Case study: RlapsRisk® BC
Authors
Case study: RlapsRisk® BC
Authors
About Owkin
Owkin is an AI biotechnology company that uses AI to find the right treatment for every patient. We combine the best of human and artificial intelligence to answer the research questions shared by biopharma and academic researchers. By closing the translational gap between complex biology and new treatments, we bring new diagnostics and drugs to patients sooner.
We use AI to identify new treatments, de-risk and accelerate clinical trials and build diagnostic tools. Using federated learning, a pioneering collaborative AI framework, Owkin enables partners to unlock valuable insights from siloed datasets while protecting patient privacy and securing proprietary data.
Owkin was co-founded by Thomas Clozel MD, a former assistant professor in clinical onco-hematology, and Gilles Wainrib, a pioneer in the field of machine learning in biology, in 2016. Owkin has raised over $300 million and became a unicorn through investments from leading biopharma companies (Sanofi and BMS) and venture funds (Fidelity, GV and BPI, among others).
Prediction of patient prognosis from digitized pathology slides in early Breast Cancer (ER+/HER2-)
Context
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.
Methods
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.
Results1, 2
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.
Impact
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
Diagnostic:
- 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