Related Experiment Video
Updated: Jul 12, 2026
08:05
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
Refining Stratification in Premenopausal Node-Positive HR+/HER2- Breast Cancer With a Novel AI-Based Test
Jailan Elayoubi1, Cerise Tang2, Kathryn J Ruddy3
1Department of Hematology and Oncology, Karmanos Cancer Institute, Wayne State University, Detroit, MI.
Clinical Breast Cancer
|July 10, 2026
Summary
An artificial intelligence (AI) test, Ataraxis Breast RISK (ATX), shows promise in predicting recurrence in premenopausal breast cancer patients. Unlike genomic assays, ATX effectively stratifies risk, identifying high-risk individuals for potential intervention.
Area of Science:
- Oncology
- Artificial Intelligence in Medicine
- Genomic Medicine
Background:
- Genomic assays are standard for breast cancer stratification in postmenopausal women.
- These assays have limited utility for premenopausal women, particularly for chemotherapy decisions in node-positive cases.
- There is a need for improved risk stratification tools in this demographic.
Purpose of the Study:
- To evaluate the Ataraxis Breast RISK (ATX) test, an AI-based tool, for recurrence risk stratification in premenopausal women with node-positive breast cancer.
- To compare the performance of ATX against a clinically approved genomic assay.
- To explore ATX's ability to identify patients who might benefit from intensified treatment or de-escalation strategies.
Main Methods:
- ATX scores were generated for 222 HR+ HER2- premenopausal patients with node-positive breast cancer.
- Patients were stratified into ATX high- and low-risk groups.
- Recurrence-free interval (RFI) was analyzed using Kaplan-Meier estimates and C-index.
- Exploratory comparison with a genomic assay was performed on a subset of 43 patients.
Main Results:
- ATX demonstrated good discrimination with a pooled C-index of 0.75 and 5-year time-dependent AUC of 0.63.
- ATX stratified patients into high-risk (75%) and low-risk (25%) groups with significantly different RFI (P = .04).
- High-risk patients had a twofold higher 5-year recurrence rate (17%) compared to low-risk patients (7%), whereas genomic risk groups showed similar recurrence rates (17% vs. 14%).
Conclusions:
- The ATX test provides meaningful prognostic information in premenopausal, node-positive breast cancer patients.
- ATX may identify patients at elevated recurrence risk who are not adequately captured by current genomic assays.
- AI-based tools like ATX hold potential for refining risk stratification and guiding treatment decisions in specific breast cancer populations.
