University of Pittsburgh Joins Disruptive AI-based Federated Learning Network to Advance Clinical Research

Mar 9, 2020 | AI, Artificial Intelligence, Federated Learning Technologies, Machine Learning, Owkin, University of Pittsburgh

University of Pittsburgh Joins Disruptive AI-based Federated Learning Network to Advance Clinical Research

The University of Pittsburgh has partnered with AI and Federated Learning technologies startup to help augment medical research and enable scientific discoveries. In first establishing a pilot agreement, the University of Pittsburgh will leverage its own high-quality datasets world-class medical research within its Departments of Biomedical Informatics and Pathology and Owkin’s pioneering technologies and research platform to in combination, advance clinical research and drug development. Increasingly, clinical and medical research will require a combination of externalization along with disruptive technologies.

New Innovative Partnerships Externalize

Advancing innovation in drug discovery and development requires continuously thinking out-of-the-box and externalizing know-how, technology, and insight, and this recently announced partnership evidences this trend. In this case, the prestigious university and the startup will team to develop and validate prognostic machine learning models. Upon progress within a pilot, the initiative can potentially expand into several key therapeutic areas for the university.

On this promising partnership, the University of Pittsburgh—involving the institution’s Biomedical Informatics in partnership with the Department of Pathology—commits to “improving biomedical research and clinical care through the innovative application of informatics and best practices in next-generation data sharing. This collaboration with Owkin will expand our innovations in the computational pathology space,” reported Dr. Michael Becich.

Joining the Owkin Loop

This partnership makes it possible for the University of Pittsburgh to join the Owkin Loop, a federated network of U.S. and European academic medical centers that collaborate with Owkin to generate new insights from high-quality, curated, research-grade, multi-modal patient data captured in clinical trials or research cohorts. Loop generated insights can inform pharmaceutical drug development strategy, from biomarker discovery, to clinical trial design, and product differentiation. In this way, Owkin is on a mission to create a movement in medicine by establishing federated learning at the core of future research.

What are Federated Learning Technologies?

Federated learning technologies enable researchers in different institutions and different geographies to collaborate and train multicentric AI models on heterogeneous datasets, resulting in better predictive performance and higher generalizability. Data does not move, only the algorithms travel, thus protecting the institution’s data governance and privacy. In this way, Owkin offers a breakthrough offering a private and secure machine learning framework. Moreover, Owkin’s data use is compliant with local ethical body consent processes and data compliance regulations such as HIPAA and GDPR. 

Profiling Recent Discoveries

Forthcoming at HIMSS 2020, Owkin is presenting their recent discoveries at HIMSS 2020 in Orlando, Florida, on March 10th, 2:45 PM EDT. Owkin’s staff will showcase opportunities to transform medical research with a Federated AI Learning platform.

About Owkin

Owkin specializes in artificial intelligence technologies applied to clinical research. It was Co-founded in 2016 by Thomas Clozel—a hematologist, oncologist, and researcher, and Gilles Wainrib—a computer science teacher-researcher at the École Normale Supérieure, and a Stanford University Postdoc. Owkin enables researchers to use data from health care or research activities to train interpretable machine learning models. These models allow a better prediction of patient prognosis and response to treatment, developing new generations of biomarkers. In October 2019, Owkin published its breakthrough analysis of tumor biology using an interpretable deep-learning model, called MesoNet, in Nature Medicine

Founded in 2016, the firm has already raised over $18 million in venture capital funds led by investor F-Prime Capital. Owkin has grown to about 100 employees in just a few years.

Lead Research/Investigators

Michael Becich, MD, Ph.D., Associate Vice Chancellor for Informatics, Health Sciences and Chairman and Distinguished University Professor, Department of Biomedical Informatics (DBMI)

Call to Action: Interested in learning more about Owkin and how to partner with them? See the link for HIMSS.

0 Comments

Pin It on Pinterest