What question did this study set out to answer?

This study aims to validate a regression model for predicting chemotherapy response in hormone receptor-positive breast cancer patients.

May 31, 2026Open Access

Accessible Clinical Tool for Prognosis and Chemotherapy Prediction in Hormone Receptor–Positive/Human Epidermal Growth Factor Receptor 2–Negative Breast Cancer in Diverse and Low-Resource Settings

Key Points

This study aims to validate a regression model for predicting chemotherapy response in hormone receptor-positive breast cancer patients.
Retrospective analysis of 1,566 patients from Chicago and 296 from Rio de Janeiro.
Model accuracy assessed using area under the receiver operating characteristic curve (AUROC).
Survival outcomes analyzed using Kaplan-Meier and Cox regression.
The estrogen receptor/progesterone receptor/Ki-67 model achieved an AUROC of 0.81 in Chicago and 0.91 in Rio de Janeiro.
Low-risk patients showed a 5-year disease-free interval of 98.0% compared to 81.6% in high-risk patients (HR 11.89, P < .001).
Chemotherapy offered no significant benefit for low-risk patients.

Abstract

PURPOSE Genomic assays are commonly used to predict breast cancer recurrence but remain inaccessible in low-resource settings, often leading to unnecessary chemotherapy. We previously optimized a LASSO-penalized regression model incorporating quantitative clinicopathologic features to predict genomic risk. Here, we present validation and clinical utility in an international cohort. METHODS We retrospectively analyzed patients with early-stage hormone receptor–positive/human epidermal growth factor receptor 2–negative breast cancer treated in Chicago and Rio de Janeiro. Model accuracy for predicting high Oncotype DX (ODX) scores was evaluated using area under the receiver operating characteristic curve (AUROC) in Chicago cohorts. Survival outcomes—disease-free interval (DFI), disease-free survival (DFS), and overall survival (OS)—were compared by Kaplan-Meier and Cox regression using a predefined threshold for high-risk disease. Adjusted models examined chemotherapy benefit by predicted risk. Estimated cost was compared between testing strategies and chemotherapy allocation in Brazil and the United States. The study was approved by the Brazilian Research Ethics Committee on October 24, 2024, under CAAE number 67993323.6.0000.5274. Due to the retrospective nature of the study, which involved only data collection from electronic medical records, the requirement for informed consent was waived by the Ethics Committee. Additionally, the study is covered under Institutional Review Board 22-0707 at the University of Chicago. RESULTS We included 1,566 patients from Chicago and 296 from Rio de Janeiro. The estrogen receptor/progesterone receptor/Ki-67 model showed strong performance for ODX prediction (AUROC 0.81 and 0.91).Compared with high-risk patients, low-risk patients had superior 5-year DFI (98.0% v 81.6%, hazard ratio HR, 11.89, P < .001), DFS (91.3% v 77.5%, HR, 3.41, P < .001), and OS (92.1% v 87.3%, HR, 2.47, P = .02). Chemotherapy provided no significant benefit in the low-risk group. CONCLUSION Our model accurately predicted recurrence and outcomes across US and Brazilian cohorts, supporting treatment de-escalation in low-risk patients and promoting equitable care where genomic testing is limited.

Read Full Paperexternally

AIに質問

Bookmark

View Full Paper