Swarm Learning for decentralized and confidential clinical machine learning
Open accessPublished version of a preprint
The DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index; 9 of the 25 sources its claims cite were checked for support.
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 transcriptomes 3 . 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.
Overview
CoChat Summary
TL;DR
Swarm Learning (SL) is a decentralized machine-learning approach that combines edge computing, permissioned blockchain peer-to-peer networking, and coordination without a central parameter server, preserving confidentiality by design. Across four disease use cases—leukaemia, tuberculosis, COVID-19, and lung pathologies—SL classifiers trained on distributed data outperformed classifiers developed at individual sites and were close to or equivalent to centralized models.
Key findings
- Using more than 16,400 blood transcriptomes from 127 clinical studies and more than 95,000 chest X-ray images, SL outperformed individual nodes across leukaemia, tuberculosis, COVID-19, and lung pathology use cases; central models were only slightly better or equivalent in several scenarios.
- In leukaemia PBMC datasets A1–A3, comprising more than 12,000 individuals, SL outperformed each node across multiple scenarios, including uneven case/control distributions, study-specific siloing, different transcriptomic technologies, up to 32 nodes, and LASSO instead of deep neural networks.
- For tuberculosis, SL outperformed individual nodes even when training samples were reduced by 50% or split into six smaller nodes; for COVID-19, SL outperformed all nodes in AUC on global test datasets and predicted samples from other centres when individual centre nodes could not.
- Overall, 16,694 analyses were performed across 26 AML, 4 ALL, 13 TB, 1 X-ray, and 18 COVID-19 scenarios, with 5–100 permutations per scenario and a total of 8,347 computer hours.
Methods
- Design: decentralized SL framework using edge nodes and a permissioned blockchain for secure onboarding, dynamic leader election, and parameter merging, with no central parameter server; raw data remain local and model parameters are exchanged and merged.
- Data: PBMC transcriptome datasets A1 (n = 2,500), A2 (n = 8,348), and A3 (n = 1,181); whole-blood datasets B (n = 1,999), D (n = 2,143), and E (n = 2,400); chest X-ray dataset C (95,831 images); simulations used 3–32 training nodes and independent test nodes.
- Analysis: deep neural network (Keras sequential) and LASSO; performance metrics included sensitivity, specificity, accuracy, F1 score, and AUC; differences were tested with one-sided Wilcoxon signed-rank test with continuity correction, using 5–100 permutations per scenario.
Limitations
- Stated: no statistical methods were used to predetermine sample size; experiments were not randomized, although permutations were performed; investigators were not blinded to allocation during experiments and outcome assessment.
- Stated/implied: SL performance was tested in simulated siloing and outbreak scenarios using existing datasets, not in a prospective real-world multi-centre clinical deployment; the paper notes potential limitations in TB outbreak scenarios but does not quantify them.
- Evident: although confidentiality is preserved by design and no raw data are exchanged, model parameters are shared; the paper suggests SL can inherit differential privacy, functional encryption, or encrypted transfer learning, but these were not implemented or tested here.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures














Verification
Claims the paper makes
6 Valid · 0 Not valid · 7 Not checked · 58 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As medicine is inherently decentral, the volume of local data is often insufficient to train reliable classifiers20,21.”
§ Swarm Learning for decentralized and confidential clinical machine learning > Main
What the sources say
- Not checked yetcites [20] Rajkomar, A., Dean, J. & Kohane, I. Machine learning in medicine. N. Engl. J. Med. 380, 1347–1358 (2019). source
- Partly supportedcites [21] Savage, N. Calculating disease. Nature 550, S115–S117 (2017). sourceExperimental — accuracy not yet measured
In “BIOPSY BY NUMBERS” (page unavailable), the paper says a researcher wants a much larger dataset to validate and refine an ALS classification algorithm, and describes a shared MRI repository assembled to provide larger datasets. It does not say that medicine is inherently decentralized or that local datasets are often insufficient to train reliable classifiers; it also reports good predictions from a relatively small dataset. (LLM, conf=0.78)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“With increasing efforts to enforce data privacy and security5,9,10 and to reduce data traffic and duplication, a decentralized data model will become the preferred choice for handling, storing, managing, and analysing any kind of large medical dataset19.”
§ Swarm Learning for decentralized and confidential clinical machine learning > Discussion
What the sources say
- Partly supportedcites [19] Kaissis, G. A., Makowski, M. R., Rückert, D. & Braren, R. F. Secure, privacy-preserving and federated machine learning in medical imaging. Nat. Mach. Intell. 2, 305–311 (2020). sourceExperimental — accuracy not yet measured
The Outlook section of our copy supports the direction of the claim: it states that decentralized data storage and federated learning systems are 'replacing the current paradigm of data sharing and centralized storage' and are driven by privacy requirements, and the paper elsewhere notes such methods 'should require minimal or no data transfer'. However, the source hedges this as having 'the greatest potential to enable privacy-preserving cross-institutional research in a breadth of biomedical disciplines in the near future', whereas the citing sentence asserts it as a certainty ('will become the preferred choice') and extends it to 'handling, storing, managing, and analysing any kind of large medical dataset' — a scope and a confidence level the source does not claim. The 'reduce data traffic and duplication' motive is only partly reflected (the paper in fact lists communication overhead and burdensome data transfer as limitations of decentralized/federated and SMPC approaches). (LLM, conf=0.72)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“with current privacy regulations5,9,10 making it less appealing to develop centralized AI systems”
§ Swarm Learning for decentralized and confidential clinical machine learning > Discussion
What the sources say
- Partly supportedcites [5] Price, W. N., II & Cohen, I. G. Privacy in the age of medical big data. Nat. Med. 25, 37–43 (2019). sourceExperimental — accuracy not yet measured
Price & Cohen (2019) do support the general thrust: in 'A path forward' they write that 'The basic harm of privacy overprotection is the brakes it puts on data-driven innovation,' that privacy protections limit data aggregation and innovative data use, and that 'Patchy, fragmented health data make data-driven innovation hard, imposing both technological and economic hurdles' (A path forward); they also note in 'Why do we need big data in health?' that AI uses 'require very large sets of data' and that without them 'algorithms cannot be trained or ... evaluated.' But our copy nowhere contrasts centralized with decentralized/federated architectures, and says nothing about privacy regulation making 'centralized' AI systems specifically less appealing — that comparative claim is the citing authors'. The paper's regulatory discussion is also confined to U.S. law (HIPAA de-identification, covered entities), narrower than the unqualified 'current privacy regulations' in the citing sentence. (LLM, conf=0.72)
- Not checked yetcites [9] Kels, C. G. HIPAA in the era of data sharing. J. Am. Med. Assoc. 323, 476–477 (2020). source
- Not checked yetcites [10] McCall, B. What does the GDPR mean for the medical community? Lancet 391, 1249–1250 (2018). source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“but progress is hindered by the limited size of datasets19”
§ Swarm Learning for decentralized and confidential clinical machine learning > Discussion
What the sources say
- Supportedcites [19] Kaissis, G. A., Makowski, M. R., Rückert, D. & Braren, R. F. Secure, privacy-preserving and federated machine learning in medical imaging. Nat. Mach. Intell. 2, 305–311 (2020). source
The opening of our copy (Abstract/front-matter, p. 305) states that 'the broad application of artificial intelligence techniques in medicine is currently hindered by limited dataset availability for algorithm training and validation.' The Introduction (Abstract section, p. 305) ties progress specifically to oncology applications (tumour detection, genomic characterization, subtyping, grading, outcome/relapse risk) to 'the release of large, curated corpora of images', notes that 'even the largest current imaging studies in the field ... include considerably less data than, for example, ImageNet', and that 'the inability to access and leverage this data poses a significant barrier to AI applications in this field.' This supports the paraphrase that limited dataset size hinders progress in oncology machine learning, with the caveat that the source's scope is medical imaging AI generally rather than oncology alone. (LLM, conf=0.85)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When we reduced cases at training nodes, all performance measures remained very high at the test node for SL and individual nodes (Extended Data Fig. 8e–j).”
§ Swarm Learning for decentralized and confidential clinical machine learning > Identification of COVID-19
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
32 more claims
Create a free account to see all 71 claims and to verify the 16 references still open.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 20
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It can also overcome the straggler dilemma with heterogeneous hardware, as well as improve the robustness to data poisoning attacks and master node fails [35], [145].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [35]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“FL allows training of AI models through averaging of local updates from numerous healthcare facilities and smart devices, such as IoMT, despite the lack of local data.”
From Federated learning-based AI approaches in smart healthcare: Concepts, taxonomies, challenges and open issues (2023) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Federated Learning has presented itself as a viable method for implementing economic, innovative healthcare systems while ensuring privacy [11–15].”
From Federated learning-based AI approaches in smart healthcare: Concepts, taxonomies, challenges and open issues (2023) · cites this paper as [11]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In particular, swarm learning [35] provides a completely decentralized AI solution based on decentralized ML by keeping local datasets at each edge device.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [35]
The cited source says what the claim attributes to it.
In the citing paper
“Besides, swarm learning has recently been developed in [35] to provide a decentralized and confidential clinical disease detection solution for diseases (e.g., COVID-19, tuberculosis, and leukaemia).”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [35]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2
Love, M. I., Huber, W., & Anders, S. (2014) · Genome Biology · doi:10.1186/s13059-014-0550-8 · Cited by 95,106
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
STAR: ultrafast universal RNA-seq aligner
Dobin, A., Davis, C. A., Schlesinger, F., Drenkow, J., Zaleski, C., Jha, S., Batut, P., Chaisson, M., & Gingeras, T. R. (2013) · Bioinformatics · doi:10.1093/bioinformatics/bts635 · Cited by 51,709
Bootstrap methods: another look at the jackknife
Efron, B. (1979) · The Annals of Statistics · doi:10.1214/aos/1176344552 · Cited by 17,602
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · cited 1×
“Particularly in oncology, success has been reported in machine-learning-based tumour detection 3,37 , sub-typing 38 , and outcome prediction 39 , but progress is hindered by the limited size of datasets 19 , with current privacy regulations 5,9,10 making it less appealing to develop centralized AI…”
BackgroundCommunication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Gene Expression Omnibus: NCBI gene expression and hybridization array data repository
Edgar, R. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.1.207 · Cited by 13,288
Exploration, normalization, and summaries of high density oligonucleotide array probe level data
Irizarry, R. A. (2003) · Biostatistics · doi:10.1093/biostatistics/4.2.249 · Cited by 10,603
Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR
Corman, V. M., Landt, O., Kaiser, M., Molenkamp, R., Meijer, A., Chu, D. K., Bleicker, T., Brünink, S., Schneider, J., Schmidt, M. L., et al. (2020) · Eurosurveillance · doi:10.2807/1560-7917.es.2020.25.3.2000045 · Cited by 7,344 · cited 10×
“We obtained very similar results using datasets A1 and A3, which strongly supports the idea that the improvement in performance of SL is independent of data collection (clinical studies) or the technologies (microarray or RNA-seq) used for data generation (Extended Data Fig.”
MethodInfluential
Cited by
Scientific discovery in the age of artificial intelligence.
Wang, H., Fu, T., Du, Y., Gao, W., Huang, K., Liu, Z., Chandak, P., Liu, S., Van Katwyk, P., Deac, A., et al. (2023) · Nature · doi:10.1038/s41586-023-06221-2 · Cited by 1,823
Towards Personalized Federated Learning
Tan, A. Z., Yu, H., Cui, L., & Yang, Q. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3160699 · Cited by 1,182
Acosta, J. N., Falcone, G. J., Rajpurkar, P., & Topol, E. J. (2022) · Nature Medicine · doi:10.1038/s41591-022-01981-2 · Cited by 1,365
“Finally, swarm learning is a relatively novel approach that, similarly to federated learning, is also based on several individuals or organizations training a model on local data, but does not require a trusted central server because it replaces it with the use of blockchain smart contracts 170 .”
BackgroundEdge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“to-peer network was developed in [35] to support swarm learning without a central server.”
BackgroundInfluentialFederated learning for smart healthcare: A survey
Nguyen, D. C., Pham, Q.-V., Pathirana, P. N., Ding, M., Seneviratne, A., Lin, Z., Dobre, O., & Hwang, W.-J. (2023) · ACM Computing Surveys · doi:10.1145/3501296 · Cited by 827
Metadata
- Authors
- 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., 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., (COVAS), C.-1. A. S., Balfanz, P., Eggermann, T., Boor, P., Hausmann, R., Kuhn, H., Isfort, S., Stingl, J. C., Schmalzing, G., Kuhl, C. K., Röhrig, R., Marx, G., Uhlig, S., Dahl, E., Müller-Wieland, D., Dreher, M., Marx, N., Nattermann, J., Skowasch, D., Kurth, I., Keller, A., Bals, R., Nürnberg, P., Rieß, O., Rosenstiel, P., Netea, M. G., Theis, F., Mukherjee, S., Backes, M., Aschenbrenner, A. C., Ulas, T., (DeCOI), D. C.-1. O. I., Angelov, A., Bartholomäus, A., Becker, A., Bezdan, D., Blumert, C., Bonifacio, E., Bork, P., Boyke, B., Blum, H., Clavel, T., Colome-Tatche, M., Cornberg, M., De La Rosa Velázquez, I. A., Diefenbach, A., Dilthey, A., Fischer, N., Förstner, K., Franzenburg, S., Frick, J.-S., Gabernet, G., Gagneur, J., Ganzenmueller, T., Gauder, M., Geißert, J., Goesmann, A., Göpel, S., Grundhoff, A., Grundmann, H., Hain, T., Hanses, F., Hehr, U., Heimbach, A., Hoeper, M., Horn, F., Hübschmann, D., Hummel, M., Iftner, T., Iftner, A., Illig, T., Janssen, S., Kalinowski, J., Kallies, R., Kehr, B., Keppler, O. T., Klein, C., Knop, M., Kohlbacher, O., Köhrer, K., Korbel, J., Kremsner, P. G., Kühnert, D., Landthaler, M., Li, Y., Ludwig, K. U., Makarewicz, O., Marz, M., McHardy, A. C., Mertes, C., Münchhoff, M., Nahnsen, S., Nöthen, M., Ntoumi, F., Overmann, J., Peter, S., Pfeffer, K., Pink, I., Poetsch, A. R., Protzer, U., Pühler, A., Rajewsky, N., Ralser, M., Reiche, K., Ripke, S., da Rocha, U. N., Saliba, A.-E., Sander, L. E., Sawitzki, B., Scheithauer, S., Schiffer, P., Schmid-Burgk, J., Schneider, W., Schulte, E.-C., Sczyrba, A., Sharaf, M. L., Singh, Y., Sonnabend, M., Stegle, O., Stoye, J., Vehreschild, J., Velavan, T. P., Vogel, J., Volland, S., von Kleist, M., Walker, A., Walter, J., Wieczorek, D., Winkler, S., Ziebuhr, J., Breteler, M. M. B., Giamarellos-Bourboulis, E. J., Kox, M., Becker, M., Cheran, S., Woodacre, M. S., Goh, E. L., & Schultze, J. L.
- Affiliations
- Hewlett Packard Enterprise (United States) (US)
- German Center for Neurodegenerative Diseases (DE)
- University of Bonn (DE)
- Radboud University Nijmegen (NL)
- National and Kapodistrian University of Athens (GR)
- Christian-Albrechts-Universität zu Kiel (DE)
- Universitätsklinikum Tübingen (DE)
- University of Tübingen (DE)
- Universitätsklinikum des Saarlandes (DE)
- LMU Klinikum (DE)
- Technical University of Munich (DE)
- Saarland University (DE)
- University of Cologne (DE)
- German Center for Infection Research (DE)
- Universitätsklinikum Aachen (DE)
- RWTH Aachen University (DE)
- University Hospital Bonn (DE)
- GFZ Helmholtz Centre for Geosciences (DE)
- Philipps University of Marburg (DE)
- Center for Regenerative Therapies Dresden (DE)
- European Molecular Biology Laboratory (DE)
- Helmholtz Munich (DE)
- Medizinische Hochschule Hannover (DE)
- University Medical Center Hamburg-Eppendorf (DE)
- Düsseldorf University Hospital (DE)
- ZB MED - Information Centre for Life Sciences (DE)
- Quantitative Biology Center (DE)
- Justus-Liebig-Universität Gießen (DE)
- University Medical Center Freiburg (DE)
- Leibniz Institute of Virology (LIV) (DE)
- German Cancer Research Center (DE)
- Fraunhofer Institute for Cell Therapy and Immunology (DE)
- Charité – Universitätsmedizin Berlin (DE)
- Bielefeld University (DE)
- Helmholtz Centre for Environmental Research (DE)
- Heidelberg University (DE)
- Max Delbrück Center (DE)
- Helmholtz Centre for Infection Research (DE)
- Helmholtz Institute for RNA-based Infection Research (DE)
- Universitätsmedizin Göttingen (DE)
- Robert Koch Institute (DE)
- Max Planck Institute of Molecular Cell Biology and Genetics (DE)
- Corresponding author
- Schultze, Joachim L.
- ORCID
- Warnat-Herresthal, Stefanie
- Schultze, Hartmut
- Manamohan, Sathyanarayanan
- Mukherjee, Saikat
- Garg, Vishesh
- Händler, Kristian
- Pickkers, Peter
- Aziz, N. Ahmad
- Ktena, Sofia
- Tran, Florian
- Bitzer, Michael
- Ossowski, Stephan
- Casadei, Nicolas
- Herr, Christian
- Petersheim, Daniel
- Behrends, Uta
- Kern, Fabian
- Fehlmann, Tobias
- Schommers, Philipp
- Lehmann, Clara
- Augustin, Max
- Rybniker, Jan
- Altmüller, Janine
- Mishra, Neha
- Bernardes, Joana P.
- Krämer, Benjamin
- Bonaguro, Lorenzo
- Schulte-Schrepping, Jonas
- De Domenico, Elena
- Siever, Christian
- Desai, Milind
- Saridaki, Maria
- Siegel, Charles Martin
- Drews, Anna
- Nuesch-Germano, Melanie
- Theis, Heidi
- Heyckendorf, Jan
- Schreiber, Stefan
- Kim-Hellmuth, Sarah
- Balfanz, Paul
- Eggermann, Thomas
- Boor, Peter
- Hausmann, Ralf
- Kuhn, Hannah
- Isfort, Susanne
- Stingl, Julia Carolin
- Kuhl, Christiane K.
- Röhrig, Rainer
- Marx, Gernot
- Uhlig, Stefan
- Dahl, Edgar
- Dreher, Michael
- Marx, Nikolaus
- Nattermann, Jacob
- Skowasch, Dirk
- Kurth, Ingo
- Keller, Andreas
- Bals, Robert
- Nürnberg, Peter
- Rieß, Olaf
- Rosenstiel, Philip
- Netea, Mihai G.
- Theis, Fabian
- Aschenbrenner, Anna C.
- Ulas, Thomas
- Angelov, Angel
- Bartholomäus, Alexander
- Becker, Anke
- Bezdan, Daniela
- Blumert, Conny
- Bonifacio, Ezio
- Blum, Helmut
- Clavel, Thomas
- Cornberg, Markus
- Diefenbach, Andreas
- Dilthey, Alexander
- Fischer, Nicole
- Förstner, Konrad
- Franzenburg, Sören
- Frick, Julia-Stefanie
- Gabernet, Gisela
- Gagneur, Julien
- Ganzenmueller, Tina
- Gauder, Marie
- Geißert, Janina
- Goesmann, Alexander
- Göpel, Siri
- Grundhoff, Adam
- Grundmann, Hajo
- Hain, Torsten
- Hanses, Frank
- Hehr, Ute
- Hoeper, Marius
- Hübschmann, Daniel
- Hummel, Michael
- Iftner, Thomas
- Illig, Thomas
- Kalinowski, Jörn
- Kallies, René
- Kehr, Birte
- Keppler, Oliver T.
- Klein, Christoph
- Knop, Michael
- Kohlbacher, Oliver
- Köhrer, Karl
- Korbel, Jan
- Kremsner, Peter G.
- Kühnert, Denise
- Landthaler, Markus
- Li, Yang
- Ludwig, Kerstin U.
- Makarewicz, Oliwia
- Marz, Manja
- McHardy, Alice C.
- Mertes, Christian
- Nahnsen, Sven
- Nöthen, Markus
- Ntoumi, Francine
- Overmann, Jörg
- Peter, Silke
- Pfeffer, Klaus
- Pink, Isabell
- Poetsch, Anna R.
- Protzer, Ulrike
- Pühler, Alfred
- Rajewsky, Nikolaus
- Ralser, Markus
- Reiche, Kristin
- Ripke, Stephan
- da Rocha, Ulisses Nunes
- Saliba, Antoine-Emmanuel
- Sander, Leif Erik
- Sawitzki, Birgit
- Scheithauer, Simone
- Schiffer, Philipp
- Schmid-Burgk, Jonathan
- Schulte, Eva-Christina
- Sczyrba, Alexander
- Singh, Yogesh
- Sonnabend, Michael
- Stegle, Oliver
- Stoye, Jens
- Velavan, Thirumalaisamy P.
- Vogel, Jörg
- Volland, Sonja
- von Kleist, Max
- Walker, Andreas
- Walter, Jörn
- Wieczorek, Dagmar
- Winkler, Sylke
- Ziebuhr, John
- Breteler, Monique M. B.
- Giamarellos-Bourboulis, Evangelos J.
- Kox, Matthijs
- Becker, Matthias
- Cheran, Sorin
- Goh, Eng Lim
- Schultze, Joachim L.
- Venue
- Nature
- Published
- 2021-05-26
- Volume
- 594
- Issue
- 7862
- Pages
- 265-270
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- PMC
- PMC8189907
- OpenAlex
- W3164573547
- Cited by
- 884
- References
- 85
- Citations by year
- 2026: 131 · 2025: 174 · 2024: 177 · 2023: 207 · 2022: 157 · 2021: 36
- FWCI
- 50.98
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Nature (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Kölner Universitäts PublikationsServer (Universität zu Köln) (publishedVersion)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (publishedVersion, cc-by)
- MDC Repository (Max-Delbrueck-Center for Molecular Medicine) (acceptedVersion)
- Publication server of the Robert Koch Institute (Robert Kock Institute) (submittedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion, other-oa)
- Publication Database GFZ (GFZ German Research Centre for Geosciences) (submittedVersion, other-oa)
- Publication Database GFZ (GFZ German Research Centre for Geosciences) (submittedVersion, cc-by)
- mediaTUM (Technical University of Munich) (submittedVersion, other-oa)
- mediaTUM (Technical University of Munich) (submittedVersion)
- Site cant be reached (submittedVersion, cc-by)
- DZNE Pub (submittedVersion, cc-by)
- DZNE Pub (submittedVersion)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- GoeScholar The Publication Server of the Georg-August-Universität Göttingen (Georg-August-Universität Göttingen) (submittedVersion, cc-by)
- RWTH Publications (RWTH Aachen) (submittedVersion, cc-by)
- PuSH - Publication Server of Helmholtz Zentrum München (submittedVersion, cc-by)
- Radboud Repository (Radboud University) (submittedVersion)
- Radboud Repository (Radboud University) (submittedVersion, other-oa)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion, cc-by)
- RWTH Publications (RWTH Aachen)
- Publications of the UdS (Saarland University) (cc-by)
- Funders
- Michael J. Fox Foundation for Parkinson's Research (14446)
- Care-for-Rare Foundation
- Francis Crick Institute (10134)
- European Commission (733100)
- Deutsche Forschungsgemeinschaft (SPP193 7, 733100, INST 216/981‐1, INST 217/577-1, EXC 2151, ZT-I-0007, INST 217/988-1, 01KX2021, INST 37/1049-1, INST 269/768-1, INST 257/605-1, INST 269/768, 390873048)
- Bundesministerium für Bildung und Forschung (FKZ 01KX2021, 01EA1809A, 01KX2021)
- National and Kapodistrian University of Athens
- Deutsches Zentrum für Neurodegenerative Erkrankungen
- Universität des Saarlandes
- Hector Fellow Academy
- Dr. Rolf M. Schwiete Stiftung
- Hector Stiftung
- Helmholtz Artificial Intelligence Cooperation Unit (ZT-I-0007)
- H2020 European Research Council (833247)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- swarm learning, decentralized machine learning, privacy-preserving data sharing, edge computing, federated learning, blood transcriptome, leukemia classification, COVID-19 pandemic, tuberculosis, lung pathology, chest X-ray classification, precision medicine, data ownership
- MeSH terms
- Clinical Decision-Making, Machine Learning, Blockchain, COVID-19, Confidentiality, Disease Outbreaks, Female, Humans, Leukemia, Leukocytes, Lung Diseases, Male, Software, Tuberculosis, Precision Medicine, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Swarm Learning for decentralized and confidential clinical machine learning. https://app.cochat.ai/papers/10.1038/s41586-021-03583-3
- The paper
- 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., . . . Schultze, J. L. (2021). Swarm Learning for decentralized and confidential clinical machine learning. Nature. https://doi.org/10.1038/s41586-021-03583-3
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.