-1) for the primary and validation cohorts, respectively. The utility of the established model was confirmed by calibration and decision curves, and a nomogram was obtained.

A multiparametric model based on clinical-pathological-magnetic resonance imaging (MRI) features was established to predict the effect of NAC in patients with locally advanced breast cancer.