Approximately 10% of all eBC patients will relapse after their initial treatment each year. Breast cancer (BC) is a heterogeneous disease encompassing several subtypes associated to a wide range of prognosis. Risk determination is crucial for treatment decision.
Owkin developed RlapsRisk BC, an AI-based tool that assesses the risk of distant relapse at 5 years of ER+/HER2- early invasive (ei)BC patients, post surgery, from HES (hematoxylin-eosin-safran)-stained whole slide images (WSI) and clinical data.
The solution was validated on 2 independent cohorts of 1000+ slides, in a blind single shot fashion.
This model accurately discriminate between low and high risk breast cancer patients (ER+/HER2) using digital pathology slides on resection pieces and improves the patients identification compared to clinical scores.
Combining RlapsRisk score and the clinico-pathological factors improved the prognostic discrimination (c-index 0.80) compared to the clinico-pathological factors alone (c-index 0.76).
RlapsRisk BC achieves 76% sensitivity and 76% specificity for post-treatment, time-dependent accuracy at 5 years, outperforming current clinical scores in practice.
Optimize clinical development:
- Stratification biomarker to select high value subgroups, improving RCT statistical power
- Inform on the most prognostic variables to increase RCT statistical power
- Help oncologists and pathologists to the risk of relapse of eBC patients
1. Manuscript under review with peer-reviewed journal, and available as a pre-print on bioRxiv.
2. Earlier results of the model published at Garberis IJ, et al. Annals of Oncology (2021): Poster presented at ESMO congress 2021 ; May 9th - 13th 2022; Paris France.
Learn more about RlapsRisk BC