PuSH - Publikationsserver des Helmholtz Zentrums München

Warnat-Herresthal, S.* ; Schultze, H.* ; Shastry, K.L.* ; Manamohan, S.* ; Mukherjee, S.* ; Garg, V.* ; Sarveswara, R.* ; Händler, K.* ; Pickkers, P.* ; Aziz, N.A.* ; 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.* ; Altmüller, J.* ; Mishra, N.* ; Bernardes, J.P.* ; Krämer, B.F.* ; Bonaguro, L.* ; Schulte-Schrepping, J.* ; De Domenico, E.* ; Siever, C.* ; Kraut, M.* ; Desai, M.* ; Monnet, B.* ; Saridaki, M.* ; Siegel, C.M.* ; Drews, A.* ; Nuesch-Germano, M.* ; Theis, H.* ; Heyckendorf, J.* ; Schreiber, S.* ; Kim-Hellmuth, S.* ; Nattermann, J.* ; Skowasch, D.* ; Kurth, I.* ; Keller, A.* ; Bals, R.* ; Nürnberg, P.* ; Rieß, O.* ; Rosenstiel, P.* ; Netea, M.G.* ; Theis, F.J. ; Backes, M.* ; Aschenbrenner, A.C.* ; Ulas, T.* ; Deutsche COVID-19 Omics Initiative (DeCOI) (De La Rosa Velázquez, I.A.) ; Breteler, M.M.B.* ; Giamarellos-Bourboulis, E.J.* ; Kox, M.* ; Beck, M.* ; Cheran, S.* ; Woodacre, M.S.* ; Lim Goh, E.* ; Schultze, J.L.*

Swarm Learning for decentralized and confidential clinical machine learning.

Nature (2021)
Verlagsversion DOI
Open Access Gold (Paid Option)
Creative Commons Lizenzvertrag
Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine . Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes . However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation . 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. 1,2 3 4,5
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Privacy; Classification; Cloud
ISSN (print) / ISBN 0028-0836
e-ISSN 1476-4687
Zeitschrift Nature
Verlag Nature Publishing Group
Verlagsort London
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)
Molekulare Endokrinologie und Metabolismus (MEM)
Förderungen COVIM: NaFoUniMedCovid19
Hellenic Institute for the Study of Sepsis
HGF Incubator
FrameWork 7 programme HemoSpec
Horizon2020 Marie-Curie Project European Sepsis Academy
Saarland University
German Research Foundation (DFG) under Germany's Excellence Strategy
HGF Helmholtz AI grant Pro-Gene-Gen
Hector foundation
Staatskanzlei des Saarlandes
Spinoza Grant of the Netherlands Organization for Scientific Research
ERC Advanced Grant
Michael J. Fox Foundation for Parkinson' Research
Hector Fellow Academy
Care-for-Rare Foundation
Horizon 2020 European Grant ImmunoSep
German Research Foundation (DFG)