Related Experiment Video
Updated: Apr 15, 2026
06:46
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
1.0K
Analytical Validation of Multimodal AI Test Predicting Breast Cancer Recurrence Risk (Ataraxis Breast RISK)
Marc Dantone1, Martin Lacsamana1, Ken G Zeng1
1Ataraxis AI, New York, NY 10016, USA.
Diagnostics (Basel, Switzerland)
|April 14, 2026
Summary
A new artificial intelligence (AI) test, Ataraxis Breast RISK (ATX), accurately predicts breast cancer recurrence risk using digital pathology images, offering a faster alternative to traditional gene expression tests.
Area of Science:
- Digital Pathology and Artificial Intelligence
- Oncology and Cancer Biomarkers
- Medical Diagnostics and Prognostics
Background:
- Traditional gene expression tests for breast cancer recurrence risk are time-consuming and tissue-intensive.
- Artificial intelligence (AI) applied to digital pathology images offers a novel approach to identify prognostic morphological biomarkers.
- AI model validation requires a specialized analytical approach distinct from conventional methods.
Purpose of the Study:
- To report the analytical validation of a novel artificial intelligence-based breast cancer prognostic test, Ataraxis Breast RISK (ATX).
- To assess the performance and reliability of ATX across multiple validation axes.
- To confirm the clinical readiness of ATX for integration into diagnostic workflows.
Main Methods:
- ATX utilizes a survival analysis model incorporating morphological features extracted from H&E-stained slides by a pan-cancer foundation model.
- The model integrates extracted features with clinical variables to generate a calibrated breast cancer recurrence risk score.
- Validation encompassed intra-operator repeatability, inter-operator reproducibility, limit of blank, limit of detection, inter-laboratory reproducibility, data perturbation robustness, and a clinical validation bridging study in CLIA-certified laboratories.
Main Results:
- Exceptional intra-operator (ICC 0.99, 100% agreement) and inter-operator (ICC 0.99, 100% agreement) repeatability was achieved.
- High inter-laboratory reproducibility (ICC 0.97, 94.7% agreement) was demonstrated across multiple scanners.
- ATX maintained robust performance under simulated data perturbations (average C-index 0.62, 90.0% agreement) and showed comparable performance in the bridging study (C-index 0.63 vs. 0.62).
Conclusions:
- The Ataraxis Breast RISK (ATX) test successfully met all predefined analytical acceptance criteria.
- The validation results provide strong evidence for the analytical readiness of ATX for clinical application.
- AI-driven digital pathology offers a promising, efficient, and reliable tool for breast cancer recurrence risk stratification.
Related Concept Videos
01:21Cancer Survival Analysis
846
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
846
01:13Sensitivity, Specificity, and Predicted Value
1.8K
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
1.8K
01:15Receiver Operating Characteristic Plot
584
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
584