Swarm Learning for decentralized and confidential clinical machine learning

Stefanie Warnat-Herresthal, Hartmut Schultze, Krishnaprasad Lingadahalli Shastry, Sathyanarayanan Manamohan, Saikat Mukherjee, Vishesh Garg, Ravi Sarveswara, Kristian Händler, Peter Pickkers, N. Ahmad Aziz, Sofia Ktena, Florian Tran, Michael Bitzer, Stephan Ossowski, Nicolas Casadei, Christian Herr, Daniel Petersheim, Uta Behrends, Fabian Kern, Tobias Fehlmann, Philipp Schommers, Clara Lehmann, Max Augustin, Jan Rybniker, Janine Altmüller, Neha Mishra, Joana P. Bernardes, Benjamin Krämer, Lorenzo Bonaguro, Jonas Schulte-Schrepping, Elena Domenico, Christian Siever, Michael Kraut, Milind Desai, Bruno Monnet, Maria Saridaki, Charles Martin Siegel, Anna Drews, Melanie Nuesch-Germano, Heidi Theis, Jan Heyckendorf, Stefan Schreiber, Sarah Kim-Hellmuth, Jacob Nattermann, Dirk Skowasch, Ingo Kurth, Andreas Keller, Robert Bals, Peter Nürnberg, Olaf Rieß, Philip Rosenstiel, Mihai G. Netea, Fabian Theis, Sach Mukherjee, Michael Backes, Anna C. Aschenbrenner, Thomas Ulas, Monique M. B. Breteler, Evangelos J. Giamarellos-Bourboulis, Matthijs Kox, Matthias Becker, Sorin Cheran, Michael S. Woodacre, Eng Lim Goh and Joachim L. Schultze ()
Additional contact information
Stefanie Warnat-Herresthal: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Hartmut Schultze: Hewlett Packard Enterprise
Krishnaprasad Lingadahalli Shastry: Hewlett Packard Enterprise
Sathyanarayanan Manamohan: Hewlett Packard Enterprise
Saikat Mukherjee: Hewlett Packard Enterprise
Vishesh Garg: Hewlett Packard Enterprise
Ravi Sarveswara: Hewlett Packard Enterprise
Kristian Händler: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Peter Pickkers: Radboud University Medical Center
N. Ahmad Aziz: Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Sofia Ktena: National and Kapodistrian University of Athens, Medical School
Florian Tran: Christian-Albrechts-University and University Hospital Schleswig-Holstein
Michael Bitzer: University Hospital, University of Tübingen
Stephan Ossowski: University of Tübingen
Nicolas Casadei: University of Tübingen
Christian Herr: Saarland University Hospital
Daniel Petersheim: University Hospital LMU Munich
Uta Behrends: Technical University Munich
Fabian Kern: Saarland University
Tobias Fehlmann: Saarland University
Philipp Schommers: Faculty of Medicine and University Hospital of Cologne, University of Cologne
Clara Lehmann: Faculty of Medicine and University Hospital of Cologne, University of Cologne
Max Augustin: Faculty of Medicine and University Hospital of Cologne, University of Cologne
Jan Rybniker: Faculty of Medicine and University Hospital of Cologne, University of Cologne
Janine Altmüller: University of Cologne
Neha Mishra: Christian-Albrechts-University and University Hospital Schleswig-Holstein
Joana P. Bernardes: Christian-Albrechts-University and University Hospital Schleswig-Holstein
Benjamin Krämer: Clinical Infectious Diseases, Research Center Borstel and German Center for Infection Research (DZIF), Partner Site Hamburg-Lübeck-Borstel-Riems
Lorenzo Bonaguro: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Jonas Schulte-Schrepping: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Elena Domenico: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Christian Siever: Hewlett Packard Enterprise
Michael Kraut: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Milind Desai: Hewlett Packard Enterprise
Bruno Monnet: Hewlett Packard Enterprise
Maria Saridaki: National and Kapodistrian University of Athens, Medical School
Charles Martin Siegel: Hewlett Packard Enterprise
Anna Drews: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Melanie Nuesch-Germano: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Heidi Theis: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Jan Heyckendorf: Clinical Infectious Diseases, Research Center Borstel and German Center for Infection Research (DZIF), Partner Site Hamburg-Lübeck-Borstel-Riems
Stefan Schreiber: Christian-Albrechts-University and University Hospital Schleswig-Holstein
Sarah Kim-Hellmuth: University Hospital LMU Munich
Jacob Nattermann: University Hospital Bonn
Dirk Skowasch: University of Bonn
Ingo Kurth: RWTH Aachen University
Andreas Keller: Saarland University
Robert Bals: Saarland University Hospital
Peter Nürnberg: University of Cologne
Olaf Rieß: University of Tübingen
Philip Rosenstiel: Christian-Albrechts-University and University Hospital Schleswig-Holstein
Mihai G. Netea: Radboud University Medical Center
Fabian Theis: Helmholtz Center Munich (HMGU)
Sach Mukherjee: Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Michael Backes: CISPA Helmholtz Center for Information Security
Anna C. Aschenbrenner: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Thomas Ulas: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Monique M. B. Breteler: Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Evangelos J. Giamarellos-Bourboulis: National and Kapodistrian University of Athens, Medical School
Matthijs Kox: Radboud University Medical Center
Matthias Becker: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)
Sorin Cheran: Hewlett Packard Enterprise
Michael S. Woodacre: Hewlett Packard Enterprise
Eng Lim Goh: Hewlett Packard Enterprise
Joachim L. Schultze: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)

Nature, 2021, vol. 594, issue 7862, 265-270

Abstract: Abstract Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning—a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41586-021-03583-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:594:y:2021:i:7862:d:10.1038_s41586-021-03583-3

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-021-03583-3

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().