To design, prototype, and develop Connect, we needed considerable effort and interdisciplinary skills. They received approval from the Director of IT and Data Protection Officers, Thierry Durand, and Franck Mestre at CLB and Astrid Lang at Institut Curie to deploy Connect behind their firewalls and run federated learning model training on their data. Therefore, in November 2019, we were proud to present our security protocols to the Healthchain partners. This did not identify any severe security weaknesses. In October 2019, we ran a thorough risk analysis and a successful security audit. Hence, we had to strengthen every security aspect of Connect before deploying it at CLB and Institut Curie. A data leak could affect privacy, even though the patient data is pseudonymized. Additionally, Connect trains algorithms on patient data and shares those algorithms between centers. As with any software deployed within a hospital’s infrastructure, a security breach could endanger the hospital’s whole IT system and affect all activities, even patient care. Any mistake in the code would have severe consequences. However, in this case, we could not afford to give our partners an MVP. This means building a quick and dirty-yet functional-an early version of the product to collect user feedback with little effort before scaling up production. Startups are familiar with the concept of Minimum Viable Product (MVP). The consortium gathers seven public partners: CLB, Institut Curie, CHU Nantes, AP-HP, Université Paris Descartes, and Ecole Polytechnique, and three private partners: Owkin, Substra Foundation, and Apricity. Its goal was to develop the federated learning framework (Owkin Connect) and to train predictive models in oncology (breast cancer and melanoma) and fertility. This is a public-private consortium with a €10M budget funded by Banque Publique d’Investissement. This initial partnership formed the basis of Healthchain. All four leaders brought expertise and commitment, which were essential to the project. Guillaume Bataillon, a pathologist at Institut Curie, orchestrated the gathering of data from hundreds of breast cancer patients. Pierre-Etienne Heudel, oncologist, and Dr. In addition, the two co-principal investigators: Dr. This project was driven by visionary leaders: Thierry Durand (Director of IT at CLB) and Alain Livartowksi MD, (Deputy Head of the Data Department at Institut Curie). The prognosis for this disease is poor and typical treatments are of limited efficacy. Together, Owkin, CLB, and Institut Curie decided to investigate breast cancer because of its incidence, specifically triple-negative breast cancer. (A federation of French medical centers that are pioneering cancer research and improving patient care). Thus, Owkin turned to its internationally-renowned partners CLB and Institut Curie, both part of UNICANCER. To implement federated learning, we needed to identify two or more medical centers with curated datasets of similar data types. In this article, we outline a roadmap for how we got here and what we learned along the way. It is also an example of outstanding collaboration and an empowering conclusion to our journey. This proof-of-concept for federated learning via Owkin Connect is a remarkable technical triumph. The path to this incredible achievement was not straightforward however, it was full of many discoveries and valuable lessons. Additionally, two datasets and more than 40 talented and dedicated people from Owkin, Centre Léon Bérard (‘CLB’), and Institut Curie) contributed to this success. This model was a proof-of-concept for “Connect”. In January 2020, Connect enabled the first-ever federated deep learning model (‘Model’) trained on distributed histology images stored behind hospital firewalls. It enables distributed machine learning training without aggregating or collecting private data. This innovative software is our proprietary federated learning framework that ‘connects’ multiple data sources. In doing this, we connect medical researchers, biopharma companies, and data scientists in a collaborative, privacy-preserving Data Platform.Īccess to large-scale, meaningful medical data is a significant challenge in healthcare. As a result, Owkin has dedicated three years of R&D to develop Owkin Connect (‘Connect’). At Owkin, our mission is to fuse AI and clinical research to unlock medical discoveries.
0 Comments
Leave a Reply. |