# Integrating multiparametric MRI radiomics and clinical models to assess sensitivity to neoadjuvant chemotherapy in breast cancer: A multicenter study

## TL;DR

This study combines MRI data and clinical information to predict which breast cancer patients will respond well to a specific type of chemotherapy before treatment begins.

## Contribution

A novel SHAP-explainable radiomic-clinical model for early prediction of neoadjuvant chemotherapy sensitivity in breast cancer.

## Key findings

- The integrated model achieved high accuracy (AUC 0.904) in predicting chemotherapy sensitivity.
- Wavelet_HHL_glcm_Correlation_DCE was identified as the most important predictive radiomic feature.
- A clinical nomogram translated model outputs into risk probabilities for treatment sensitivity.

## Abstract

To develop and externally validate an interpretable multiparametric MRI‐based radiomic‐clinical model using Shapley Additive Explanations (SHAP) methodology for early prediction of breast cancer sensitivity to neoadjuvant chemotherapy (NAC).

This retrospective multicentric study enrolled 223 breast cancer patients from three medical centers. Patients underwent pretreatment multiparametric MRI (DCE‐MRI and DWI sequences) with Miller‐Payne grades 4‐5 defining NAC‐sensitive. Manual tumor segmentation generated regions of interest for extracting 2,396 radiomic features per patient. Feature selection integrated reproducibility analysis (ICC > 0.7), univariable significance testing (p < 0.01), LASSO regression, and hierarchical clustering. A support vector machine (SVM) model incorporated optimized radiomic signatures and clinical variables. SHAP methodology provided global feature importance interpretation and individualized prediction explanations.

The integrated radiomic‐clinical model demonstrated superior performance to standalone clinical (AUC 0.720) and radiomic (AUC 0.833) models in the internal validation set, achieving an AUC of 0.904 (95% CI: 0.816–0.991). This advantage persisted in external validation (AUC 0.928, 95% CI: 0.874–0.982). SHAP analysis identified wavelet_HHL_glcm_Correlation_DCE as the predominant predictive feature, with high values significantly correlating to NAC‐sensitive. A clinical nomogram translated model outputs into quantifiable risk probabilities, where total scores ≥130 indicated > 95% sensitivity likelihood.

The SHAP‐explainable radiomic‐clinical model provides a clinically applicable, noninvasive tool for pretreatment stratification of NAC sensitivity. This approach enhances personalized therapeutic decision‐making while minimizing unnecessary treatment toxicity.