TY - JOUR
T1 - Swarm Learning for decentralized and confidential clinical machine learning
AU - COVID-19 Aachen Study (COVAS)
AU - Deutsche COVID-19 Omics Initiative (DeCOI)
AU - Warnat-Herresthal, Stefanie
AU - Schultze, Hartmut
AU - Shastry, Krishnaprasad Lingadahalli
AU - Manamohan, Sathyanarayanan
AU - Mukherjee, Saikat
AU - Garg, Vishesh
AU - Sarveswara, Ravi
AU - Händler, Kristian
AU - Pickkers, Peter
AU - Aziz, N. Ahmad
AU - Ktena, Sofia
AU - Tran, Florian
AU - Bitzer, Michael
AU - Ossowski, Stephan
AU - Casadei, Nicolas
AU - Herr, Christian
AU - Petersheim, Daniel
AU - Behrends, Uta
AU - Kern, Fabian
AU - Fehlmann, Tobias
AU - Schommers, Philipp
AU - Lehmann, Clara
AU - Augustin, Max
AU - Rybniker, Jan
AU - Altmüller, Janine
AU - Mishra, Neha
AU - Bernardes, Joana P.
AU - Krämer, Benjamin
AU - Bonaguro, Lorenzo
AU - Schulte-Schrepping, Jonas
AU - De Domenico, Elena
AU - Siever, Christian
AU - Kraut, Michael
AU - Desai, Milind
AU - Monnet, Bruno
AU - Saridaki, Maria
AU - Siegel, Charles Martin
AU - Drews, Anna
AU - Nuesch-Germano, Melanie
AU - Theis, Heidi
AU - Heyckendorf, Jan
AU - Schreiber, Stefan
AU - Kim-Hellmuth, Sarah
AU - Balfanz, Paul
AU - Eggermann, Thomas
AU - Boor, Peter
AU - Hausmann, Ralf
AU - Theis, Fabian
AU - Gagneur, Julien
AU - Protzer, Ulrike
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/6/10
Y1 - 2021/6/10
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85106583195&partnerID=8YFLogxK
U2 - 10.1038/s41586-021-03583-3
DO - 10.1038/s41586-021-03583-3
M3 - Article
C2 - 34040261
AN - SCOPUS:85106583195
SN - 0028-0836
VL - 594
SP - 265
EP - 270
JO - Nature
JF - Nature
IS - 7862
ER -