Multimodal Artificial Intelligence Predicts Pathological Response and Prognosis in HER2-Positive Early Breast Cancer Treated with Chemotherapy De-escalation Strategies: Analyses from PHERGain and PHERGain-2 Trials
- 1Hospital Arnau De Vilanova, FISABIO, Valencia, Spain
Abstract
BackgroundChemotherapy (CT) de-escalation strategies based on dual HER2 blockade with trastuzumab and pertuzumab (HP) have shown promising efficacy in HER2-positive (HER2+) early breast cancer (EBC), but biomarkers to guide patient selection are lacking. The Ataraxis Breast platform (ATX) uses artificial intelligence (AI) models integrating hematoxylin-eosin (HCE) whole-slide images and clinical variables to predict pathological complete response (pCR) and long-term outcomes. We evaluated ATX in the phase II PHERGain (NCT03161353) and PHERGain-2 (NCT04733118) trials.
MethodsThe ATX NEO model was assessed for pCR prediction in PHERGain (n=306 evaluable patients) and PHERGain-2 (n=383 evaluable patients). The ATX RISK model was evaluated for prognosis in PHERGain (n=309 evaluable patients). Prespecified cutoffs classified patients into low-, medium-, and high-probability groups for pCR and low-or high-risk groups for recurrence. Associations with pCR were assessed using logistic regression. Prognostic performance was evaluated using Cox proportional hazards models, Kaplan-Meier estimates, and Harrells C-index.
ResultsOverall pCR rates were 40.2% in PHERGain and 60.3% in PHERGain-2. Continuous NEO scores were significantly associated with pCR in both PHERGain (odds ratio [OR], 1.28; 95% CI, 1.11-1.48; P<0.001) and PHERGain-2 (OR, 1.30; 95% CI, 1.13-1.52; P<0.001). Using prespecified cutoffs, pCR rates increased across low-, medium-, and high-probability groups (19.2%, 41.3%, and 48.3% in PHERGain; 29.5%, 61.6%, and 70.1% in PHERGain-2). In PHERGain, the RISK score was significantly associated with event-free survival (hazard ratio per 1-SD increase, 1.56; 95% CI, 1.17-2.08; P=0.002; C-index, 0.66). Five-year event-free survival was 93.9% in the low-risk group and 83.1% in the high-risk group.
ConclusionsNEO score was consistently associated with pCR across two independent HER2+ EBC trials, while RISK score provided prognostic information for long-term outcomes in PHERGain. Prespecified score categories identified clinically distinct response and risk groups. These findings support further evaluation of AI-based biomarkers to refine patient selection for CT de-escalation strategies in HER2+ EBC.
Related
- Predicting Pathological Dental Wear: A Roadmap for Artificial Intelligence in Natural Teeth and Restorations
- Toward integrated multimodal artificial intelligence in bone marrow examination: current state and open challenges
- Artificial Intelligence–Driven Multimodal Imaging for Cancer During Pregnancy: Advances in Maternal–Fetal Diagnostics and Precision Oncology
- Artificial Intelligence, Multi-Omics, and Multimodal Integration in Precision Radiotherapy for Head and Neck Cancer: From Biological Insights to Treatment Decisions
- Artificial Intelligence-Driven Nanobody Engineering for Pathogen Recognition: From Functional Epitope Prioritization to Multimodal Foundation Models
BibTeX
@misc{borrego2026multimodal,
title = {{Multimodal Artificial Intelligence Predicts Pathological Response and Prognosis in HER2-Positive Early Breast Cancer Treated with Chemotherapy De-escalation Strategies: Analyses from PHERGain and PHERGain-2 Trials}},
author = {M. Ruiz Borrego and J. Cortes and A. Stradella and B. Bermejo and S. Escriva de Romani and C. Reboredo and C. Albacar and L. Garrigos and S. Kummel and M. Colleoni and G. Gebhart and F. Dalenc and K. Kerrou and S. Braga and P. Schmid and F. Marme and S. Di Cosimo and G. Notini and E. Martinez Garcia and A. Amaya-Garrido and D. Alcala Lopez and L. Mina and J. Rodriguez Morato and C. Tang and D. Biswas and B. Machura and J. Witowski and K. J. Geras and J. Park and M. Mancino and J. M. Perez Garcia and A. Llombart Cussac},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.26364736},
url = {https://www.medrxiv.org/content/10.64898/2026.10.05.26364736v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Multimodal Artificial Intelligence Predicts Pathological Response and Prognosis in HER2-Positive Early Breast Cancer Treated with Chemotherapy De-escalation Strategies: Analyses from PHERGain and PHERGain-2 Trials
AU - M. Ruiz Borrego
AU - J. Cortes
AU - A. Stradella
AU - B. Bermejo
AU - S. Escriva de Romani
AU - C. Reboredo
AU - C. Albacar
AU - L. Garrigos
AU - S. Kummel
AU - M. Colleoni
AU - G. Gebhart
AU - F. Dalenc
AU - K. Kerrou
AU - S. Braga
AU - P. Schmid
AU - F. Marme
AU - S. Di Cosimo
AU - G. Notini
AU - E. Martinez Garcia
AU - A. Amaya-Garrido
AU - D. Alcala Lopez
AU - L. Mina
AU - J. Rodriguez Morato
AU - C. Tang
AU - D. Biswas
AU - B. Machura
AU - J. Witowski
AU - K. J. Geras
AU - J. Park
AU - M. Mancino
AU - J. M. Perez Garcia
AU - A. Llombart Cussac
PY - 2026
DA - 2026/10/05
PB - medRxiv
DO - 10.64898/2026.10.05.26364736
UR - https://www.medrxiv.org/content/10.64898/2026.10.05.26364736v1
AB - BackgroundChemotherapy (CT) de-escalation strategies based on dual HER2 blockade with trastuzumab and pertuzumab (HP) have shown promising efficacy in HER2-positive (HER2+) early breast cancer (EBC), but biomarkers to guide patient selection are lacking. The Ataraxis Breast platform (ATX) uses artificial intelligence (AI) models integrating hematoxylin-eosin (HCE) whole-slide images and clinical variables to predict pathological complete response (pCR) and long-term outcomes. We evaluated ATX in the phase II PHERGain (NCT03161353) and PHERGain-2 (NCT04733118) trials. MethodsThe ATX NEO model was assessed for pCR prediction in PHERGain (n=306 evaluable patients) and PHERGain-2 (n=383 evaluable patients). The ATX RISK model was evaluated for prognosis in PHERGain (n=309 evaluable patients). Prespecified cutoffs classified patients into low-, medium-, and high-probability groups for pCR and low-or high-risk groups for recurrence. Associations with pCR were assessed using logistic regression. Prognostic performance was evaluated using Cox proportional hazards models, Kaplan-Meier estimates, and Harrells C-index. ResultsOverall pCR rates were 40.2% in PHERGain and 60.3% in PHERGain-2. Continuous NEO scores were significantly associated with pCR in both PHERGain (odds ratio [OR], 1.28; 95% CI, 1.11-1.48; P<0.001) and PHERGain-2 (OR, 1.30; 95% CI, 1.13-1.52; P<0.001). Using prespecified cutoffs, pCR rates increased across low-, medium-, and high-probability groups (19.2%, 41.3%, and 48.3% in PHERGain; 29.5%, 61.6%, and 70.1% in PHERGain-2). In PHERGain, the RISK score was significantly associated with event-free survival (hazard ratio per 1-SD increase, 1.56; 95% CI, 1.17-2.08; P=0.002; C-index, 0.66). Five-year event-free survival was 93.9% in the low-risk group and 83.1% in the high-risk group. ConclusionsNEO score was consistently associated with pCR across two independent HER2+ EBC trials, while RISK score provided prognostic information for long-term outcomes in PHERGain. Prespecified score categories identified clinically distinct response and risk groups. These findings support further evaluation of AI-based biomarkers to refine patient selection for CT de-escalation strategies in HER2+ EBC.
ER -