The DOI matches its Crossref record; 65 of the 68 references it cites were found in a registry or an index; 6 of the 40 sources its claims cite were checked for support.
Federated learning for predicting clinical outcomes in patients with COVID-19
Open accessPublished version of a preprint
Abstract
Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
27 Own result · 22 Own interpretation · 19 Not checked yet · 14 Own method · 2 Partly supported · 2 No basis given · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“CXR was selected as the imaging input because it is widely available and commonly indicated by guidelines”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Abstract
What the sources say
- Not checked yetcites [22] American College of Radiology. CR recommendations for the use of chest radiography and computed tomography (CT) for suspected COVID-19 infection. https://www.acr.org/Advocacy-and-Economics/ACR-Position-Statements/Recommendations-for-Chest-Radiography-and-CT-for-Suspected-COVID19-Infection (2020).
- Partly supportedcites [23] Rubin, G. D. et al. The role of chest imaging in patient management during the COVID-19 pandemic: a multinational consensus statement from the Fleischner Society. Radiology 296, 172–180 (2020). sourceExperimental — accuracy not yet measured
The Essentials and Scenario 2 sections recommend chest imaging for certain COVID-19 presentations, supporting the claim that imaging is indicated by guidance. But the Methods section says the recommendations do not specify CXR over CT and leave modality choice to clinical teams. The paper notes CXR’s portability, not that it is widely available. (LLM, conf=0.84)
- Not checked yetcites [24] World Health Organization. Use of chest imaging in COVID-19. https://www.who.int/publications/i/item/use-of-chest-imaging-in-covid-19 (2020).
plaindirect- 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.
None of the sources cited for this claim have been checked yet.
In the paper
“Known issues of Batch Normalization (BN) in FL58 motivated us to fix our base model for image feature extraction49 in order to reduce the divergence between unbalanced client-sites.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
What the sources say
- Not checked yetcites [58] Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proc. 32nd International Conf. Machine Learning, PMLR 37, 448–456 (2015).
- Could not verifycites [49] 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 'Decentralized data and federated machine learning' section discusses challenges in updating a central model, but does not address batch normalization. Searches for batch normalization and heterogeneous client data found no passage linking BN to divergence between client sites. The decision to fix the feature-extraction model is presented as the citing authors' own response, not as a finding attributed to this source. (LLM, conf=0.72)
plaindirect- 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.
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
“In the case of client sites with relatively small datasets, the best FL model markedly outperformed the ‘local’ model as well as models trained on larger datasets from 5 client-sites in the Boston area”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Federating The Model
plaindirect- 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.
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
“It also resulted in a 38% generalizability improvement (as defined by the average-AUC when running the model on all test sets; from 0.667 to 0.920 or 25.3 percentage points) of the best global model for predicting 24h oxygen treatment compared to models trained only on a site’s own data”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Federating The Model
plaindirect- 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.
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
“For MV at 72h, EXAM had a low false-negative rate of 7.1% at CDH.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Validation At Independent Sites
plainn = 2- 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.
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
“NCH did not have any cases with MV / death at 24h.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Validation At Independent Sites
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.
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
“EXAM achieved an average area under the curve (AUC) greater than 0.92 for predicting outcomes at 24 and 72h from the time of initial presentation to the ER”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Abstract
plaincorrelational- 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.
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
“Training the model through FL resulted in a significant performance improvement (p<<1e-3, Wilcoxon signed-rank test)”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Federating The Model
plaindirect- 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.
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
“As for 72h MV prediction, EXAM achieved a sensitivity of 0.929 and specificity of 0.880 at CDH”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Validation At Independent Sites
plain- 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 paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Patient age and EMR feature distributions varied greatly between sites, as expected due to the differing demographics between globally distributed hospitals”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Data Collection
plaincorrelational- 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.
- Probably not a substantial claim. 20
- It may state two separate claims as one. 31
- The quote only partly states this claim. 1
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“FL has already shown promise in recent medical imaging applications40–43, including in COVID-19 analysis8,44,45.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Abstract
What the sources say
- Not checked yetcites [40] Roth, H. R. et al. Federated learning for breast density classification: a real-world implementation. In Proc. Second MICCAI Workshop, DART 2020 and First MICCAI Workshop, DCL 2020, Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning (eds. Albarqouni, S. et al.) Vol. 12,444, 181–191 (Springer International Publishing, 2020).
- Supportedcites [41] Sheller, M. J. et al. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci. Rep. 10, 12598 (2020). source
The Discussion reports that federated learning performed well on radiographic imaging models distinguishing healthy brain tissue from cancer, supporting the medical-imaging part of the sentence. The COVID-19 clause has a separate citation group and is not attributed to this source. (LLM, conf=0.90)
- Supportedcites [42] Remedios, S. W., Butman, J. A., Landman, B. A. & Pham, D. L. in Federated Gradient Averaging for Multi-Site Training with Momentum-Based Optimizers (eds Remedios, S. W. et al.) (Springer, 2020). source
The Abstract and Discussion report a multi-site head CT hemorrhage segmentation application in which federated gradient averaging outperformed other federated methods. This supports the medical-imaging portion of the sentence; the separate COVID-19 clause is attached to other citations. (LLM, conf=0.91)
- Not checked yetcites [43] Xu, Y. et al. A collaborative online AI engine for CT-based COVID-19 diagnosis. Preprint at https://www.medrxiv.org/content/10.1101/2020.05.10.20096073v2 (2020).
- Supportedcites [8] Yang, D. et al. Federated semi-supervised learning for Covid region segmentation in chest ct using multi-national data from China, Italy, Japan. Med. Image Anal. 70, 101992 (2021). source
The Experiment and results section reports that federated semi-supervised learning generally outperformed models trained on individual sites for COVID-region segmentation in chest CT. The Related work section also describes successful federated-learning applications in medical imaging. Together, these support the claim that the approach has shown promise, including for COVID-19 analysis. (LLM, conf=0.93)
- Partly supportedcites [44] Raisaro, J. L. et al. SCOR: A secure international informatics infrastructure to investigate COVID-19. J. Am. Med. Inform. Assoc. 27, 1721–1726 (2020). sourceExperimental — accuracy not yet measured
The Abstract describes federated machine learning as poised to help COVID-19 research, and Clinical Research Goals notes that COVID-19 registries contain imaging data. But the paper proposes infrastructure for future federated analysis; it does not report a medical-imaging application in which federated learning has already shown promise. (LLM, conf=0.83)
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
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
“The FL global trained model, EXAM, achieved an average AUC of 0.944 and 0.924 for 24/72h prediction tasks respectively (Table 2 b), which exceeded the average performance among sites used in training EXAM.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Validation At Independent Sites
plain- 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.
It may state two separate claims as one.
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
“showing two false-negative cases from CDH where one case had many missing EMR data features, and the other case had a CXR with motion artifact and some missing EMR features.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Validation At Independent Sites
plaincorrelationaln = 2- 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.
It may state two separate claims as one.
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
“For the prediction results of 72h oxygen treatments, the best global model training resulted in an average performance improvement of 18% compared to locally trained models, while generalizability of the global model improved on average by 34%”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Federating The Model
plaindirect- 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.
It may state two separate claims as one.
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
“The FL model achieved a higher true positive rate for the two positive (severe) cases and a markedly lower false positive rate compared to the local model”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Federating The Model
plaindirect- 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.
It may state two separate claims as one.
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
“We conducted a Wilcoxon signed-rank test to confirm the significance of the observed improvement in performance between the locally trained model and the FL model for the 24 and 72 hr time point (see Fig. 2 and Extended Data Fig. 1). The null hypothesis was rejected with a one-sided p-value << 1e-3 in both cases.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Statistical Analysis
plaindirect- 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.
It may state two separate claims as one.
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
“Our results show that the F-values of 5 different local sites are 245.7, 253.4, 342.3, 389.8, while the F-value of the FL model is 843.5.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Statistical Analysis
plain- 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.
It may state two separate claims as one.
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
“Histogram of CORISK results at MGB, with an illustration of how the score can be used for patient triage, in which ‘A’ is an example threshold for safe discharge that has 99.5% negative predictive value, and ‘B’ is an example threshold for Intensive Care Unit (ICU) admission that has 50.3% positive predictive value.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Extended Data
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.
It may state two separate claims as one.
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
“The average performance improved by 18% (from 0.760 to 0.899 or 13.9 percentage points) compared to locally trained models alone, while average generalizability of the global model improved by 34% (from 0.669 to 0.899 or 23.0 percentage points).”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Extended Data
plaindirect- 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.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“For both the 24h and 72h outcome prediction models, the random splits for each of the three repeated local and FL training and evaluation experiments were independently generated.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Model input
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Each client-site was asked to randomly split its dataset into 3 parts, 70% for training, 10% for validation, and 20% for testing.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Model input
plain- 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.
Probably not a substantial claim.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The model was not re-trained at these sites, and it was only used for validation purposes.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Validation At Independent Sites
plain- 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.
It may state two separate claims as one. The quote only partly states this claim.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“we limited the number of negative patients included to, at –most, 95% of the total cases at each client-site.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Data Collection
plainn = 16,148- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“All procedures were conducted in accordance with principles for human experimentation as defined in the Declaration of Helsinki and International Conference on Harmonization Good Clinical Practice guidelines and approved by the relevant institutional review boards”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Ethics Approval
plain- 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.
Probably not a substantial claim. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Data between sites was not harmonized prior to being extracted, and in light of real-life clinical informatics circumstances, a meticulous harmonization of the data input was not conducted by the authors”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Federating The Model
plainn = 16,148- 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.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“MI-CLAIM guidelines for reporting of clinical AI models were followed”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Ethics Approval
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The model’s design was constrained to objective predictors, unlike many published studies that leveraged subjective clinical impressions.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The validation results confirmed that the global model is robust, supporting our hypothesis that FL trained models are generalisable across healthcare systems.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plaincorrelational- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The EXAM score can be used in the same way.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Extended Data
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- Rests on an assumption: The CORISK thresholds derived at MGB are applicable to other populations.
None of the sources cited for this claim have been checked yet.
In the paper
“Governance of data for FL is maintained locally, alleviating privacy concerns, with only model weights or gradients communicated between the client-sites and the federated server38,39.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Abstract
What the sources say
- Not checked yetcites [38] Ma, C. et al. On safeguarding privacy and security in the framework of federated learning. IEEE Netw. 34, 242–248 (2020). source
- Not checked yetcites [39] Brisimi, T. S. et al. Federated learning of predictive models from federated Electronic Health Records. Int. J. Med. Inform. 112, 59–67 (2018). source
plaindirect- 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.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The global FL model, EXAM, proved to be more robust and achieved better results on individual sites than any model that was trained only on local data.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plaindirect- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We also used cases with unknown SARS-COV-2 status, and so the model could provide input to the physician ahead of receiving an RT-PCR test result, making it useful for a real-life clinical setting.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
hedgeddirect- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our study involved multiple sites across four continents and under the oversight of different regulatory bodies, and thus holds the promise of being provided to different regulated markets in an expedited way.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
hedgedconditional- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Similar to other machine learning models, EXAM is limited by the quality of the training data.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“In contrast, a patient who is at a lower risk of requiring invasive oxygen therapy may be placed in a less intensive care setting such as a regular ward or even released from the ED for continued self-monitoring at home65.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > EXAM Model Development
What the sources say
- Not checked yetcites [65] Kilaru, A. S. et al. Return hospital admissions among 1419 COVID-19 patients discharged from five U.S. emergency departments. Acad. Emerg. Med. 27, 1039–1042 (2020). source
hedgedconditional- 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.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We believe that due to the diversity across 20 sites, this risk may have been mitigated.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Of note, the model is not approved by any regulatory agency at this time, and it should only be used for research purposes.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > EXAM Model Development
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The encryption algorithms, such as Homomorphic Encryption60 shall maintain the performance but may significantly increase the message sizes and training time.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
What the sources say
- Not checked yetcites [60] Zhang, C. et al. BatchCrypt: efficient homomorphic encryption for cross-silo federated learning. In Proc. 2020 USENIX Annual Technical Conference, ATC 2020, 493–506 (2020).
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“To date, most AI models, including the aforementioned CDS model, have been trained and validated on ‘narrow’ data that often lacks in diversity31,32, potentially resulting in over-fitting and lower generalizability.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Abstract
What the sources say
- Not checked yetcites [31] Esteva, A. et al. A guide to deep learning in healthcare. Nat. Med. 25, 24–29 (2019). source
- Not checked yetcites [32] Cahan, E. M., Hernandez-Boussard, T., Thadaney-Israni, S. & Rubin, D. L. Putting the data before the algorithm in big data addressing personalized healthcare. NPJ Digit. Med. 2, 78 (2019). source
plaindirect- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The data collected reflects varied incidence rates, and thus the ‘population momentum’ we encountered is more diverse.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plaindirect- 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.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The dataset from the 20 institutes that participated in this study remains under their custody. This data was used for training at each of the local sites and was not shared with any of the other participant institutions or with the Federated Server, and it is not publicly available.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Data availability
plain- 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.
It may state two separate claims as one.
In the paper
“Arguably, the most established form of FL is implementing the Federated Averaging algorithm proposed by McMahan et al72, or variations thereof.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Federated Learning Details
What the sources say
- Not checked yetcites McMahan et al72
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“The output of the CDS model was a score, termed ‘CORISK’27 that corresponded to oxygen support requirements, and that could aid in triaging patients by front-line clinicians28+30.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Abstract
What the sources say
- Not checked yetcites [27] Buch, V. et al. Development and validation of a deep learning model for prediction of severe outcomes in suspected COVID-19 Infection. Preprint at https://arxiv.org/abs/2103.11269 (2021).
- Not checked yetcites 28+30
hedgedcorrelational- 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.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“While differential privacy algorithms36,48,49 show good protection, they may weaken the model’s performance.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
What the sources say
- Not checked yetcites [36] Rieke, N. et al. The future of digital health with federated learning. NPJ Dig. Med. 3, 119 (2020). source
- Not checked yetcites [48] Zhu, L., Liu, Z. & Han, S. in Advances in Neural Information Processing Systems 32 (eds Wallach, H. et al.) 14774–14784 (Curran Associates, Inc., 2019).
- Not checked yetcites [49] 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
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Each client site learns locally, and shares model weight updates with a central server that aggregates contributions using secure SSL encryption and communication protocols.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Federated Learning Details
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“All code and software used in this study are publicly available on NGC.”
- Also stated in: § Code availability · plain
“The trained models, data preparation guidelines, code for training, validating testing the model, readme file, installation guideline, and license files are publicly available at NVIDIA NGC61: https://ngc.nvidia.com/catalog/models/nvidia:med:clara_train_covid19_exam_ehr_xray”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Code availability
What the sources say
- Not checked yetcites [61] Nvidia NGC Catalog: COVID-19 Related Models. https://ngc.nvidia.com/catalog/models?orderBy=scoreDESC&pageNumber=0&query=covid&quickFilter=models&filters (2020).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Also stated in: § Code availability · plain
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The finding, that these two approaches were outperformed on all three prediction tasks by the global FL model, indicate that the benefit for client-sites with small datasets arising from participation in FL collaborations is substantial.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
hedgeddirect- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We believe that consistent improvement was achieved not only due to larger, but also a more diverse data set, the use of data inputs that can be standardized and avoidance of clinical impressions / reported symptoms.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
hedgeddirect- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Unlike the majority of the publications, focused on diagnosis of COVID-19 or predicting mortality, we predicted oxygen requirements that have implications for patient management.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plain- 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.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“As data was not centralized, it is not readily accessible. Given that, any future analysis of the results, beyond what was derived and collected, is limited.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plaindirect- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The model’s imaging input is used in common practice, in contrast with models that use chest Computed Tomography (CT), a non-consensual diagnostic modality.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“A critical decision made during the evaluation of a patient at the initial point of care or the ED, is whether the patient is likely to require more invasive or resource-limited countermeasures or interventions”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > EXAM Model Development
What the sources say
- Not checked yetcites [64] Galloway, J. B. et al. A clinical risk score to identify patients with COVID-19 at high risk of critical care admission or death: an observational cohort study. J. Infect. 81, 282–288 (2020). source
plain- 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.
Probably not a substantial claim.
None of the sources cited for this claim have been checked yet.
In the paper
“For FL, there remains the potential risk of model ‘inversion’47 or even the reconstruction of training images from the model gradients themselves48.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > Use Of Differential Privacy
What the sources say
- Not checked yetcites [47] Fredrikson, M., Jha, S. & Ristenpart, T. Model inversion attacks that exploit confidence information and basic countermeasures. In Proc. 22nd ACM SIGSAC Conference on Computer and Communications Security 1322–1333, https://doi.org/10.1145/2810103.2813677 (2015). source
- Not checked yetcites [48] Zhu, L., Liu, Z. & Han, S. in Advances in Neural Information Processing Systems 32 (eds Wallach, H. et al.) 14774–14784 (Curran Associates, Inc., 2019).
hedgedconditional- 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.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is likely a reflection of FL’s ability to capture more diversity than local training, and to mitigate the bias present in models trained on a homogenous population.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Discussion
hedgedconditional- 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.
It may state two separate claims as one.
The authors state this as an assumption.
Oxygen delivered to a patient is equivalent to the patient's oxygen need.
“It is assumed that oxygen delivered to the patient equates with the oxygen need.”
The paper relies on this without support.
In the early phase of the COVID-19 pandemic, many patients received high-flow oxygen prophylactically regardless of their oxygen need.
“However, in the early phase of the COVID-19 pandemic, many patients were provided high flow oxygen prophylactically, regardless of their oxygen need.”
The paper relies on this without support.
The clinical labels for oxygen support requirements accurately reflect the patients' true clinical states.
“The final output was a continuous value in the range of 0 – 1 for both the 24 hour and 72-hour predictions, corresponding to the labels described above”
The paper relies on this without support.
The test datasets at each site are independent and representative of the target populations.
“After the FL training finishes, the best local models and the best global model are automatically shared with all client-sites and evaluated on their local test data.”
The paper relies on this without support.
The CORISK thresholds derived at MGB are applicable to other populations.
“The EXAM score can be used in the same way.”
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
“Because federated learning uses several datasets reflecting worldwide diversity in demographics, imaging modalities, and disease presentations, it is particularly helpful in osteoarthritis imaging [180].”
From Biomarker-Guided Imaging and AI-Augmented Diagnosis of Degenerative Joint Disease (2025) · cites this paper as [180]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The authors in [56] discuss the development of a federated learning model called EXAM, which predicts the oxygen requirements of COVID-19 patients using data from 20 institutions worldwide.”
From Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions (2023) · cites this paper as [56]
In the citing paper
“Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates.”
From Federated learning enables big data for rare cancer boundary detection (2022) · cites this paper as [16]
In the citing paper
“The extended global footprint and the task complexity are what sets this study apart from current literature, since it dealt with a multi-parametric multi-class problem with reference standards that require expert clinicians following an involved manual annotation protocol, rather than simply recording a categorical entry from medical records16,32.”
From Federated learning enables big data for rare cancer boundary detection (2022) · cites this paper as [16]
In the citing paper
“These insights differ from previous literature that describes studies that were smaller in scale and involved simpler tasks16,32.”
From Federated learning enables big data for rare cancer boundary detection (2022) · cites this paper as [16]
In the citing paper
“demonstrating an improved average AUC and a broader applicability in contrast to models trained at only one site.”
From Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions (2023) · cites this paper as [56]
In the citing paper
“EXAM achieved a mean AUC (Area Under The Curve) of 0.92 in predicting outcomes within 24 and 72 h, demonstrating an improved average AUC and a broader applicability in contrast to models trained at only one site.”
From Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions (2023) · cites this paper as [56]
In the citing paper
“FL facilitated rapid collaboration without data sharing and enabled a model that could be generalized across heterogeneous datasets, demonstrating the potential of FL in healthcare.”
From Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions (2023) · cites this paper as [56]
In the citing paper
“The first way is to directly use databases from different medical sites/centers [48,100].”
From Federated learning for medical image analysis: A survey (2024) · cites this paper as [100]
In the citing paper
“Dayan et al. [100] build a large-scale federation through international cooperation.”
From Federated learning for medical image analysis: A survey (2024) · cites this paper as [100]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Results > The EXAM Model Architecture
“In total, 20 features (19 from the EMR and a CXR) were used as input to the model.”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Model input
“In total, 21 EMR features were used as input to the model.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Statistical Analysis
“5 different local sites”
§ Federated learning for predicting clinical outcomes in patients with COVID-19 > Methods > Statistical Analysis
“245.7, 253.4, 342.3, 389.8”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“9a, the model fuses information from both EMR and CXR features (based on a modified ResNet34 with spatial attention 66 pretrained on the CheXpert dataset) 67 and the Deep & Cross network 68 .”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
Communication-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 · cited 1×
“Arguably the most established form of FL is implemention of the federated averaging algorithm as proposed by McMahan et al. 72 , or variations thereof.”
MethodpROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697 · cited 1×
“The computation of P values was conducted in R with the pROC library 74 .”
MethodFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
MissForest—Non-parametric missing value imputation for mixed-type data
Stekhoven, D. J., & Bühlmann, P. (2012) · Bioinformatics · doi:10.1093/bioinformatics/btr597 · Cited by 6,156 · cited 1×
“A MissForest algorithm 71 was used to impute EMR features, based on the local training dataset.”
MethodA guide to deep learning in healthcare
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0316-z · Cited by 5,312 · cited 1×
“To date most AI models, including the aforementioned CDS model, have been trained and validated on ‘narrow’ data that often lack diversity 31,32 , potentially resulting in overfitting and lower generalizability.”
MethodThe future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015 · cited 4×
“This is conducted as an iterative process until training is complete 36 .”
BackgroundMethodInfluentialSelf-citationWynants, L., Van Calster, B., Bonten, M. M., Collins, G. S., Debray, T. P., De Vos, M., Haller, M. C., Heinze, G., Moons, K. G., Riley, R. D., et al. (2020) · doi:10.1101/2020.03.24.20041020 · Cited by 3,070
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961 · cited 2×
“For FL, there remains the potential risk of model ‘inversion’ 47 or even the reconstruction of training images from the model gradients themselves 48 .”
Background
Research works printed but not linked: 3
- Zhu, L., Liu, Z. & Han, S. in Advances in Neural Information Processing Systems 32 (eds Wallach, H. et al.) 14774–14784 (Curran Associates, Inc., 2019).
- Abadi, M. et al. TensorFlow: asystem for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), USENIX Association 265–283 (2016).
- Hsieh, K., Phanishayee, A., Mutlu, O. & Gibbons, P. B. The non-IID data quagmire of decentralized machine learning. In Proc. 37th International Conf. Machine Learning PMLR 119 (2020).
Cited by
Sorted by citations
Wynants, L., Van Calster, B., Bonten, M. M., Collins, G. S., Debray, T. P., De Vos, M., Haller, M. C., Heinze, G., Moons, K. G., Riley, R. D., et al. (2020) · doi:10.1101/2020.03.24.20041020 · Cited by 3,070
Traumatic brain injury: progress and challenges in prevention, clinical care, and research
Maas, A. I. R., Menon, D. K., Manley, G. T., Abrams, M. B., Åkerlund, C. A. I., Anđelić, N., Aries, M. J. H., Bashford, T., Bell, M. J., Bodien, Y. G., et al. (2022) · The Lancet Neurology · doi:10.1016/s1474-4422(22)00309-x · Cited by 1,737
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
“168 ).”
Towards Personalized Federated Learning
Tan, A. Z., Yu, H., Cui, L., & Yang, Q. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3160699 · Cited by 1,474
“This is especially relevant in the healthcare industry where medical data are highly sensitive and they are often collected and reside across different healthcare institutions [1]–[4].”
BackgroundA survey on federated learning: challenges and applications
Wen, J., Zhang, Z., Lan, Y., Cui, Z., Cai, J., & Zhang, W. (2022) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01647-y · Cited by 1,014
Communication-efficient federated learning via knowledge distillation
Wu, C., Wu, F., Lyu, L., Huang, Y., & Xie, X. (2022) · Nature Communications · doi:10.1038/s41467-022-29763-x · Cited by 700
“Federated learning is a recent technique to learn intelligent models from decentralized private data 4 , which has been widely used in various applications that involve privacy-sensitive data such as intelligent healthcare 9,10 , personalized recommendation 11 , and mobile keyboard prediction 12 .”
Heterogeneous Federated Learning: State-of-the-art and Research Challenges
Ye, M., Fang, X., Du, B., Yuen, P. C., & Tao, D. (2023) · ACM Computing Surveys · doi:10.1145/3625558 · Cited by 709
“Federated learning has drawn increasing attention in both academia and industry owing to its potential utility in large-scale applications [48, 85, 185], which has been widely explored in the fields of healthcare [39, 178, 214], medical analysis [54, 97], and data security [205], etc.”
BackgroundFederated learning for medical image analysis: A survey
Guan, H., Yap, P.-T., Bozoki, A., & Liu, M. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110424 · Cited by 518
Development of metaverse for intelligent healthcare
Wang, G., Badal, A., Jia, X., Maltz, J. S., Mueller, K. D., Myers, K. J., Niu, C., Vannier, M. W., Yan, P., Yu, Z., et al. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00549-6 · Cited by 442
Federated learning enables big data for rare cancer boundary detection
Pati, S., Baid, U., Edwards, B., Sheller, M., Wang, S.-H., Reina, G. A., Foley, P., Gruzdev, A., Karkada, D., Davatzikos, C., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-33407-5 · Cited by 394
“…is what sets this study apart from current literature, since it dealt with a multi-parametric multi-class problem with reference standards that require expert clinicians following an involved manual annotation protocol, rather than recording a categorical entry from medical records 30,51 .”
BackgroundResultInfluentialSelf-citationRahman, A., Hossain, M. S., Muhammad, G., Kundu, D., Debnath, T., Rahman, M., Khan, M. S. I., Tiwari, P., & Band, S. S. (2023) · Cluster Computing · doi:10.1007/s10586-022-03658-4 · Cited by 399
FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction
Gao, L., Fu, H., Li, L., Chen, Y., Xu, M., & Xu, C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00987 · Cited by 417
“Recently, FL has become a hot research topic [3, 8, 11].”
BackgroundRauniyar, A., Hagos, D. H., Jha, D., Håkegård, J. E., Bagci, U., Rawat, D. B., & Vlassov, V. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3329061 · Cited by 315
“Another groundbreaking initiative, the EMR chest X-ray AI model (EXAM) [98], utilizes FL to estimate future oxygen requirements for symptomatic COVID-19 patients.”
BackgroundMethodDecentralized Federated Learning: A Survey and Perspective
Yuan, L., Wang, Z., Sun, L., Yu, P. S., & Brinton, C. G. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3407584 · Cited by 365
“Researchers employed FL to aggregate data from 20 institutes worldwide to train a universal model to predict clinical outcomes of COVID-19 patients [30].”
MethodThe Role of Machine Learning in Cybersecurity
Apruzzese, G., Laskov, P., de, E. M., Mallouli, W., Búrdalo, L., Grammatopoulos, A. V., & Franco, F. D. (2022) · Digital Threats Research and Practice · doi:10.1145/3545574 · Cited by 359
“Fascinating examples of practical achievements of ML are machine translation [168], travel and vacation recommendations [77], object detection and tracking [139] and even various applications in healthcare [57].”
BackgroundThe promise of digital healthcare technologies
Yeung, A. W. K., Torkamani, A., Butte, A. J., Glicksberg, B. S., Schuller, B. W., Rodríguez, B., Ting, D. S. W., Bates, D. W., Schaden, E., Peng, H., et al. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1196596 · Cited by 284
“The analysis of clinical data of COVID-19 patients with AI/federated learning could effectively predict their clinical outcomes such as the necessity to use mechanical ventilation or death at 24 h (68).”
Self-citationTeo, Z. L., Jin, L., Liu, N., Li, S., Miao, D., Zhang, X., Ng, W. Y., Tan, T. F., Lee, D. M., Chua, K. J., et al. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101419 · Cited by 255
“1,6 FL has been shown to remain robusttomultipledatatypesincludingimaging,suchasmagnetic resonance imaging (MRI) for brain tumor segmentation 7 ; chest X-rayforCOVID-19clinicaloutcomeprediction 8 ;electronicmed-ical records for predicting hospitalization 9 ; colored photographs, such as skin photographs in skin lesion…”
BackgroundFederated Class-Incremental Learning
Dong, J., Wang, L., Fang, Z., Sun, G., Xu, S., Wang, X., & Zhu, Q. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00992 · Cited by 279
“To better coma prehend the FCIL problem, we here use COVID-19 diagnosis among different hospitals as a possible example [6].”
MethodSelf-citationPrivacy preservation for federated learning in health care
Pati, S., Kumar, S., Varma, A., Edwards, B., Lu, C., Qu, L., Wang, J. J., Lakshminarayanan, A., Wang, S.-H., Sheller, M., et al. (2024) · Patterns · doi:10.1016/j.patter.2024.100974 · Cited by 294
“14,22,24,25,27,48,49 The degree to which an FL system can be thought to be ‘‘secure and pri-vate’’ largely depends on the additional security and privacy technologies that it incorporates into the system.”
BackgroundArtificial intelligence in ophthalmology: The path to the real-world clinic
Li, Z., Wang, L., Wu, X., Jiang, J., Qiang, W., Xie, H., Zhou, H., Wu, S., Shao, Y., & Chen, W. (2023) · Cell Reports Medicine · doi:10.1016/j.xcrm.2023.101095 · Cited by 219
“Meanwhile, federated learning can facilitate rapid data science collaboration and thus improve the robustness of AI systems.(128) In addition, controlled-access data sharing, an approach that requires a request for access to datasets to be approved, is another alternative solution for researchers to acquire data to so…”
Federated benchmarking of medical artificial intelligence with MedPerf
Karargyris, A., Umeton, R., Sheller, M. J., Aristizabal, A., George, J., Wuest, A., Pati, S., Kassem, H., Zenk, M., Baid, U., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00652-2 · Cited by 188
Self-citationArtificial Intelligence and Biosensors in Healthcare and Its Clinical Relevance: A Review
(2023) · doi:10.1109/access.2023.3285596 · Cited by 205
“In [123], a federated learning model was developed to predict future oxygen requirements for COVID-19 patients making use of clinical and radiology”
MethodReview on security of federated learning and its application in healthcare
Li, H., Li, C., Wang, J., Yang, A., Ma, Z., Zhang, Z., & Hua, D. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.02.021 · Cited by 202
Yang, J., Soltan, A. A. S., & Clifton, D. A. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00614-9 · Cited by 181
Yan, R., Qu, L., Wei, Q., Huang, S.-C., Shen, L., Rubin, D. L., Xing, L., & Zhou, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3233574 · Cited by 183
“[3] I. Dayan et al., “Federated learning for predicting clinical outcomes in patients with COVID-19,” Nature Med., vol. 27, no. 10, pp. 1735–1743, 2021.”
MethodInfluentialArtificial intelligence for modelling infectious disease epidemics
Kraemer, M. U. G., Tsui, J. L.-H., Chang, S. Y., Lytras, S., Khurana, M. P., Vanderslott, S., Bajaj, S., Scheidwasser, N., Curran-Sebastian, J. L., Semenova, E., et al. (2025) · Nature · doi:10.1038/s41586-024-08564-w · Cited by 222
“An example of this is federated learning, in which partial model training occurs across multiple local servers without sharing sensitive data externally, with the results iteratively merged on a central server 139,140 .”
Hergenroeder, G. W., Moore, A. N., McCoy, J. P., Samsel, L., Ward, N. H., Clifton, G. L., & Dash, P. K. (2010) · Journal of Neuroinflammation · doi:10.1186/1742-2094-7-19 · Cited by 165
An adversarial training framework for mitigating algorithmic biases in clinical machine learning
Yang, J., Soltan, A. A. S., Eyre, D. W., Yang, Y., & Clifton, D. A. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00805-y · Cited by 159
“Recently, researchers have shown that federated learning (FL) could effectively predict clinical outcomes of COVID-19, using combined data from multiple sites 20 .”
BackgroundPrivacy and Security in Federated Learning: A Survey
Gosselin, R., Vieu, L., Loukil, F., & Benoît, A. (2022) · Applied Sciences · doi:10.3390/app12199901 · Cited by 178
“In [14], data collected from over 20 institutions around the world were used to train a global FL model.”
MethodTao, S., Liu, H., Sun, C., Ji, H., Ji, G., Han, Z., Gao, R., Ma, J., Ma, R., Chen, Y., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-43883-y · Cited by 171
“Federated machine learning has been extensively investigated in numerous applicative fi elds, including public health 41,42 , clinical diagnosis 43 – 45 , e-commerce 46 , Internet of Things 47 , mobile computing 48 , and smart grid 49 – 51 .”
BackgroundConcepts and applications of digital twins in healthcare and medicine
Zhang, K., Zhou, H.-Y., Baptista‐Hon, D. T., Gao, Y., Liu, X., Oermann, E. K., Xu, S. H., Jin, S., Zhang, J., Sun, Z., et al. (2024) · Patterns · doi:10.1016/j.patter.2024.101028 · Cited by 185
Self-citationArtificial Intelligence in Critical Care Medicine
Yoon, J. H., Pinsky, M. R., & Clermont, G. (2022) · Critical Care · doi:10.1186/s13054-022-03915-3 · Cited by 149
“Across the globe, 20 academic centers collaborated to predict clinical outcomes from COVID-19 by constructing federated learning within a strong cloud computing system [42].”
BackgroundA Review of Privacy Enhancement Methods for Federated Learning in Healthcare Systems
Gu, X., Sabrina, F., Fan, Z., & Sohail, S. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20156539 · Cited by 139
“In population health management, FL has been investigated, such as predicting clinical outcomes in patients with COVID-19 [6].”
MethodInfluentialFederated learning for healthcare applications
Chaddad, A., Wu, Y., & Desrosiers, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3325822 · Cited by 136
Federated machine learning for privacy preserving, collective supply chain risk prediction
Ge, Z., Kong, L., & Brintrup, A. M. (2023) · International Journal of Production Research · doi:10.1080/00207543.2022.2164628 · Cited by 155
“…applications included cross-institutional medical diagnosis (Sheller et al. 2020), forecasting hospitalisations in the USA (Brisimi et al. 2018; Dayan et al.2021), credit risk (Kawa et al. 2019), fraud detection (Yang et al. 2019; Li et al. 2019), energy demand forecasting (Briggs, Fan, and…”
BackgroundGoto, S., Solanki, D., John, J. E., Yagi, R., Homilius, M., Ichihara, G., Katsumata, Y., Gaggin, H. K., Itabashi, Y., MacRae, C. A., et al. (2022) · Circulation · doi:10.1161/circulationaha.121.058696 · Cited by 130
The Cross-Evaluation of Machine Learning-Based Network Intrusion Detection Systems
Apruzzese, G., Pajola, L., & Conti, M. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3157344 · Cited by 142
“…(e.g., [35]), and cross-evaluations could greatly benefit from dedicated ‘banks’ of NID data (e.g., [36]): it is true that the cybersecurity domain has high confiden-tiality, but anonymization techniques exists [37], and some recent solutions in federated learning overcame privacy issues (e.g. [38]).”
BackgroundFedNI: Federated Graph Learning With Network Inpainting for Population-Based Disease Prediction
Peng, L., Wang, N., Dvornek, N. C., Zhu, X., & Li, X. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3188728 · Cited by 131
Self-citationIntegrating multi-omics data with EHR for precision medicine using advanced artificial intelligence
Tong, L., Shi, W., Isgut, M., Zhong, Y., Lais, P., Gloster, L., Sun, J., Swain, A., Giuste, F., & Wang, M. D. (2024) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2023.3324264 · Cited by 130
“Moreover, under the COVID-19 pandemic, EHR data has been explored to predict the risk of mortality [53], [55], the risk for the transition from mild to severe [47], future oxygen requirements [48], and the need for mechanical ventilation [54].”
BackgroundDo Gradient Inversion Attacks Make Federated Learning Unsafe?
Hatamizadeh, A., Yin, H., Molchanov, P. A., Myronenko, A., Li, W., Dogra, P., Feng, A., Flores, M. G., Kautz, J., Xu, D., et al. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3239391 · Cited by 144
“Several real-world applications of FL in medical imaging have shown its potential to improve the model performance and generalizability of AI models by allowing them to learn from large and diverse patient populations, which could include variations in scanner equipment and acquisition protocols, often spanning differ…”
BackgroundSelf-citationFedMix: Mixed Supervised Federated Learning for Medical Image Segmentation
Wicaksana, J., Yan, Z., Zhang, D., Huang, X., Wu, H., Yang, X. Y., & Cheng, K.-T. T. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3233405 · Cited by 142
“In recent years, FL has drawn great attention from the medical image communities [19], [58] and has been validated for multi-site functional magnetic resonance imaging classification [14], health tracking through wearables [64], COVID-19 screening and lesion detection [59], and brain tumor segmentation [13], [18].”
BackgroundSpecificity-Preserving Federated Learning for MR Image Reconstruction
Feng, C.-M., Yan, Y., Wang, S., Xu, Y. D., Shao, L., & Fu, H. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3202106 · Cited by 131
Moor, M., Bennett, N., Plečko, D., Horn, M., Rieck, B., Meinshausen, N., Bühlmann, P., & Borgwardt, K. (2023) · eClinicalMedicine · doi:10.1016/j.eclinm.2023.102124 · Cited by 118
“35,36 The availability of the harmonised and annotated dataset used in this study allows for other researchers and clinicians to evaluate their prediction models on external hospital sites, which could be a valuable consideration when making decisions about implementing early warning systems in new…”
MethodLi, M., Xu, P., Hu, J., Tang, Z., & Yang, G. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103497 · Cited by 167
Ullah, F., Nadeem, M., Abrar, M. Y. B. T., Amin, F., Salam, A., & Khan, S. (2023) · Mathematics · doi:10.3390/math11194189 · Cited by 114
“In addition, to reduce the communication overhead of the client data transfer, model compression is discussed, and its performance is presented.”
IoMT: A COVID-19 Healthcare System Driven by Federated Learning and Blockchain
Samuel, O., Omojo, A. B., Onuja, A. M., Sunday, Y., Tiwari, P., Gupta, D., Hafeez, G., Yahaya, A. S., Fatoba, O. J., & Shamshirband, S. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3143576 · Cited by 113
“To deal with the problem, federated learning (FL) has been proposed by the research community [3].”
BackgroundBadidi, E. (2023) · Future Internet · doi:10.3390/fi15110370 · Cited by 113
“The authors in [56] discuss the development of a federated learning model called EXAM, which predicts the oxygen requirements of COVID-19 patients using data from 20 institutions worldwide.”
Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
Chaddad, A., Lu, Q., Li, J., Katib, Y., Kateb, R., Tanougast, C., Bouridane, A., & Abdulkadir, A. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123123 · Cited by 114
“For example, data from 20 institutes across the globe to train a model (EXAM: electronic medical record (EMR) chest X-ray AI model), for predicting COVID-19 [144].”
MethodMultimodal federated learning: Concept, methods, applications and future directions
Huang, W. X., Wang, D., Ouyang, X., Wan, J., Liu, J., & Li, T. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102576 · Cited by 105
Federated learning for medical imaging radiology
Rehman, M. H. U., Pinaya, W. H. L., Nachev, P., Teo, J., Sebastien Ourselin, A., & Cardoso, M. J. (2023) · British Journal of Radiology · doi:10.1259/bjr.20220890 · Cited by 125
Malik, H., Naeem, A., Naqvi, R. A., & Loh, W.-K. (2023) · Sensors · doi:10.3390/s23020743 · Cited by 104
“The problem of inconsistent data must be solved.”
BackgroundFederated Semi-Supervised Learning for Medical Image Segmentation via Pseudo-Label Denoising
Qiu, L., Cheng, J., Gao, H., Xiong, W., & Ren, H. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3274498 · Cited by 98
Self-citationImmune digital twins for complex human pathologies: applications, limitations, and challenges
Niarakis, A., Laubenbacher, R., An, G. C., Ilan, Y., Fisher, J., Flobak, Å., Reiche, K., Martínez, M. R., Geris, L., Ladeira, L., et al. (2024) · npj Systems Biology and Applications · doi:10.1038/s41540-024-00450-5 · Cited by 104
“Federated learning, a collaborative learning approach thattacklesdatasharingandprivacyissuesbykeeping datalocalisedwhile enabling collective model training 51,52 .”
Encrypted federated learning for secure decentralized collaboration in cancer image analysis
Truhn, D., Arasteh, S. T., Saldanha, O. L., Müller‐Franzes, G. A., Khader, F., Quirke, P., West, N. P., Gray, R. G., Hutchins, G. G. A., James, J. A., et al. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.103059 · Cited by 111
Federated learning for preserving data privacy in collaborative healthcare research
Loftus, T. J., Ruppert, M. M., Shickel, B., Ozrazgat‐Baslanti, T., Balch, J. A., Efron, P. A., Upchurch, G. R., Rashidi, P., Tignanelli, C. J., Bian, J., et al. (2022) · Digital Health · doi:10.1177/20552076221134455 · Cited by 98
“Acquiring more, diverse data for artificial intelligence training datasets is a positive-sum game, as evident in artificial intelligence models in general and in federated learning models that perform better on local datasets than similar models using local data exclusively.(3) Despite the potential advantages of fede…”
MethodArtificial Intelligence and Deep Learning for Rheumatologists
McMaster, C., Bird, A., Liew, D. F. L., Buchanan, R. R. C., Owen, C., Chapman, W. W., & Pires, D. E. V. (2022) · Arthritis & Rheumatology · doi:10.1002/art.42296 · Cited by 89
“Several federated learning techniques exist; however, recent work has focused on methods whereby individual sites train small models on local data, with the coef fi cients of these models sent to a central site that uses these to train a multicenter model (74,75).”
MethodMedical Imaging Applications of Federated Learning
Sandhu, S. S., Gorji, H. T., Tavakolian, P., Tavakolian, K., & Akhbardeh, A. (2023) · Diagnostics · doi:10.3390/diagnostics13193140 · Cited by 100
“Dayan et al. had previously published work within the field using local ML models and transferred their knowledge into their FL findings [69].”
Yang, Y., Du, Y., Gupta, V. K., Ahmad, F., Amiri, H., Pan, J., Aghbashlo, M., Tabatabaei, M., & Rajaei, A. (2024) · Food Packaging and Shelf Life · doi:10.1016/j.fpsl.2024.101287 · Cited by 91
Federated Learning for the Internet-of-Medical-Things: A Survey
Prasad, V. K., Bhattacharya, P., Maru, D., Tanwar, S., Verma, A., Singh, A., Tiwari, A. K., Sharma, R., Alkhayyat, A. H., Țurcanu, F.-E., et al. (2022) · Mathematics · doi:10.3390/math11010151 · Cited by 87
AI in Pathology: What could possibly go wrong?
Nakagawa, K., Moukheiber, L., Celi, L. A., Patel, M. P., Mahmood, F., Gondim, D. D., Hogarth, M. A., & Levenson, R. M. (2023) · Seminars in Diagnostic Pathology · doi:10.1053/j.semdp.2023.02.006 · Cited by 79
IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentation
Jiang, M., Yang, H., Chen, C., & Dou, Q. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3263072 · Cited by 83
“FEDERATED learning (FL) in medical image analysis has been an increasingly important topic, owning to its advantage of jointly learning a global model on many clients in a decentralized way [1], [2], [3], [4], [5], [6], [7], [8], [9],”
Nguyen, T., Dakka, M. A., Diakiw, S. M., VerMilyea, M. D., Perugini, M., Hall, J. M. M., & Perugini, D. (2022) · Scientific Reports · doi:10.1038/s41598-022-12833-x · Cited by 86
Federated Learning in Health care Using Structured Medical Data
Oh, W., & Nadkarni, G. N. (2023) · Advances in Kidney Disease and Health · doi:10.1053/j.akdh.2022.11.007 · Cited by 88
Han, F., Huang, X., Wang, X., Chen, Y., Lu, C., Li, S., Lu, L., & Zhang, D. (2025) · MedComm · doi:10.1002/mco2.70260 · Cited by 104
Machine learning in prostate MRI for prostate cancer: current status and future opportunities
Li, H., Lee, C. H., Chia, D., Lin, Z., Huang, W., & Tan, C. H. (2022) · Diagnostics · doi:10.3390/diagnostics12020289 · Cited by 74
Self-citationShao, J., Ma, J., Zhang, Q., Li, W., & Wang, C. (2023) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2023.02.006 · Cited by 85
Self-citationA federated machine learning approach for order-level risk prediction in Supply Chain Financing
Kong, L., Ge, Z., & Brintrup, A. M. (2023) · International Journal of Production Economics · doi:10.1016/j.ijpe.2023.109095 · Cited by 78
Roth, H. R., Xu, Z., Tor-Díez, C., Jacob, R. S., Zember, J. S., Molto, J., Li, W., Xu, S., Türkbey, B., Turkbey, E. B., et al. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102605 · Cited by 104
“Alternatively, federated approaches allow algorithms to access data from multiple sites without the need of sharing raw data, but through this paradigm access is granted to a single algorithm and consortium, with sharing of model weights instead of raw data (Yang et al., 2021; Dayan et al., 2021).”
BackgroundSelf-citationNo One Left Behind: Real-World Federated Class-Incremental Learning
Dong, J., Li, H., Cong, Y., Sun, G., Zhang, Y., & Gool, L. V. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3334213 · Cited by 90
“In this case, existing FL models [16], [38] suffer from large performance degradation on old diseases when collecting new COVID-19 variants continuously [4].”
MethodSimon, B. D., Ozyoruk, K. B., Gelikman, D. G., Harmon, S. A., & Türkbey, B. (2024) · Diagnostic and Interventional Radiology · doi:10.4274/dir.2024.242631 · Cited by 73
Self-citationFair Federated Medical Image Segmentation via Client Contribution Estimation
Jiang, M., Roth, H. R., Li, W., Yang, D. L., Zhao, C. H., Nath, V., Xu, D., Dou, Q., & Xu, Z. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01564 · Cited by 86
Self-citationFedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation
Miao, J., Yang, Z., Fan, L., & Yang, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00777 · Cited by 75
“Federated Learning (FL) has attracted more and more attention in recent years, which provides a decentralized machine learning paradigm with data privacy-preserving [1,10, 11,15,18,19,21,26,31,32,36,38,44,60,61].”
BackgroundApplications of Distributed Machine Learning for the Internet-of-Things: A Comprehensive Survey
Le, M., Huynh‐The, T., Do‐Duy, T., Vu, T.-H., Hwang, W., & Pham, Q. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3427324 · Cited by 94
“In addition, in a paper published by Nature Medicine [158], 20 institutes around the world have collaborated to realize a training AI model using federated learning that predicts the future oxygen demands of symptomatic patients with COVID-19 infections.”
Ullah, F., Srivastava, G., Xiao, H., Ullah, S., Lin, J. C., & Zhao, Y. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3282955 · Cited by 70
“Several researchers, including [18], proposed specialized FL paradigms foridentifyingCOVID-19illnessusingX-rayimages.”
BackgroundChallenges and prospects of visual contactless physiological monitoring in clinical study
Huang, B., Hu, S., Liu, Z., Lin, C., Su, J., Zhao, C., Wang, L., & Wang, W. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00973-x · Cited by 76
“Recently, federated learning have been widely applied in healthcare and clinical systems 57,58,136 – 138 , and just one VCPM study leverages federated learning at present 63 .”
BackgroundSelf-citationFederated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics
Haggenmüller, S., Schmitt, M., Krieghoff‐Henning, E., Hekler, A., Maron, R. C., Wies, C., Utikal, J. S., Meier, F. E., Hobelsberger, S., Gellrich, F. F., et al. (2024) · JAMA Dermatology · doi:10.1001/jamadermatol.2023.5550 · Cited by 72
Park, W., Huh, J., & Lee, J. (2023) · Scientific Reports · doi:10.1038/s41598-023-32118-1 · Cited by 68
Big data and deep learning for RNA biology
Hwang, H., Jeon, H., Yeo, N., & Baek, D. (2024) · Experimental & Molecular Medicine · doi:10.1038/s12276-024-01243-w · Cited by 64
“Using federated learning, multiple institutions can collaborate without sharing sensitive transcriptome data outside the institution 292,293 .”
BackgroundDifferentially private knowledge transfer for federated learning
Qi, T., Wu, F., Wu, C., He, L., Huang, Y., & Xie, X. (2023) · Nature Communications · doi:10.1038/s41467-023-38794-x · Cited by 65
“as Covid-19 patient detection 27,28 and intelligent personal assistant 29,30 .”
BackgroundNardone, V., Marmorino, F., Germani, M. M., Cichowska-Cwalińska, N., Menditti, V. S., Gallo, P., Studiale, V., Taravella, A., Landi, M., Reginelli, A., et al. (2024) · Current Oncology · doi:10.3390/curroncol31090369 · Cited by 71
“Compliance with GDPR and ISO 27001 standards [123] is essential to align with industry best practices [124].”
MethodFederated Learning in Dentistry: Chances and Challenges
Rischke, R., Schneider, L., Müller, K. R., Samek, W., Schwendicke, F., & Krois, J. (2022) · Journal of Dental Research · doi:10.1177/00220345221108953 · Cited by 72
“The performance of all local AI models regarding their predictive quality and generalizability can be improved by collaborative training (Roth et al. 2020; Dayan et al. 2021; Yang et al. 2021).”
BackgroundLambin, P., Woodruff, H. C., Mali, S. A., Zhong, X., Kuang, S., Lavrova, E., Khan, H., Lekadir, K., Zwanenburg, A., Deasy, J. O., et al. (2025) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-025-01067-1 · Cited by 72
“Federated learning has been used for several radiology tasks performed on CT and MRI images for the detection of coronavirus disease 2019 and brain tumour segmentation, showing great promise in achieving performance equivalent to that in a centralized setting 148,149 .”
Study on transfer learning capabilities for pneumonia classification in chest-x-rays images
Avola, D., Bacciu, A., Cinque, L., Fagioli, A., Marini, M. R., & Taiello, R. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106833 · Cited by 61
Zhao, J., Bagchi, S., Avestimehr, S., Chan, K., Chaterji, S., Dimitriadis, D., Li, J., Li, N., Nourian, A., & Roth, H. (2025) · ACM Computing Surveys · doi:10.1145/3724113 · Cited by 63
“This diversity is rooted in demographic variances, regional characteristics, or the intrinsic nature of the collected data.”
Self-citationBiosecurity in an age of open science
Smith, J. A., & Sandbrink, J. B. (2022) · PLoS Biology · doi:10.1371/journal.pbio.3001600 · Cited by 63
““Code only access,” where analytic code is run on datasets but researchers do not see the data directly [49,50], is another possibility.”
BackgroundArtificial General Intelligence for Medical Imaging Analysis
Li, X., Zhao, L., Zhang, L., Wu, Z., Liu, Z., Jiang, H., Cao, C., Xu, S., Li, Y., Dai, H., et al. (2024) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2024.3493775 · Cited by 91
“In the medical domain, federated learning has demonstrated great promise as it allows the development of powerful and accurate machine learning models while maintaining the privacy and security of sensitive healthcare data [10], [137].”
Self-citationMajeed, A., & Hwang, S. O. (2021) · Symmetry · doi:10.3390/sym14010016 · Cited by 73
“In addition, studying the role of federated learning in the context of COVID-19 is also a very hot research area in recent times [297–299].”
BackgroundRadhakrishnan, L., Schenk, G., Muenzen, K., Oskotsky, B., Choshali, H. A., Plunkett, T., Israni, S., & Butte, A. J. (2023) · JAMIA Open · doi:10.1093/jamiaopen/ooad045 · Cited by 54
Harfouche, A. L., Nakhle, F., Harfouche, A., Sardella, O. G., Dart, E., & Jacobson, D. (2022) · Trends in Plant Science · doi:10.1016/j.tplants.2022.08.021 · Cited by 56
Meduri, K., Nadella, G. S., Yadulla, A. R., et al. (2024) · Journal of Economy and Technology · doi:10.1016/j.ject.2024.11.001 · Cited by 54
Shiri, I., Sadr, A. V., Akhavan, A., Salimi, Y., Sanaat, A., Amini, M., Razeghi, B., Saberi, A., Arabi, H., Ferdowsi, S., et al. (2022) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-022-06053-8 · Cited by 60
“In a more recent study [37], an FL-based model, referred to as EXAM, was developed based on vital signs laboratory exams and chest X-rays for future oxygen requirements of COVID-19 patients across twenty centers.”
MethodShiri, I., Sadr, A. V., Amini, M., Salimi, Y., Sanaat, A., Akhavanallaf, A., Razeghi, B., Ferdowsi, S., Saberi, A., Arabi, H., et al. (2022) · Clinical Nuclear Medicine · doi:10.1097/rlu.0000000000004194 · Cited by 56
Innovations in thoracic imaging: CT , radiomics, AI and x‐ray velocimetry
Vliegenthart, R., Fouras, A., Jacobs, C., & Papanikolaou, N. K. (2022) · Respirology · doi:10.1111/resp.14344 · Cited by 50
“72 Important challenges for the adoption of AI technology are integration into healthcare IT systems, current clinical workflows and reimbursement.”
BackgroundChallenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting
Leming, M., Bron, E. E., Bruffaerts, R., Ou, Y., Iglesias, J. E., Gollub, R. L., & Im, H. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00868-x · Cited by 63
“In healthcare particularly, federated learning 106,107 , in which models are trained internally in several different sites for generalizability, has great potential to be an effective method to improve model robustness that also follows data privacy laws.”
BackgroundWearable AI to enhance patient safety and clinical decision-making
Mahajan, A., Heydari, K., & Powell, D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01554-w · Cited by 64
Precision dentistry—what it is, where it fails (yet), and how to get there
Schwendicke, F., & Krois, J. (2022) · Clinical Oral Investigations · doi:10.1007/s00784-022-04420-1 · Cited by 48
Federated Learning in Ocular Imaging: Current Progress and Future Direction
Nguyen, T. X., Ran, A. R., Hu, X., Yang, D., Jiang, M., Dou, Q., & Cheung, C. Y.-L. (2022) · Diagnostics · doi:10.3390/diagnostics12112835 · Cited by 53
Bhujel, R., Enkmann, V., Burgstaller, H., & Maharjan, R. (2025) · Pharmaceutics · doi:10.3390/pharmaceutics17080992 · Cited by 51
“The system’s federated learning framework continuously improves prediction models using anonymized data from 12 global distribution hubs [143].”
Rong, Y., Chen, Q., Fu, Y., Yang, X., Al‐Hallaq, H., Wu, Q., Yuan, L., Xiao, Y., Cai, B., Latifi, K., et al. (2023) · International Journal of Radiation Oncology*Biology*Physics · doi:10.1016/j.ijrobp.2023.10.033 · Cited by 58
Mining multi-center heterogeneous medical data with distributed synthetic learning
Chang, Q., Yan, Z., Zhou, M., Qu, H. Y., He, X., Zhang, H., Baskaran, L., Alaref, S. J., Li, H., Zhang, S., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-40687-y · Cited by 53
“Also, combining imaging data with other forms of electronic health records such as clinical lab results or radiology reports into a united learning framework could be of substantial interest 57 .”
Metadata
- Authors
- Dayan, I., Roth, H. R., Zhong, A., Harouni, A., Gentili, A., Abidin, A. Z., Liu, A., Costa, A. B., Wood, B. J., Tsai, C.-S., Wang, C.-H., Hsu, C.-N., Lee, C. K., Ruan, P., Xu, D., Wu, D., Huang, E., Kitamura, F. C., Lacey, G., de Antônio Corradi, G. C., Nino, G., Shin, H.-H., Obinata, H., Ren, H., Crane, J. C., Tetreault, J., Guan, J., Garrett, J. W., Kaggie, J. D., Park, J. G., Dreyer, K., Juluru, K., Kersten, K., Rockenbach, M. A. B. C., Linguraru, M. G., Haider, M. A., AbdelMaseeh, M., Rieke, N., Damasceno, P. F., e Silva, P. M. C., Wang, P., Xu, S., Kawano, S., Sriswasdi, S., Park, S. Y., Grist, T. M., Buch, V., Jantarabenjakul, W., Wang, W., Tak, W. Y., Li, X., Lin, X., Kwon, Y. J., Quraini, A., Feng, A., Priest, A. N., Turkbey, B., Glicksberg, B., Bizzo, B., Kim, B. S., Tor-Díez, C., Lee, C.-C., Hsu, C.-J., Lin, C., Lai, C.-L., Hess, C. P., Compas, C., Bhatia, D., Oermann, E. K., Leibovitz, E., Sasaki, H., Mori, H., Yang, I., Sohn, J. H., Murthy, K. N. K., Fu, L.-C., de Mendonça, M. R. F., Fralick, M., Kang, M. K., Adil, M., Gangai, N., Vateekul, P., Elnajjar, P., Hickman, S., Majumdar, S., McLeod, S. L., Reed, S., Gräf, S., Harmon, S., Kodama, T., Puthanakit, T., Mazzulli, T., de Lavor, V. L., Rakvongthai, Y., Lee, Y. R., Wen, Y., Gilbert, F. J., Flores, M. G., & Li, Q.
- Affiliations
- Harvard University (US)
- Nvidia (United States) (US)
- VA San Diego Healthcare System (US)
- Icahn School of Medicine at Mount Sinai (US)
- National Institutes of Health (US)
- Tri-Service General Hospital (TW)
- DASA (Brazil) (BR)
- Memorial Sloan Kettering Cancer Center (US)
- Self-Defense Forces Central Hospital (JP)
- University of California, San Francisco (US)
- University of Wisconsin–Madison (US)
- University of Cambridge (GB)
- Yeungnam University College (KR)
- Children's National (US)
- University of Toronto (CA)
- Lunenfeld-Tanenbaum Research Institute (CA)
- Chulalongkorn University (TH)
- Kyungpook National University (KR)
- Mass General Brigham (US)
- National Taiwan University (TW)
- Daegu Catholic University (KR)
- National Defense Medical Center (TW)
- National Health Insurance Administration (TW)
- New York University (US)
- Sinai Health System (CA)
- University Health Network (CA)
- Corresponding author
- Flores, Mona G.
- ORCID
- Dayan, Ittai
- Roth, Holger R.
- Zhong, Aoxiao
- Gentili, Amilcare
- Abidin, Anas Z.
- Costa, Anthony Beardsworth
- Wood, Bradford J.
- Tsai, Chien-Sung
- Wang, Chih-Hung
- Hsu, Chun-Nan
- Xu, Daguang
- Wu, Dufan
- Kitamura, Felipe Campos
- Shin, Hao-Hsin
- Obinata, Hirofumi
- Ren, Hui
- Crane, Jason C.
- Tetreault, Jesse
- Guan, Jiahui
- Garrett, John W.
- Kaggie, Joshua D.
- Park, Jung Gil
- Dreyer, Keith
- Juluru, Krishna
- Rockenbach, Marcio Aloisio Bezerra Cavalcanti
- Linguraru, Marius George
- Haider, Masoom A.
- AbdelMaseeh, Meena
- Rieke, Nicola
- Damasceno, Pablo F.
- Wang, Pochuan
- Xu, Sheng
- Sriswasdi, Sira
- Park, Soo Young
- Grist, Thomas M.
- Buch, Varun
- Jantarabenjakul, Watsamon
- Wang, Weichung
- Tak, Won Young
- Li, Xiang
- Lin, Xihong
- Kwon, Young Joon
- Feng, Andrew
- Priest, Andrew N.
- Turkbey, Baris
- Glicksberg, Benjamin
- Bizzo, Bernardo
- Kim, Byung Seok
- Tor-Díez, Carlos
- Lee, Chia-Cheng
- Hsu, Chia-Jung
- Lin, Chin
- Hess, Christopher P.
- Oermann, Eric K.
- Sasaki, Hisashi
- Yang, Isaac
- Sohn, Jae Ho
- Murthy, Krishna Nand Keshava
- Fu, Li-Chen
- de Mendonça, Matheus Ribeiro Furtado
- Fralick, Mike
- Kang, Min Kyu
- Gangai, Natalie
- Vateekul, Peerapon
- Elnajjar, Pierre
- Hickman, Sarah
- Majumdar, Sharmila
- McLeod, Shelley L.
- Reed, Sheridan
- Gräf, Stefan
- Harmon, Stephanie
- Kodama, Tatsuya
- Puthanakit, Thanyawee
- Mazzulli, Tony
- Rakvongthai, Yothin
- Lee, Yu Rim
- Wen, Yuhong
- Gilbert, Fiona J.
- Flores, Mona G.
- Li, Quanzheng
- Venue
- Nature Medicine
- Published
- 2021-09-15
- Volume
- 27
- Issue
- 10
- Pages
- 1735-1743
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- PMC
- PMC9157510
- OpenAlex
- W3200840849
- Semantic Scholar
- 99b056a04fd4f98cad8b9987ff8d205fe62d786e
- Cited by
- 842
- References
- 68
- Citations by year
- 2026: 194 · 2025: 166 · 2024: 150 · 2023: 197 · 2022: 122 · 2021: 10
- FWCI
- 42.32
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Nature Medicine (publishedVersion, other-oa)
- Research Square (acceptedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Digital Access to Scholarship at Harvard (DASH) (Harvard University) (acceptedVersion)
- Europe PMC (PubMed Central) (submittedVersion, cc-by)
- PubMed Central (submittedVersion, cc-by)
- eScholarship (California Digital Library) (submittedVersion)
- Funders
- Foundation for the National Institutes of Health
- Doris Duke Charitable Foundation
- Colgate-Palmolive Company
- Brigham and Women's Hospital
- Massachusetts General Hospital
- American Association for Dental, Oral, and Craniofacial Research
- Nvidia
- National Center for Theoretical Sciences
- Children's National Hospital
- Lunit
- Cancer Research UK (26884)
- National Institute for Health and Care Research (NF-SI-0515-10067)
- Department of Health and Social Care
- University of Cambridge
- Chulalongkorn University
- Cambridge University Hospitals
- Ministry of Science and Technology, Taiwan
- Centre d'Imagerie BioMédicale
- National Taiwan University
- National Institutes of Health (COVID-19)
- Genentech
- University of California, San Francisco
- National Health Insurance Administration
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital
- Engineering and Physical Sciences Research Council (EP/N014588/1)
- Faculty of Medicine, Chulalongkorn University
- NIHR Cambridge Biomedical Research Centre
- National Heart, Lung, and Blood Institute (R01HL141237, R42HL145669)
- National Cancer Institute (P30CA008748, ZIDBC011242)
- National Institute of Allergy and Infectious Diseases (COVID-19)
- U.S. National Library of Medicine (R01LM013151)
- NIH Clinical Center (ZIACL040015)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- federated learning, COVID-19 pandemic, clinical outcome prediction, chest radiography, electronic health records, mechanical ventilation prediction, mortality prediction, model generalization, vital signs, laboratory findings
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.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
