Pittsburgh Uni, Owkin to use federated learning technologies in healthcare research

SOURCE: Malachi Jacobs /
University of Pittsburgh partners with Owkin to use AI and federated learning technologies to form new clinical insights.

By U2B Staff 

Read all stories

The University of Pittsburgh has entered a collaboration with Owkin, a start-up that deploys artificial intelligence (AI) and Federated Learning technologies to augment medical research and enable scientific discoveries.

This partnership will combine Owkin’s pioneering technologies and research platform with the university’s expertise with the goal to advance clinical research and drug development.

This goal can be achieved by leveraging on the high-quality datasets and world-class medical research from the university’s Department of Biomedical Informatics and Pathology.


Through this partnership, the university will join the Owkin Loop, a federated network of US and European academic medical centres 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.

The insights that are generated by Loop can inform pharmaceutical drug development strategy, from biomarker discovery to clinical trial design, and product differentiation.

The start-up aims to revolutionise medicine by establishing federated learning at the core of future research.

The use of federated learning technologies will enable researchers in different institutions and different locations to collaborate and train multicentric AI models using the same datasets.
This approach results in better predictive performance and higher generalisability.

Owkin is a pioneer of Federated Learning technologies. This technology uses a decentralised analysis approach that protects patient data by ensuring that it never leaves the hospital.

Through this technology, only the algorithms and not the data is transferred, which protects the institution’s data governance and privacy.

Owkin’s use of data also complies with ethical body consent processes and data compliance regulations.


Head of Partnerships at Owkin, Meriem Sefta expressed excitement at this partnership, “We’re thrilled to launch this project with Dr Becich and his team at Pitt. The quality and size of the university’s research cohorts in combination with the DBMI’s mandate to bring together healthcare physicians and innovative academics to work on some of the most cutting-edge science makes this collaboration a great opportunity to develop predictive AI models and to scale other research in the future.”

Sefta added that the start-up is proud to bring its expertise in machine learning technologies and data scientists to the table to foment new clinical insights.