Federated learning: A solution to AI’s data-sharing challenges

Federated learning can solve data-sharing challenges, allowing nimble collaboration across institutions to drive medical advances using artificial intelligence (AI), according to a new manuscript from 10 thought leaders in AI and machine learning in medicine.

In Health Informatics Journal, these leading experts on how technology is shaping medicine shared a conversation that they had at the Radiology Society of North America’s conference. They weighed challenges facing AI, including barriers to data sharing because of privacy rules that prevent the distribution of information to different institutions. With federated learning, models are shared – rather than data – allowing institutions to aggregate information and collaborate with a master model.

“Federated learning offers tremendous promise,” said Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor of Research and Innovation, principal investigator at the Sheikh Zayed Institute of Pediatric Surgical Innovation and senior author on the manuscript. “As a community of experts, we have found that federated learning allows us to move away from the challenges of sharing data in central repositories. Instead, we share the models, which can be designed to protect privacy by limiting what’s shared outside of any given institution.”

A champion of pediatric health, Linguraru wants to ensure that children are represented in the development of models that advance science and medicine. “Sharing data is even more crucial when there are few patients, such as in rare diseases or pediatric populations,” he said. “In general, healthcare data suffers from inequitable representation in our public health systems and services.”

Learn more here about the challenges and potential solutions from experts at Rhino Health, Johns Hopkins University School of Medicine, NVIDIA, University of Cambridge, Ben-Gurion University Israel, MD Anderson Cancer Center, Dana-Farber Cancer Institute and Children’s National Hospital.