Plate IV.287 · Publications
Swarm Learning for decentralized and confidential clinical machine learning
Article in Nature, 26 May 2021.
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.
Versions2
- PublishedNature10.1038/s41586-021-03583-3
- PreprintbioRxiv10.1101/2020.06.25.171009
Cite
@article{warnatherresthal2021swarm,
title = {{Swarm Learning for decentralized and confidential clinical machine learning}},
author = {Warnat-Herresthal, Stefanie and Schultze, Hartmut and Shastry, Krishnaprasad Lingadahalli and Manamohan, Sathyanarayanan and Mukherjee, Saikat and Garg, Vishesh and Sarveswara, Ravi and Händler, Kristian and Pickkers, Peter and Aziz, N. Ahmad and Ktena, Sofia and Tran, Florian and Bitzer, Michael and Ossowski, Stephan and Casadei, Nicolas and Herr, Christian and Petersheim, Daniel and Behrends, Uta and Kern, Fabian and Fehlmann, Tobias and Schommers, Philipp and Lehmann, Clara and Augustin, Max and Rybniker, Jan and Altmüller, Janine and Mishra, Neha and Bernardes, Joana P. and Krämer, Benjamin and Bonaguro, Lorenzo and Schulte-Schrepping, Jonas and De Domenico, Elena and Siever, Christian and Kraut, Michael and Desai, Milind and Monnet, Bruno and Saridaki, Maria and Siegel, Charles Martin and Drews, Anna and Nuesch-Germano, Melanie and Theis, Heidi and Heyckendorf, Jan and Schreiber, Stefan and Kim-Hellmuth, Sarah and COVID-19 Aachen Study (COVAS) and Balfanz, Paul and Eggermann, Thomas and Boor, Peter and Hausmann, Ralf and Kuhn, Hannah and Isfort, Susanne and Stingl, Julia Carolin and Schmalzing, Günther and Kuhl, Christiane K. and Röhrig, Rainer and Marx, Gernot and Uhlig, Stefan and Dahl, Edgar and Müller-Wieland, Dirk and Dreher, Michael and Marx, Nikolaus and Nattermann, Jacob and Skowasch, Dirk and Kurth, Ingo and Keller, Andreas and Bals, Robert and Nürnberg, Peter and Rieß, Olaf and Rosenstiel, Philip and Netea, Mihai G. and Theis, Fabian and Mukherjee, Sach and Backes, Michael and Aschenbrenner, Anna C. and Ulas, Thomas and Deutsche COVID-19 Omics Initiative (DeCOI) and Angelov, Angel and Bartholomäus, Alexander and Becker, Anke and Bezdan, Daniela and Blumert, Conny and Bonifacio, Ezio and Bork, Peer and Boyke, Bunk and Blum, Helmut and Clavel, Thomas and Colome-Tatche, Maria and Cornberg, Markus and De La Rosa Velázquez, Inti Alberto and Diefenbach, Andreas and Dilthey, Alexander and Fischer, Nicole and Förstner, Konrad and Franzenburg, Sören and Frick, Julia-Stefanie and Gabernet, Gisela and Gagneur, Julien and Ganzenmueller, Tina and Gauder, Marie and Geißert, Janina and Goesmann, Alexander and Göpel, Siri and Grundhoff, Adam and Grundmann, Hajo and Hain, Torsten and Hanses, Frank and Hehr, Ute and Heimbach, André and Hoeper, Marius and Horn, Friedemann and Hübschmann, Daniel and Hummel, Michael and Iftner, Thomas and Iftner, Angelika and Illig, Thomas and Janssen, Stefan and Kalinowski, Jörn and Kallies, René and Kehr, Birte and Keppler, Oliver T. and Klein, Christoph and Knop, Michael and Kohlbacher, Oliver and Köhrer, Karl and Korbel, Jan and Kremsner, Peter G. and Kühnert, Denise and Landthaler, Markus and Li, Yang and Ludwig, Kerstin U. and Makarewicz, Oliwia and Marz, Manja and McHardy, Alice C. and Mertes, Christian and Münchhoff, Maximilian and Nahnsen, Sven and Nöthen, Markus and Ntoumi, Francine and Overmann, Jörg and Peter, Silke and Pfeffer, Klaus and Pink, Isabell and Poetsch, Anna R. and Protzer, Ulrike and Pühler, Alfred and Rajewsky, Nikolaus and Ralser, Markus and Reiche, Kristin and Ripke, Stephan and da Rocha, Ulisses Nunes and Saliba, Antoine-Emmanuel and Sander, Leif Erik and Sawitzki, Birgit and Scheithauer, Simone and Schiffer, Philipp and Schmid-Burgk, Jonathan and Schneider, Wulf and Schulte, Eva-Christina and Sczyrba, Alexander and Sharaf, Mariam L. and Singh, Yogesh and Sonnabend, Michael and Stegle, Oliver and Stoye, Jens and Vehreschild, Janne and Velavan, Thirumalaisamy P. and Vogel, Jörg and Volland, Sonja and von Kleist, Max and Walker, Andreas and Walter, Jörn and Wieczorek, Dagmar and Winkler, Sylke and Ziebuhr, John and Breteler, Monique M. B. and Giamarellos-Bourboulis, Evangelos J. and Kox, Matthijs and Becker, Matthias and Cheran, Sorin and Woodacre, Michael S. and Goh, Eng Lim and Schultze, Joachim L.},
journal = {Nature},
publisher = {Springer Science and Business Media LLC},
year = {2021},
month = may,
doi = {10.1038/s41586-021-03583-3},
url = {https://doi.org/10.1038/s41586-021-03583-3},
pmid = {34040261},
pmcid = {PMC8189907}
}