Owkin Manifesto: A new frontier of medical research
Owkin Manifesto: A new frontier of medical research
As the world responds to COVID-19, speed, and collaboration in clinical research has never been more important. Our collective race to understand and discover treatments for this threat to society offers unprecedented opportunities to improve the field of medical research from every angle.
We are fully engaged in this new frontier with the goal of improving drug development and patient outcomes. Founded in 2016, Owkin has quickly emerged as a leader in bringing Artificial Intelligence (AI) and Machine Learning (ML) technologies to the healthcare industry. Our solutions improve the traditional medical research paradigm. They turn a previously siloed, disjointed system into an innovative and collaborative one that, above all, puts the privacy of patients first.
The Power of Federated Learning
Owkin serves researchers in hospitals, universities and biotech companies. We aim to help them understand why drug efficacy varies from patient to patient, enhance the drug development process and identify the best drug for the right patient at the right time, to improve treatment outcomes.
How do we do it? We believe that achieving the most accurate view of patient treatment requires collaboration that is both inclusive and secure. To that end, Owkin is assembling a global research network powered by federated learning, a framework for AI model development that enables us to train ML models on distributed data at scale across multiple medical institutions without centralizing the data.
Through decentralized ML and AI, we enable researchers to draw insights from millions of patients’ multimodal data points, while keeping patient data local – preserved safely within the hospital’s local security infrastructure. Our Federated Learning software, Owkin Connect, enables an unprecedented breadth of collaboration for life science companies while protecting patient privacy and ensuring compliance.
The result: an acceleration of the clinical research process that offers protected data for patients, exhaustive traceability of computations for institutions, maximum collaboration for researchers, and predictive power for data scientists.
We Believe In Connections.
Collaborative Research: Owkin federated learning technologies connect researchers.
Working in concert with academic centers and researchers, we deploy infrastructure, prepare data, train predictive models, validate results, and co-publish our collective findings in top scientific journals.
We coordinate and power federated learning projects including:
MELLODDY, a pharma consortium that trains machine learning on chemical libraries from ten major European pharmaceutical companies and six other technical and research partners, which receive funding from the EU’s Innovative Medicines Initiative 2 Joint Undertaking
Two leading academic consortia: Healthchain in France (partners include The Institut Curie, Assistance Publique-Hôpitaux de Paris, Nantes University Hospital Center and The Centre Léon Bérard), with first projects focusing on melanoma and breast cancer; and AI4VBH in London (including Kings College London and Nvidia among other partners), with an early focus on cancer, heart failure, dementia and stroke
Through these projects, each institution maintains governance of its own data and privacy for its own individual scientific question, while benefiting from the predictive models trained on datasets of members. The results are more powerful predictive models for better insights, and ultimately, more impactful medical discoveries.
AI & Biology: Owkin ML technologies connect the dots between raw medical data and ultimate patient outcomes.
In search of more effective and targeted treatments, the pharmaceutical industry is analyzing human biology at an unprecedented speed, scale, and level of accuracy. Owkin believes that the patient is the most critical factor in this research: the truth will emerge from patient data.
AI enables researchers to uncover precise insights and identify complex relationships within immense amounts of data. By combining our unprecedented access to expertly-curated large sets of data to feed AI with our proprietary multimodal AI technologies, we enable researchers to integrate a wide and dynamic range of medical data, interpret results, and make scientific discoveries that accelerate drug development and improve patient outcomes.
Data Protection & Acceleration of Medical Research: Owkin federated learning technologies connect datasets securely.
Owkin balances patient privacy and data protection, in compliance with government regulations.
This drives all of our activities at Owkin, differentiating us as we complement the standard approach of centralizing data from multiple centers, across multiple geographies.
Owkin safeguards patient data.
All data remains protected and adheres to data governance frameworks enabling strict control over each participating institution’s data. Our federating learning architecture is statistically equivalent to the traditional pooled model for predictive power while offering improved privacy for patients and compliance with data ownership.
Owkin leverages data for research.
The true power of federated learning lies in unlocking all datasets as widely as possible within a secure architecture, thus maximizing the potential to contribute to groundbreaking medical discovery.