An ultrasound-based model for predicting the response to neoadjuvant chemotherapy in early stage triple negative breast cancer patients
Abstract Background The accurate identification of patients with triple negative breast cancer (TNBC) likely to achieve pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) holds significant clinical value. The aim of this study was to establish a prediction model that incorporate...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01818-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Background The accurate identification of patients with triple negative breast cancer (TNBC) likely to achieve pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) holds significant clinical value. The aim of this study was to establish a prediction model that incorporate clinical data and ultrasound features to predict pCR among TNBC patients as early as possible after the initial two NAC cycles. Methods From January 2016 to December 2021, a total of 262 patients were recruited and divided into training and validation groups at a 7:3 ratio. Both univariate and multivariate logistic regression analyses were conducted to identify independent factors predicting pCR in the training group. Subsequently, a nomogram integrating the predictive factors was established and applied to the validation group. The performance of this model was assessed based on its discrimination, calibration and clinical utility. Results The nomogram that incorporated patient age, clinical T stage, posterior echo enhancement and tumor volume reduction showed robust performance. It achieved an area under curve (AUC) of 0.818, and recorded sensitivity, specificity, and accuracy of 65.2%, 82.5%, and 75.0% respectively in the training group. In the validation group, the model scored an AUC of 0.776, with sensitivity, specificity, and accuracy of 85.7%, 66.7%, and 73.4%, respectively. The decision curve analysis further indicated that the model provided more benefit than standard treat-all or treat-none approaches in predicting pCR. Conclusion This prediction model may assist in predicting pCR to NAC among patients with TNBC, enabling an optimal treatment management in clinical practice. Trial registration Not applicable. |
|---|---|
| ISSN: | 1471-2342 |