EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ultrasound and Clinicopathological Features‐Based Machine Learning Model for Predicting Neoadjuvant Therapy Efficacy in Breast Cancer

Tongtong Hao iD, Xiaohui Ji iD, Qianying Zhao iD, Mengying Wei iD

Cancer Reports · 2026-06 · 9 (6)

DOI: 10.1002/cnr2.70600 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancer Reports, online erschienen am 16.06.2026. Verfasst von Tongtong Hao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound Medicine, The Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, China. Hauptthemen laut MEDLINE: Breast Neoplasms, Neoadjuvant Therapy, Prediction Algorithms, Ultrasonography, Mammary. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate prediction of pathological complete response (pCR) after neoadjuvant therapy (NAT) remains challenging in breast cancer. Conventional imaging modalities, such as ultrasound and magnetic resonance imaging (MRI), have limited accuracy when used alone.

Aims

To develop and validate a machine learning model integrating ultrasound imaging features and clinicopathological information for non‐invasive and individualized prediction of pCR following NAT in breast cancer patients. Methods and Results This retrospective study included 609 breast cancer patients who underwent NAT. Ultrasound imaging features and clinicopathological variables were collected and analyzed. Data preprocessing was performed using Python and R. The diagnostic performance of ultrasound and MRI for predicting pCR was evaluated as a baseline. Significant predictors were identified through univariate and multivariate analyses. Three machine learning models—Random Forest, Logistic Regression, and Support Vector Machine—were developed and validated. Model performance was assessed using receiver operating characteristic (ROC) curves and decision curve analysis, while SHAP analysis and feature importance rankings were used to evaluate variable contributions. The Random Forest model achieved the best performance, with an AUC of 0.85 and an accuracy of 84.7%, outperforming conventional imaging assessments. Key predictors included early NAT tumor volume reduction ≥ 80%, increased echogenicity, HER2 positivity, and higher tumor‐infiltrating lymphocyte levels.

Conclusion

The Random Forest model substantially improved prediction of pCR after NAT in breast cancer and may provide a practical, non‐invasive tool to support individualized treatment planning, and clinical decision‐making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsNeoadjuvant TherapyPrediction AlgorithmsUltrasonography, MammaryAdultAgedFemaleHumansMiddle AgedClassification AlgorithmsMachine LearningMagnetic Resonance ImagingPathologic Complete ResponsePredictive Learning ModelsPrognosisRandom ForestRetrospective StudiesROC Curve

Stichwörter der Autor:innen

breast cancermachine learningneoadjuvant therapyultrasound

Autor:innen und Institutionen

  • Department of Ultrasound Medicine, The Fourth Hospital of Hebei Medical University, Shijiazhuang City, Hebei Province, China.

ORCID-Profile: Tongtong Hao, Xiaohui Ji, Qianying Zhao, Mengying Wei

Zitieren

APA

Hao, T., Ji, X., Zhao, Q., & Wei, M. (2026). Ultrasound and Clinicopathological Features‐Based Machine Learning Model for Predicting Neoadjuvant Therapy Efficacy in Breast Cancer. Cancer Reports, 9(6). https://doi.org/10.1002/cnr2.70600

Vancouver

Hao T, Ji X, Zhao Q, Wei M. Ultrasound and Clinicopathological Features‐Based Machine Learning Model for Predicting Neoadjuvant Therapy Efficacy in Breast Cancer. Cancer Reports. 2026;9(6). doi:10.1002/cnr2.70600

BibTeX
@article{Hao2026,
  author = {Hao, Tongtong and Ji, Xiaohui and Zhao, Qianying and Wei, Mengying},
  title = {Ultrasound and Clinicopathological Features‐Based Machine Learning Model for Predicting Neoadjuvant Therapy Efficacy in Breast Cancer},
  journal = {Cancer Reports},
  year = {2026},
  volume = {9},
  number = {6},
  doi = {10.1002/cnr2.70600}
}
Kostenlos starten →