New partnership between CALYM and Owkin
Owkin and Institut Carnot CALYM Launch a Collaboration to Advance Lymphoma Research with Artificial Intelligence
Owkin, a startup that deploys AI and Federated Learning technologies to augment medical research and enable scientific discoveries, and Institut Carnot CALYM Launch a Collaboration to Advance Lymphoma Research with Artificial Intelligence.
This engagement was formed to leverage high-quality datasets from LYSARC, member of Institut Carnot CALYM, as well as Owkin’s pioneering technologies and research platform, to advance clinical research and drug development for the benefit of patients.
Researchers at Institut Carnot CALYM will team up with Owkin to develop and validate predictive machine learning models based on digitized histology slides from LYSARC clinical trials. This collaboration will focus on diffuse large B-cell lymphoma, the most common type of non-Hodgkin Lymphoma in adults (30-40%). The disease is known to be very heterogeneous with 60% of patients who respond to a treatment regimen known as R-CHOP and 40% of patients that are either refractory from the outset or relapse early. In this context, a better characterization of patients is important to optimize treatment assignment. This collaboration aims at better classifying DLBCLs into different subtypes based on deep learning models trained on digital pathology images.
Built around data coming from clinical trials performed by the LYSA and LYSARC, and Owkin machine learning platform, this project will benefit from the complementarity of expertises of CALYM members in clinical and anatomopathology research and of Owkin in data science.
A second research project will focus on synthetic control arm, and, more precisely on the evaluation of debiased machine learning methods to estimate the average treatment effect.
The CALYM researchers will have access to Owkin’s machine learning platform, Owkin Studio, which was specifically designed for researchers. Institut Carnot CALYM members will benefit from studying the AI algorithms developed by Owkin’s teams and trained on their own histology data, to collaborate directly with data scientists on the results.
Go further: watch the replay of RedTalks # 2
“WHY AI HYPE SHOULD NOT MAKE US LOSE COMMON SENSE?”
