A Causal Multi-modal AI Model Stratifies Residual Risk and Identifies Candidates for Treatment Escalation in Node-Positive HR+/HER2- Early Breast Cancer
- 1Medical Oncology Department, Centre Leon Berard, Lyon, France
Abstract
PURPOSEPrognostic biomarkers that estimate residual recurrence risk after standard adjuvant therapy to guide further treatment escalation are an unmet clinical need. This study used Ataraxis Breast CTX, a causal multi-modal AI model integrating clinical variables and histopathology, to stratify residual risk in clinically defined high-risk patients. We aimed to identify patients who have excellent outcomes on standard-of-care chemoendocrine therapy and patients who may benefit from additional therapies such as everolimus or CDK4/6 inhibitors.
METHODSCTX combines clinical variables with image features from H&E images to produce estimates of recurrence risk (CTX-prognostic) and chemotherapy benefit (CTX-benefit). Prospective-retrospective validation was performed in the phase III UNIRAD trial to assess CTX-prognostics performance in the subset of patients who had not received neoadjuvant chemotherapy, who had received adjuvant chemotherapy, and who had H&E slides available (n = 556). The primary endpoint in this study was disease-free survival (DFS). As an exploratory analysis, we evaluated CTX-benefits ability to predict benefit from adjuvant everolimus.
RESULTSCTX-prognostic effectively stratified patients into high- and low-risk groups. Across all patients, 5-year DFS was significantly higher in the low-risk group (93%) than in the high-risk group (80%). Additionally, treatment benefit from everolimus differed significantly by CTX-benefit score in an exploratory multivariable analysis adjusting for age, tumor size, nodal status, grade, and menopausal status (interaction p = 0.01).
CONCLUSIONCTX identified patients with good outcomes under chemoendocrine therapy alone and patients with residual risk who may benefit from treatment escalation. Additionally, CTX was found to be predictive of everolimus benefit. These results suggest that CTX may effectively stratify clinically high-risk HR+/HER2- patients by residual risk and may inform selection of adjuvant escalation strategies.
Related
- Real‐World Treatment Escalation Patterns of Biologics and Functional Endoscopic Sinus Surgery in Chronic Rhinosinusitis (CRS): A Nationwide Database Study
- Modeling single nucleus microglia across species identifies immune pathways and therapeutic candidates in Alzheimer’s disease
- Potential biomarker candidates for improving diagnosis and disease treatment in adenomyosis
- Integrated adipose tissue transcriptomic and miRNA remodeling identifies molecular pathways associated with residual cardiovascular risk after weight loss
- HIGH-THROUGHPUT SCREENING OF BLOOD–BRAIN BARRIER-PENETRANT COMPOUNDS IDENTIFIES THERAPEUTIC CANDIDATES FOR CENTRAL NERVOUS SYSTEM-TROPIC PEDIATRIC ACUTE LYMPHOBLASTIC LEUKEMIA
BibTeX
@misc{bachelot2026causal,
title = {{A Causal Multi-modal AI Model Stratifies Residual Risk and Identifies Candidates for Treatment Escalation in Node-Positive HR+/HER2- Early Breast Cancer}},
author = {T. Bachelot and S. Chabaud and J. Lemonnier and P. H. Cottu and F. Dalenc and F. M. Howard and L. Pusztai and C. Tang and D. Biswas and K. Zeng and J. Witowski and K. J. Geras and F. Andre and F. M. Penault-Llorca},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.15.26362492},
url = {https://www.medrxiv.org/content/10.64898/2026.09.15.26362492v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - A Causal Multi-modal AI Model Stratifies Residual Risk and Identifies Candidates for Treatment Escalation in Node-Positive HR+/HER2- Early Breast Cancer
AU - T. Bachelot
AU - S. Chabaud
AU - J. Lemonnier
AU - P. H. Cottu
AU - F. Dalenc
AU - F. M. Howard
AU - L. Pusztai
AU - C. Tang
AU - D. Biswas
AU - K. Zeng
AU - J. Witowski
AU - K. J. Geras
AU - F. Andre
AU - F. M. Penault-Llorca
PY - 2026
DA - 2026/09/15
PB - medRxiv
DO - 10.64898/2026.09.15.26362492
UR - https://www.medrxiv.org/content/10.64898/2026.09.15.26362492v1
AB - PURPOSEPrognostic biomarkers that estimate residual recurrence risk after standard adjuvant therapy to guide further treatment escalation are an unmet clinical need. This study used Ataraxis Breast CTX, a causal multi-modal AI model integrating clinical variables and histopathology, to stratify residual risk in clinically defined high-risk patients. We aimed to identify patients who have excellent outcomes on standard-of-care chemoendocrine therapy and patients who may benefit from additional therapies such as everolimus or CDK4/6 inhibitors. METHODSCTX combines clinical variables with image features from H&E images to produce estimates of recurrence risk (CTX-prognostic) and chemotherapy benefit (CTX-benefit). Prospective-retrospective validation was performed in the phase III UNIRAD trial to assess CTX-prognostics performance in the subset of patients who had not received neoadjuvant chemotherapy, who had received adjuvant chemotherapy, and who had H&E slides available (n = 556). The primary endpoint in this study was disease-free survival (DFS). As an exploratory analysis, we evaluated CTX-benefits ability to predict benefit from adjuvant everolimus. RESULTSCTX-prognostic effectively stratified patients into high- and low-risk groups. Across all patients, 5-year DFS was significantly higher in the low-risk group (93%) than in the high-risk group (80%). Additionally, treatment benefit from everolimus differed significantly by CTX-benefit score in an exploratory multivariable analysis adjusting for age, tumor size, nodal status, grade, and menopausal status (interaction p = 0.01). CONCLUSIONCTX identified patients with good outcomes under chemoendocrine therapy alone and patients with residual risk who may benefit from treatment escalation. Additionally, CTX was found to be predictive of everolimus benefit. These results suggest that CTX may effectively stratify clinically high-risk HR+/HER2- patients by residual risk and may inform selection of adjuvant escalation strategies.
ER -