Cross-cohort generalizability of machine learning models for early-stage node-negative breast cancer relapse prediction
- 1Delaware State University
Abstract
BackgroundAdjuvant therapy decision in early-stage node-negative breast cancer remains one of the most challenging problems in oncology. Although most patients in this population achieve favorable outcomes with endocrine therapy alone, a subset remains at risk of relapse and may benefit from chemotherapy. Accurate identification of high-risk and low-risk patients is therefore essential to prevent both undertreatment and overtreatment.
MethodsIn this study, machine learning models were assessed using MSK-IMPACT (n=645) and METABRIC (n=503) cohorts comprising node-negative stage I-II breast cancer patients. Three experimental settings were evaluated: training on MSK-IMPACT and testing on METABRIC, the reverse direction, and five-fold cross-validation on the combined cohort. Sensitivity analysis and data harmonization were applied to identify and mitigate cohort-specific bias. Survival analysis, SHapley Additive exPlanations (SHAP) interpretability, and ablation analyses were performed to validate clinical relevance and characterize feature contributions.
ResultsThe combined cohort model achieved an area under the receiver operating characteristic curve (AUC) of 0.788{+/-}0.028 across five-fold cross-validation, while bidirectional cross-cohort validation yielded AUC of 0.741 when testing on MSK-IMPACT and AUC of 0.714 when testing on METABRIC. Survival validation on METABRIC out-of-fold predictions from the combined cohort model showed hazard ratios of 3.01 (95% CI: 2.28-3.98) for disease-free survival and 2.35 (95% CI: 1.79-3.09) for overall survival, consistent across Luminal A, Luminal B, and Triple-Negative subtypes.
ConclusionValidated across two geographically independent cohorts, the proposed model enables cost-effective, gene expression-free identification of patients at high-risk of distant relapse and may facilitate adjuvant chemotherapy decision-making in early-stage node-negative breast cancer.
Related
- An interpretable machine-learning signature predicts early triple-negative breast cancer recurrence but adds no prognostic value beyond clinicopathological factors in external validation
- Generalizability of a prediction model for walking independence at discharge in older adults after hip fracture surgery: a multicenter study
- Generalizability of proteomic risk prediction across biobanks reveals dependence on phenotype definitions
- Baseline severity of positive and negative symptoms predicts relapse in opposing directions among placebo-treated schizophrenia patients: analysis of five placebo-controlled, antipsychotic withdrawal, relapse-prevention trials
- Human Skin Permeability Prediction by Machine Learning for Transdermal Drug Delivery
BibTeX
@misc{ozdemir2026crosscohort,
title = {{Cross-cohort generalizability of machine learning models for early-stage node-negative breast cancer relapse prediction}},
author = {C. Ozdemir and S. Gupta},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.02.26364592},
url = {https://www.medrxiv.org/content/10.64898/2026.10.02.26364592v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Cross-cohort generalizability of machine learning models for early-stage node-negative breast cancer relapse prediction
AU - C. Ozdemir
AU - S. Gupta
PY - 2026
DA - 2026/10/02
PB - medRxiv
DO - 10.64898/2026.10.02.26364592
UR - https://www.medrxiv.org/content/10.64898/2026.10.02.26364592v1
AB - BackgroundAdjuvant therapy decision in early-stage node-negative breast cancer remains one of the most challenging problems in oncology. Although most patients in this population achieve favorable outcomes with endocrine therapy alone, a subset remains at risk of relapse and may benefit from chemotherapy. Accurate identification of high-risk and low-risk patients is therefore essential to prevent both undertreatment and overtreatment. MethodsIn this study, machine learning models were assessed using MSK-IMPACT (n=645) and METABRIC (n=503) cohorts comprising node-negative stage I-II breast cancer patients. Three experimental settings were evaluated: training on MSK-IMPACT and testing on METABRIC, the reverse direction, and five-fold cross-validation on the combined cohort. Sensitivity analysis and data harmonization were applied to identify and mitigate cohort-specific bias. Survival analysis, SHapley Additive exPlanations (SHAP) interpretability, and ablation analyses were performed to validate clinical relevance and characterize feature contributions. ResultsThe combined cohort model achieved an area under the receiver operating characteristic curve (AUC) of 0.788{+/-}0.028 across five-fold cross-validation, while bidirectional cross-cohort validation yielded AUC of 0.741 when testing on MSK-IMPACT and AUC of 0.714 when testing on METABRIC. Survival validation on METABRIC out-of-fold predictions from the combined cohort model showed hazard ratios of 3.01 (95% CI: 2.28-3.98) for disease-free survival and 2.35 (95% CI: 1.79-3.09) for overall survival, consistent across Luminal A, Luminal B, and Triple-Negative subtypes. ConclusionValidated across two geographically independent cohorts, the proposed model enables cost-effective, gene expression-free identification of patients at high-risk of distant relapse and may facilitate adjuvant chemotherapy decision-making in early-stage node-negative breast cancer.
ER -