What does this research mean for the field?

A machine learning model using Ki-67, histologic grade, and progesterone receptor status moderately predicts high Oncotype DX® Recurrence Scores (RS ≥ 25) in patients with ER+ breast cancer. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.SUPPORTS_CONSENSUS.

What question did this study set out to answer?

The study aims to evaluate the accuracy of machine learning models based on clinicopathologic data in predicting high Oncotype DX® recurrence scores.

February 19, 2026Clinical Cancer Research

Abstract PS3-08-12: Machine Learning Prediction of High Oncotype DX® RS based on Clinicopathologic features: Results from the GBECAM 0520 Multicenter Retrospective Study

View Full Paper

Ask AI

Bookmark

The study aims to evaluate the accuracy of machine learning models based on clinicopathologic data in predicting high Oncotype DX® recurrence scores.
Retrospective cohort assembly of 897 ER+ breast cancer patients with Oncotype DX results.
Statistical analysis to identify predictive variables such as Ki-67, PR status, and histologic grade.
Development of a ridge regression model to estimate Recurrence Score values.
Performance measured using area under the curve (AUC) and Pearson correlation.
Leave-one-center-out cross-validation for robustness.
The model achieved a mean Pearson correlation of 0.50 ± 0.03 between predicted and actual recurrence scores.
An AUC of 0.78 ± 0.03 for detecting high-risk tumors (Recurrence Score ≥ 25).
Ki-67 emerged as the strongest positive predictor of high recurrence scores.
Histologic grade positively correlated, while PR status was inversely correlated with recurrence score.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Multicenter retrospective study predicts high recurrence scores in breast cancer using machine learning models, suggesting clinical implications.

Cite This Study

Araujo et al. (2026) studied this question.

synapsesocial.com/papers/6996a8d4ecb39a600b3eff22 https://doi.org/10.1158/1557-3265.sabcs25-ps3-08-12

View Full Paper

Ask AI

Bookmark

Implication

Multicenter retrospective study predicts high recurrence scores in breast cancer using machine learning models, suggesting clinical implications.

Abstract PS3-08-12: Machine Learning Prediction of High Oncotype DX® RS based on Clinicopathologic features: Results from the GBECAM 0520 Multicenter Retrospective Study

Key Points

Discussion

Implication

Cite This Study

Abstract PS3-08-12: Machine Learning Prediction of High Oncotype DX® RS based on Clinicopathologic features: Results from the GBECAM 0520 Multicenter Retrospective Study

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider