The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index; none of the 1 sources its claims cite is checked for support yet.
Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19
Open accessPublished version of a preprint
Abstract
Machine learning (ML) models require large datasets which may be siloed across different healthcare institutions. Using federated learning, a ML technique that avoids locally aggregating raw clinical data across multiple institutions, we predict mortality within seven days in hospitalized COVID-19 patients. Patient data was collected from Electronic Health Records (EHRs) from five hospitals within the Mount Sinai Health System (MSHS). Logistic Regression with L1 regularization (LASSO) and Multilayer Perceptron (MLP) models were trained using local data at each site, a pooled model with combined data from all five sites, and a federated model that only shared parameters with a central aggregator. Both the federated LASSO and federated MLP models performed better than their local model counterparts at four hospitals. The federated MLP model also outperformed the federated LASSO model at all hospitals. Federated learning shows promise in COVID-19 EHR data to develop robust predictive models without compromising patient privacy.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This study used federated learning to predict 7-day mortality among 4,029 hospitalized COVID-19 patients across five Mount Sinai Health System hospitals, comparing local, pooled, and federated LASSO and MLP models. Federated models generally improved on local models, and federated MLP often performed best, while pooled LASSO remained stronger than federated LASSO.
Key findings
- In 4,029 COVID-19-positive patients, 7-day mortality prevalence differed significantly across hospitals (p<0.001), ranging from 5.6% to 24.2%.
- Federated LASSO outperformed local LASSO at all sites except MSQ, with AUC-ROC 0.693–0.805; pooled LASSO outperformed federated LASSO at all five sites, with AUC-ROC 0.736–0.822.
- Federated MLP surpassed federated LASSO at all sites and consistently outperformed all other tested models at all hospitals except MSB; local MLP outperformed local LASSO at all hospitals.
- Adding Gaussian noise to federated MLP decreased performance at all sites except MSQ; AUC-ROC ranged 0.796–0.834 without noise and 0.767–0.830 with noise.
Methods
- Data came from Epic EHRs of five MSHS hospitals in NYC: MSB (n=611), MSH (n=1644), MSM (n=749), MSQ (n=540), and MSW (n=485); primary outcome was mortality within seven days of admission.
- LASSO and MLP models were trained locally at each site, pooled across all sites, and federated via parameter sharing with a central aggregator using federated averaging; no raw data were shared.
- Models were evaluated with 10-fold stratified cross-validation, using AUC-ROC averaged across folds; Gaussian noise experiments simulated federated learning in practice.
Limitations
- Stated: data were limited to MSHS hospitals in NYC, which may limit generalizability; the work focused on principle rather than an operational deployment and did not address load balancing, convergence, or scaling; only clinical data and two classifiers were used; identical MLP architectures were used across strategies for comparison but could have been further optimized.
- Evident from the text: there was no external validation outside the same health system, and some sites had small samples and marked differences in mortality prevalence (e.g., MSQ n=540, 23.0%; MSW n=485, 5.6%), which may affect site-level comparisons.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 of 1 cited sources checked · 0 supported · 0 flagged
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 found significant differences across hospitals in the proportion of outcome, specifically mortality within seven days (p<0.001), which ranged from 5.6% to 24.2% (Table 1).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Intercohort Comparisons
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA 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
“There were also significant differences in gender (p=0.004), age (p<0.001), ethnicity (p<0.001), and race (p<0.001).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Intercohort Comparisons
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA 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 found significant differences in the majority of key clinical features such as past medical history like asthma (p<0.001) and relevant lab tests including white blood cell counts (p<0.001; Supplementary Table 1).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Intercohort Comparisons
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe 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
“MSQ was the only hospital where federated LASSO performed slightly worse than the local model with a difference of 0.04 in AUC-ROC, which may be attributed to a low sample size of 540 patients and a high mortality prevalence of 23.0% compared to other sites.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Strength:plain· not yet calibratedn = 540Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe 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
“Federated MLP also outperformed pooled MLP at all sites which might be due to the experimental condition where the same underlying architecture was used for all MLP models.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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 metrics were similar to federated MLP without noise insertion (Supplemental Figure 2).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
“Gaussian noise introduced into federated MLP led to decreased performance at all sites except MSQ, where both had AUC-ROCs of 0.822.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Effect of Gaussian Noise
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA 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
“Federated MLP outperformed local MLP and federated LASSO at all hospitals.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
“An average difference of 0.013 in AUC-ROC across all hospitals in these two models demonstrates that noise may be inserted to increase data security without severely compromising federated model performance.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe 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
“Local MLP outperformed local LASSO at all hospitals.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Cross-model Comparisons
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA 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
“While performance varied slightly among both classifiers in different experiments, federated MLP consistently outperformed all other tested models at all hospitals except MSB.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Cross-model Comparisons
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
“AUC-ROCs ranged from 0.796 to 0.834 in federated MLP without noise and 0.767–0.830 in federated MLP with noise (Supplemental Figure 1).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Effect of Gaussian Noise
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA 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
“Federated MLP surpassed federated LASSO at all sites.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Cross-model Comparisons
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
“However, at MSW, local LASSO severely underperformed in comparison to federated LASSO, with a difference of 0.351.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
“Collectively, these results exhibit the potential of federated learning to overcome drawbacks of fragmented local models.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
“An average difference of 0.013 in AUC-ROC across all hospitals in these two models demonstrates that noise may be inserted to increase data security without severely compromising federated model performance.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Rests on an assumption: Adding Gaussian noise to federated model parameters increases data security.
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
“Federated learning shows promise in COVID-19 EHR data to develop robust predictive models without compromising patient privacy.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > Abstract
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“While it has been proposed, to our knowledge there are no published studies that implement and assess the utility of federated learning to predict COVID-19 outcomes from Electronic Health Record (EHR) data.[17]”
- Also stated in: § DISCUSSION · hedged
“To our knowledge, this is the first study to evaluate the efficacy of applying federated learning to predict mortality for COVID-19 using clinical data from EHRs.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > INTRODUCTION > Background and Significance
What the sources say
- Not checked yetcites [17] Raisaro JL , Marino F , Troncoso-Pastoriza J , et al. SCOR: A secure international informatics infrastructure to investigate COVID-19. Journal of the American Medical Informatics Association 2020. source
Load-bearingStrength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § DISCUSSION · hedged
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
“With disparate patient characteristics per hospital in terms of demographics, outcomes, sample size, and lab values, this study reflects a real-world scenario where federated learning can be leveraged for hospitals with diverse patient populations.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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 pattern emphasizes the benefit of federated learning for sites with small sample sizes and large class imbalance.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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 demonstrated that federated learning models outperformed locally trained models to predict mortality.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > CONCLUSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- It may state two separate claims as one. 6
- Probably not a substantial claim. 8
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
“Both the federated LASSO and federated MLP models performed better than their local model counterparts at four hospitals.”
- Also stated in: § DISCUSSION · plain
“The primary findings of this study demonstrate that federated MLP and LASSO models outperformed their respective local models at most sites.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > Abstract
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Also stated in: § DISCUSSION · plain
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
“Federated LASSO outperformed the site’s local LASSO at all sites except MSQ, with AUC-ROC ranging from 0.693 to 0.805.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Learning Framework Comparisons
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“LASSO pooled outperformed federated LASSO at all five sites and had AUC-ROCs ranging from 0.736 to 0.822.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > RESULTS > Learning Framework Comparisons
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“MSW had the lowest sample size of all hospitals at 485 and the lowest COVID-19 mortality prevalence of 5.6%.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
“All models were trained and evaluated using 10-fold stratified cross validation.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > MATERIALS AND METHODS > Experimental Evaluation
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
“To simulate federated learning in practice, we also performed experiments with the addition of Gaussian noise (see Supplementary Materials).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > MATERIALS AND METHODS > Study Design
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
“First, data collection was limited to MSHS hospitals in NYC. This may limit model generalizability to hospitals in other regions.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > DISCUSSION
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
“To promote replicability, we placed our study within the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines (Supplementary Table 3) and released our code under the GPLv3 license (Supplementary Materials).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > MATERIALS AND METHODS > Study Design
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. 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
“Federated learning is an effective method to share ML models without jeopardizing patient privacy.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > CONCLUSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. 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
“Through this technique, federated models did not receive any raw data.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > MATERIALS AND METHODS > Model Development and Selection
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
“For consistency and to enable direct comparisons, each MLP model was built with the same architecture.”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > MATERIALS AND METHODS > Model Development and Selection
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
“Due to varying prevalence across hospitals, we assessed multiple class balancing techniques (Supplementary Table 2).”
§ Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19 > MATERIALS AND METHODS > Study Design
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
Adding Gaussian noise to federated model parameters increases data security.
“An average difference of 0.013 in AUC-ROC across all hospitals in these two models demonstrates that noise may be inserted to increase data security without severely compromising federated model performance.”
The paper relies on this without support.
The pooled model, trained on combined data from all sites, represents an ideal framework for comparison.
“Although the pooled model is not practically feasible, it represents an ideal framework.”
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?
In the citing paper
“The MLP federated model performed better than the MLP local model at all five hospitals.”
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 [92]
In the citing paper
“The LASSO federated model outperformed the LASSO local model at three hospitals.”
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 [92]
In the citing paper
“The MLP federated model performed better than the MLP local model at all five hospitals.”
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 [91]
In the citing paper
“In this case, FL devised a privacy-preserving approach that does not require the transfer of sensitive data from the source, instead of training local models with their own data and then sharing results with the global network [209].”
From Federated learning-based AI approaches in smart healthcare: Concepts, taxonomies, challenges and open issues (2023) · cites this paper as [209]
Citations
Cites
Wu, Z., & McGoogan, J. M. (2020) · JAMA · doi:10.1001/jama.2020.2648 · Cited by 17,016
An interactive web-based dashboard to track COVID-19 in real time
Dong, E., Du, H., & Gardner, L. (2020) · The Lancet Infectious Diseases · doi:10.1016/s1473-3099(20)30120-1 · Cited by 10,048
Pathological findings of COVID-19 associated with acute respiratory distress syndrome
Xu, Z., Shi, L., Wang, Y., Zhang, J., Huang, L., Zhang, C., Liu, S., Zhao, P., Liu, H., Zhu, L., et al. (2020) · The Lancet Respiratory Medicine · doi:10.1016/s2213-2600(20)30076-x · Cited by 8,545
Self-citationLauer, S. A., Grantz, K. H., Bi, Q., Jones, F. K., Zheng, Q., Meredith, H. R., Azman, A. S., Reich, N. G., & Lessler, J. (2020) · Annals of Internal Medicine · doi:10.7326/m20-0504 · Cited by 5,970
CT Imaging Features of 2019 Novel Coronavirus (2019-nCoV)
Chung, M., Bernheim, A., Mei, X., Zhang, N., Huang, M., Zeng, X., Cui, J., Xu, W., Yang, Y., Fayad, Z. A., et al. (2020) · Radiology · doi:10.1148/radiol.2020200230 · Cited by 2,751
Self-citationCOVID-19 and cardiovascular disease
Clerkin, K. J., Fried, J. A., Raikhelkar, J., Sayer, G., Griffin, J. M., Masoumi, A., Jain, S. S., Burkhoff, D., Kumaraiah, D., Rabbani, L., et al. (2020) · Circulation · doi:10.1161/circulationaha.120.046941 · Cited by 1,738
Federated Learning for Healthcare Informatics
Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2021) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-020-00082-4 · Cited by 1,542 · cited 1×
“predictions that may not be generalizable.[14] Briefly, federated learning allows for decentralized refinement of independently built ML models.”
BackgroundSelf-citationFederated Learning for Healthcare Informatics
Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2019) · arXiv · doi:10.48550/arxiv.1911.06270 · Cited by 1,538
Self-citationArtificial intelligence–enabled rapid diagnosis of patients with COVID-19
Mei, X., Lee, H.-C., Diao, K.-Y., Huang, M., Lin, B., Liu, C., Xie, Z., Ma, Y., Robson, P. M., Chung, M., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0931-3 · Cited by 1,084 · cited 1×
“[2-11] Large-scale initiatives such as the National COVID Cohort Collaborative and the 4CE Consortium have joined globally distributed hospitals to examine association analyses, but meta-analysis does not allow joint machine learning from diverse patient data.”
BackgroundSelf-citationParanjpe, I., Fuster, V., Lala, A., Russak, A. J., Glicksberg, B. S., Levin, M. A., Charney, A. W., Narula, J., Fayad, Z. A., Bagiella, E., et al. (2020) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2020.05.001 · Cited by 918
Self-citation
Flagged first, then by citations
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
Federated Learning for Healthcare Informatics
Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2021) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-020-00082-4 · Cited by 1,542
Self-citationFederated learning for predicting clinical outcomes in patients with COVID-19
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., et al. (2021) · Nature Medicine · doi:10.1038/s41591-021-01506-3 · Cited by 842
“FL has already shown promise in recent medical imaging applications 40–43 , including in COVID-19 analysis 8,44,45 .”
BackgroundSelf-citationAlgorithmic fairness in artificial intelligence for medicine and healthcare
Chen, R. J., Wang, J. J., Williamson, D. F. K., Chen, T. Y., Lipkova, J., Lu, M. Y., Sahai, S., & Mahmood, F. (2023) · Nature Biomedical Engineering · doi:10.1038/s41551-023-01056-8 · Cited by 750
Federated learning for healthcare: Systematic review and architecture proposal
Antunes, R. S., André da Costa, C., Küderle, A., Yari, I. A., & Eskofier, B. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501813 · Cited by 595
Metadata
- Authors
- Vaid, A., Jaladanki, S. K., Xu, J., Teng, S., Kumar, A., Lee, S., Somani, S., Paranjpe, I., Freitas, J. K. D., Wanyan, T., Johnson, K. W., Bicak, M., Klang, E., Kwon, Y. J., Costa, A., Zhao, S., Miotto, R., Charney, A. W., Böttinger, E., Fayad, Z. A., Nadkarni, G. N., Wang, F., & Glicksberg, B. S.
- Affiliations
- Icahn School of Medicine at Mount Sinai (US)
- Weill Cornell Medicine (US)
- Indiana University Bloomington (US)
- Hasso Plattner Institute (DE)
- Corresponding author
- Glicksberg, Benjamin S
- ORCID
- Vaid, Akhil
- Jaladanki, Suraj K
- Xu, Jie
- Teng, Shelly
- Kumar, Arvind
- Lee, Samuel
- Somani, Sulaiman
- Paranjpe, Ishan
- Freitas, Jessica K De
- Wanyan, Tingyi
- Johnson, Kipp W
- Bicak, Mesude
- Klang, Eyal
- Kwon, Young Joon
- Costa, Anthony
- Zhao, Shan
- Miotto, Riccardo
- Charney, Alexander W
- Böttinger, Erwin
- Fayad, Zahi A
- Nadkarni, Girish N
- Wang, Fei
- Glicksberg, Benjamin S
- Venue
- JMIR Medical Informatics
- Publisher
- openRxiv
- Published
- 2020-08-14
- Volume
- 9
- Issue
- 1
- Pages
- e24207-e24207
- ISSN
- 2291-9694 (ISSN-L)
- PMC
- PMC7430624
- OpenAlex
- W3118996476
- Cited by
- 253
- References
- 20
- Citations by year
- 2026: 33 · 2025: 40 · 2024: 43 · 2023: 54 · 2022: 47 · 2021: 32 · 2020: 4
- FWCI
- 15.49
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Medical Informatics (publishedVersion, cc-by)
- medRxiv (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- publish.UP (University of Potsdam) (submittedVersion, cc-by)
- Funders
- National Institutes of Health (UL1TR001433)
- National Center for Advancing Translational Sciences (U54 TR001433-05)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Health Sciences › Medicine › Infectious Diseases › COVID-19 Clinical Research Studies
- Keywords
- federated learning, COVID-19 pandemic, mortality prediction, hospitalized patients, electronic health records, data privacy, model generalization, LASSO, multilayer perceptron
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 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
