Accelerating artificial intelligence: How federated learning can protect privacy, facilitate collaboration, and improve outcomes

Authors

Malhar Patel, Rhino Health, Boston, MA, USA.
Ittai Dayan, Rhino Health, Boston, MA, USA.
Elliot K. Fishman, The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Department of Oncology, Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
Mona Flores, NVIDIA, Santa Clara, CA, USA.
Fiona J. Gilbert, Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge, Cambridge, CB, USA.
Michal Guindy, Assuta Medical Centers, Tel Aviv, Israel; BGU University Israel, Beer-Sheva, Israel.
Eugene J. Koay, Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Michael Rosenthal, Dana-Farber Cancer Institute, Boston, MA, USA; Brigham & Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.
Holger R. Roth, NVIDIA, Santa Clara, CA, USA.
Marius G. Linguraru, Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, USA; Departments of Radiology and Pediatrics, The George Washington University School of Medicine and Health Sciences, Washington, DC, USA.

Document Type

Journal Article

Publication Date

1-1-2023

Journal

Health informatics journal

Volume

29

Issue

4

DOI

10.1177/14604582231207744

Keywords

IT healthcare evaluation; clinical decision-making; cloud computing; collaborative work practices and IT; data security and confidentiality; databases and data mining; decision-support systems; machine learning; medical imaging; privacy

Abstract

Cross-institution collaborations are constrained by data-sharing challenges. These challenges hamper innovation, particularly in artificial intelligence, where models require diverse data to ensure strong performance. Federated learning (FL) solves data-sharing challenges. In typical collaborations, data is sent to a central repository where models are trained. With FL, models are sent to participating sites, trained locally, and model weights aggregated to create a master model with improved performance. At the 2021 Radiology Society of North America's (RSNA) conference, a panel was conducted titled "Accelerating AI: How Federated Learning Can Protect Privacy, Facilitate Collaboration and Improve Outcomes." Two groups shared insights: researchers from the EXAM study (EMC CXR AI Model) and members of the National Cancer Institute's Early Detection Research Network's (EDRN) pancreatic cancer working group. EXAM brought together 20 institutions to create a model to predict oxygen requirements of patients seen in the emergency department with COVID-19 symptoms. The EDRN collaboration is focused on improving outcomes for pancreatic cancer patients through earlier detection. This paper describes major insights from the panel, including direct quotes. The panelists described the impetus for FL, the long-term potential vision of FL, challenges faced in FL, and the immediate path forward for FL.

APA Citation

Patel, Malhar; Dayan, Ittai; Fishman, Elliot K.; Flores, Mona; Gilbert, Fiona J.; Guindy, Michal; Koay, Eugene J.; Rosenthal, Michael; Roth, Holger R.; and Linguraru, Marius G., "Accelerating artificial intelligence: How federated learning can protect privacy, facilitate collaboration, and improve outcomes" (2023). GW Authored Works. Paper 3659.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/3659

Department

Radiology