Swarm Learning for decentralized and confidential clinical machine learning

Warnat-Herresthal S, Schultze H, Shastry KL, Manamohan S, Mukherjee S, Garg V, Sarveswara R, Haendler K, Pickkers P, Aziz NA, Ktena S, Tran F, Bitzer M, Ossowski S, Casadei N, Herr C, Petersheim D, Behrends U, Kern F, Fehlmann T, Schommers P, Lehmann C, Augustin M, Rybniker J, Altmueller J, Mishra N, Bernardes JP, Kraemer B, Bonaguro L, Schulte-Schrepping J, De Domenico E, Siever C, Kraut M, Desai M, Monnet B, Saridaki M, Siegel CM, Drews A, Nuesch-Germano M, Theis H, Heyckendorf J, Schreiber S, Kim-Hellmuth S, Nattermann J, Skowasch D, Kurth I, Keller A, Bals R, Nuernberg P, Riess O, Rosenstiel P, Netea MG, Theis F, Mukherjee S, Backes M, Aschenbrenner AC, Ulas T, Breteler MMB, Giamarellos-Bourboulis EJ, Kox M, Becker M, Cheran S, Woodacre MS, Goh EL, Schultze JL (2021)

Publication Type: Journal article

Publication year: 2021

Journal

Book Volume: 594

Pages Range: 265-270

Journal Issue: 7862

DOI: 10.1038/s41586-021-03583-3

Abstract

Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine^1,2. 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 legislation^4,5. 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.

Involved external institutions

Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE) Germany (DE) Hewlett Packard Enterprise Company (HPE) United States (USA) (US) Radboud University Nijmegen Medical Centre / Radboudumc of voluit Radboud Universitair Medisch Centrum (UMC) Netherlands (NL) National and Kapodistrian University of Athens Greece (GR) Christian-Albrechts-Universität zu Kiel Germany (DE) Eberhard Karls Universität Tübingen Germany (DE) Universitätsklinikum des Saarlandes (UKS) Germany (DE) Ludwig-Maximilians-Universität (LMU) Germany (DE) Universität des Saarlandes (UdS) Germany (DE) Technische Universität München (TUM) Germany (DE) Universität zu Köln Germany (DE) Forschungszentrum Borstel - Leibniz-Zentrum für Medizin und Biowissenschaften / Research Center Borstel - Leibniz-Center for Medicine and Biosciences Germany (DE) Universitätsklinikum Bonn Germany (DE) Rheinische Friedrich-Wilhelms-Universität Bonn Germany (DE) Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen Germany (DE) Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (HMGU) / Helmholtz Munich Germany (DE) CISPA − Helmholtz-Zentrum für Informationssicherheit Germany (DE)

How to cite

APA:

Warnat-Herresthal, S., Schultze, H., Shastry, K.L., Manamohan, S., Mukherjee, S., Garg, V.,... Schultze, J.L. (2021). Swarm Learning for decentralized and confidential clinical machine learning. Nature, 594(7862), 265-270. https://doi.org/10.1038/s41586-021-03583-3

MLA:

Warnat-Herresthal, Stefanie, et al. "Swarm Learning for decentralized and confidential clinical machine learning." Nature 594.7862 (2021): 265-270.

BibTeX: Download