Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 29, 2026Journal of Clinical Oncology

Clinicopathology-based machine learning model for prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer.

View Full Paper
Ask AI
Bookmark
Share

Authors

EÖEnver ÖzkurtIstanbul Bilim UniversityFSFatma Zehra SariTurkish Society of CardiologyMBMehmet BaysanIstanbul Technical University

Discussion

Loading...

Member takes

Implication

Retrospective study develops a machine learning model to predict pCR in breast cancer, suggesting improved clinical outcomes.

Key Points

  • The aim is to develop a machine learning framework to predict pathologic complete response to neoadjuvant chemotherapy in breast cancer using clinicopathological data.
  • Analyzed 298 breast cancer cases from a Turkish cohort (n = 84 pCR vs. n = 214 non-pCR).
  • Partitioned dataset into training and independent test sets with nested cross-validation for model evaluation.
  • Used 12 machine learning algorithms including Logistic Regression and XGBoost, while addressing class imbalance and optimizing decision thresholds.
  • Logistic Regression achieved a ROC-AUC of 0.803 and 88% sensitivity in the test set (n = 60), identifying 15 out of 17 pCR cases.
  • The model outperformed random baseline estimates for NPV (71% to 93.1%) and PPV (26.9% to 48.4%).
  • HER2 expression was the strongest predictor of pCR, while ER status and AJCC stage were the strongest negative predictors.

Cite This Study

Özkurt et al. (2026) studied this question.

synapsesocial.com/papers/6a192eb9fab5b468c4417eadhttps://doi.org/10.1200/jco.2026.44.16_suppl.e12567
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Practical Machine Learning Model for Predicting Neoadjuvant Response in HER2-Positive Breast Cancer2026
  2. 2A predictive model for pathological complete response in neoadjuvant-treated breast cancer: integrating pretreatment clinicopathologic and contrast-enhanced ultrasound characteristics via interpretable machine learning2026
  3. 3Interpretable Machine Learning for Predicting Neoadjuvant Chemotherapy Response in Breast Cancer Using the Baseline Clinical and Pathological Characteristics2025 · 4 citations
  4. 4Predicting Pathological Complete Response in HER2+ Breast Cancer: An AI-Driven Model Using Standard Clinical Practice Parameters2025
  5. 5A real-world clinicopathological model for predicting pathological complete response to neoadjuvant chemotherapy in breast cancer2024 · 19 citations