Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Objectives: We propose a one-shot, privacy-preserving distributed algorithm to perform logistic regression (ODAL) across multiple clinical sites. Materials and Methods: ODAL effectively utilizes the information from the local site (where the patient-level data are accessible) and incorporates the first-order (ODAL1) and second-order (ODAL2) gradients of the likelihood function from other sites to construct an estimator without requiring iterative communication across sites or transferring patient-level data. We evaluated ODAL via extensive simulation studies and an application to a dataset from the University of Pennsylvania Health System. The estimation accuracy was evaluated by comparing it with the estimator based on the combined individual participant data or pooled data (ie, gold standard). Results: Our simulation studies revealed that the relative estimation bias of ODAL1 compared with the pooled estimates was <3%, and the ratio of standard errors was <1.25 for all scenarios. ODAL2 achieved higher accuracy (with relative bias <0.1% and ratio of standard errors <1.05). In real data analysis, we investigated the associations of 100 medications with fetal loss during pregnancy. We found that ODAL1 provided estimates with relative bias <10% for 85% of medications, and ODAL2 has relative bias <10% for 99% of medications. For communication cost, ODAL1 requires transferring p numbers from each site to the local site and ODAL2 requires transferring (p×p+p) numbers from each site to the local site, where p is the number of parameters in the regression model. Conclusions: This study demonstrates that ODAL is privacy-preserving and communication-efficient with small bias and high statistical efficiency.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“Federated learning is a viable method to connect EHR data from medical institutions, allowing them to share their experiences, and not their data, with a guarantee of privacy [9, 25, 34, 45, 65, 82].”
From Federated Learning for Healthcare Informatics (2021) · cites this paper as [25]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Estimates of global seasonal influenza-associated respiratory mortality: a modelling study
Iuliano, A. D., Roguski, K. M., Chang, H. H., Muscatello, D. J., Palekar, R., Tempia, S., Cohen, C., Gran, J. M., Schanzer, D., Cowling, B. J., et al. (2018) · The Lancet · doi:10.1016/s0140-6736(17)33293-2 · Cited by 3,019
Self-citationA systematic review of barriers to data sharing in public health
van Panhuis, W. G., Paul, P., Emerson, C., Grefenstette, J., Wilder, R., Herbst, A. J., Heymann, D., & Burke, D. S. (2014) · BMC Public Health · doi:10.1186/1471-2458-14-1144 · Cited by 579
Achieving a Nationwide Learning Health System
Friedman, C. P., Wong, A. K., & Blumenthal, D. (2010) · Science Translational Medicine · doi:10.1126/scitranslmed.3001456 · Cited by 539
Communication-Efficient Distributed Statistical Inference
Jordan, M. I., Lee, J. D., & Yang, Y. (2019) · Journal of the American Statistical Association · doi:10.1080/01621459.2018.1429274 · Cited by 442 · cited 3×
“…data from one of the sites (termed as the local site) are accessible, Duan et al 15 adopted the surrogate likelihood approach in Jordan et al 13 and constructed the following first-order surrogate likelihood function as an approximation of the global likelihood function: where (cid:2) b is…”
MethodInfluentialCharacterizing treatment pathways at scale using the OHDSI network
Hripcsak, G., Ryan, P. B., Duke, J. D., Shah, N. H., Park, R. W., Huser, V., Suchard, M. A., Schuemie, M. J., DeFalco, F. J., Perotte, A., et al. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1510502113 · Cited by 326 · cited 1×
“In addition, tools are made available in an open source framework to enable further advancement of analytic methods.(3,8,9) In many situations, it is not feasible to share patient-level data across sites or provide data to a central site, especially if sites exist in different countries.”
MethodSelf-citationGrid Binary LOgistic REgression (GLORE): building shared models without sharing data
Wu, Y., Jiang, X., Kim, J., & Ohno-Machado, L. (2012) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2012-000862 · Cited by 173 · cited 1×
“For example, Wu et al 10 proposed an iterative algorithm for distributed logistic regression named GLORE (Grid binary LOgistic Regression) and successfully deployed it to the multi-institutional pSCANNER (patient-centered Scalable National Network for Effectiveness Research) network.”
MethodSchuemie, M. J., Hripcsak, G., Ryan, P. B., Madigan, D., & Suchard, M. A. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1708282114 · Cited by 163 · cited 1×
“3,8,9 In many situations, it is not feasible to share patient-level data across sites or provide data to a central site, especially if sites exist in different countries.”
BackgroundSelf-citationWebDISCO: a web service for distributed cox model learning without patient-level data sharing
Lu, C.-L., Wang, S., Ji, Z., Wu, Y., Xiong, L., Jiang, X., & Ohno-Machado, L. (2015) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv083 · Cited by 141 · cited 1×
“11 These algorithms are lossless, yet the communication cost, which is characterized by the total number of bytes transferred per iteration and number of iterations needed, is often high, and therefore could lead to operational difficulty.”
BackgroundDecker, S. L., Jamoom, E. W., & Sisk, J. E. (2012) · Health Affairs · doi:10.1377/hlthaff.2011.1121 · Cited by 132 · cited 1×
“The last few decades have seen large-scale adoption of EHRs throughout the United States, including providers in rural communities,(1) although adoption in these settings was slower than that among larger, urban medical centers.(2) This availability of clinical data from EHRs throughout the United States, from small-s…”
BackgroundRegression Cubes with Lossless Compression and Aggregation
Chen, Y., Dong, G., Han, J., Pei, J., Wah, B. W.-S., & Wang, J. (2006) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2006.196 · Cited by 76 · cited 2×
“However, for other commonly used statistical models without close-form solutions, such as logistic regression or the Cox proportional hazards model, the analogy of Chen et al 12 is not available.”
BackgroundMethodSelf-citation
Research works printed but not linked: 2
- 14. Wang J, Kolar M, Srebro N, Zhang T. Efficient distributed learning with sparsity. In proceedings of the 34th International Conference on Machine Learning-Volume 70; 2017. *
- 15. Duan R, Boland MR, Moore JH, Chen Y.. ODAL: A One-Shot Distributed Algorithm to Perform Logistic Regressions on Electronic Health Records Data from Multiple Clinical Sites. Singapore: World Scientific; 2019. [[PMC free article](/articles/PMC6417819/)] [[PubMed](https://pubmed.ncbi.nlm.nih.gov/30864308/)] [[Google Scholar](https://scholar.google.com/scholar_lookup?title=ODAL:%20A%20One-Shot%20Distributed%20Algorithm%20to%20Perform%20Logistic%20Regressions%20on%20Electronic%20Health%20Records%20Data%20from%20Multiple%20Clinical%20Sites&author=R%20Duan&author=MR%20Boland&author=JH%20Moore&author=Y.%20Chen&publication_year=2019&)] * 16.R Core Team. R: A Language and Environment for Statistical Com‐Puting. Vienna: R Foundation for Statistical Computing; 2017. <https://www.R-project.org>. [[Google Scholar](https://scholar.google.com/scholar_lookup?title=R:%20A%20Language%20and%20Environment%20for%20Statistical%20Com%E2%80%90Puting&publication_year=2017&)] *
Cited by
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
“Federated learning is a viable method to connect EHR data from medical institutions, allowing them to share their experiences, and not their data, with a guarantee of privacy [8,27,74,19,57,37].”
MethodFederated 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
Why Is the Electronic Health Record So Challenging for Research and Clinical Care?
Holmes, J. H., Beinlich, J., Boland, M. R., Bowles, K. H., Chen, Y., Cook, T. S., Demiris, G., Draugelis, M., Fluharty, L., Gabriel, P. E., et al. (2021) · Methods of Information in Medicine · doi:10.1055/s-0041-1731784 · Cited by 117
“57,58 This approach aims to minimize the number of communications among investigators at different clinical sites, while seeking estimates that are close to the analysis results from pooled data.”
ResultSelf-citationMorin, O., Vallières, M., Braunstein, S. E., Ginart, J. B., Upadhaya, T., Woodruff, H. C., Zwanenburg, A., Chatterjee, A., Villanueva-Meyer, J. E., Valdés, G., et al. (2021) · Nature Cancer · doi:10.1038/s43018-021-00236-2 · Cited by 133
Federated learning: Applications, challenges and future directions
Bharati, S., Mondal, M. R. H., Podder, P., & Prasath, V. B. S. (2022) · International Journal of Hybrid Intelligent Systems · doi:10.3233/his-220006 · Cited by 198
“maintaining the confidentiality of the data itself [108-113].”
Electronic health records and polygenic risk scores for predicting disease risk
Li, R., Chen, Y., Ritchie, M. D., & Moore, J. H. (2020) · Nature Reviews Genetics · doi:10.1038/s41576-020-0224-1 · Cited by 135
Self-citationFederated Learning for Electronic Health Records
Dang, T. K., Lan, X., Weng, J., & Feng, M. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3514500 · Cited by 85
Heterogeneity-aware and communication-efficient distributed statistical inference
Duan, R., Ning, Y., & Chen, Y. (2021) · Biometrika · doi:10.1093/biomet/asab007 · Cited by 115
Self-citationFold-stratified cross-validation for unbiased and privacy-preserving federated learning
Bey, R., Goussault, R., Grolleau, F., Benchoufi, M., & Porcher, R. (2020) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa096 · Cited by 71
“Federated learning appears as a promising privacy-enhancing technique that avoids single points of failure, and it is currently being developed and tested in various projects worldwide [26–30].”
BackgroundCS-MIA: Membership inference attack based on prediction confidence series in federated learning
Gu, Y., Bai, Y., & Xu, S. (2022) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2022.103201 · Cited by 102
Kirienko, M., Sollini, M., Ninatti, G., Loiacono, D., Giacomello, E., Gozzi, N., Amigoni, F., Mainardi, L. T., Lanzi, P. L., & Chiti, A. (2021) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-021-05339-7 · Cited by 60
In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare
Topaloglu, M. Y., Morrell, E. M., Rajendran, S., & Topaloglu, U. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.746497 · Cited by 50
Decentralized Learning in Healthcare: A Review of Emerging Techniques
Shiranthika, C., Saeedi, P., & Bajić, I. V. (2023) · IEEE Access · doi:10.1109/access.2023.3281832 · Cited by 71
“They cover areas of medications [108], [109], [110], human emotions [108], activity recognition [111], [112], EEG classification [113], personalized wearable healthcare applications [111], patient hospitalization [114], patient mortality [114], and preterm birth data [115].”
BackgroundLi, S., Liu, P., Nascimento, G. G., Wang, X., Leite, F. R. M., Chakraborty, B., Hong, C., Ning, Y., Xie, F., Teo, Z. L., et al. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad170 · Cited by 66
Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous Data
Cai, T., Liu, M., & Yin, X. (2021) · Journal of the American Statistical Association · doi:10.1080/01621459.2021.1904958 · Cited by 63
“…of statistical methods have been developed for distributed analysis that satisfy the DataSHIELD constraint (see, e.g., Chen et al. 2006; Wu et al. 2012; Liu and Ihler 2014; Lu et al. 2015; Huang and Huo 2015; Han and Liu 2016; He et al. 2016; Zöller, Lenz, and Binder 2018; Duan et al. 2019, 2020).”
MethodDLMM as a lossless one-shot algorithm for collaborative multi-site distributed linear mixed models
Luo, C., Islam, M. N., Sheils, N. E., Buresh, J., Reps, J., Schuemie, M. J., Ryan, P. B., Edmondson, M. J., Duan, R., Tong, J., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-29160-4 · Cited by 46
“By considering a large, more diverse sample from multiple sites, we expect a more robust estimation, which bene fi ts general knowledge discovery 26,27 .”
BackgroundSelf-citationFederated causal inference in heterogeneous observational data
Xiong, R., Koenecke, A., Powell, M. A., Shen, Z., Vogelstein, J. T., & Athey, S. C. (2023) · Statistics in Medicine · doi:10.1002/sim.9868 · Cited by 62
ODACH: a one-shot distributed algorithm for Cox model with heterogeneous multi-center data
Luo, C., Duan, R., Naj, A. C., Kranzler, H. R., Bian, J., & Chen, Y. (2022) · Scientific Reports · doi:10.1038/s41598-022-09069-0 · Cited by 46
Self-citationNian, Y., Hu, X., Zhang, R., Feng, J., Du, J., Li, F., Bu, L., Zhang, Y., Chen, Y., & Tao, C. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-04934-1 · Cited by 41
“The total costs for health care, long-term care and hospital services for all Americans with AD/ADRD are estimated at 305 billion in 2020 [3].”
BackgroundSelf-citationLuo, C., Islam, M. N., Sheils, N. E., Buresh, J., Schuemie, M. J., Doshi, J. A., Werner, R. M., Asch, D. A., & Chen, Y. (2022) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocac067 · Cited by 30
Self-citationPrivacy-preserving harmonization via distributed ComBat
Chen, A. A., Luo, C., Chen, Y., Shinohara, R. T., Shou, H., & Initiative, T. A. D. N. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.118822 · Cited by 32
Self-citationFederated attention consistent learning models for prostate cancer diagnosis and Gleason grading
Kong, F., Wang, X., Xiang, J., Yang, S., Wang, X., Yue, M., Zhang, J., Zhao, J., Han, X., Dong, Y., et al. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.03.028 · Cited by 47
“Several studies have made notable progress in addressing the heterogeneity problem through the following approaches.”
Self-citationCentralized and Federated Models for the Analysis of Clinical Data
Li, R., Romano, J. D., Chen, Y., & Moore, J. H. (2024) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-122220-115746 · Cited by 39
“Although ODAL can be implemented with a minimum of one round of communication, it is often advised that a meta-analysis should be implemented for more accurate initial values than the local estimates in order to get superior performance.”
Self-citationEdmondson, M. J., Luo, C., Islam, M. N., Sheils, N. E., Buresh, J., Chen, Z., Bian, J., & Chen, Y. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104097 · Cited by 28
Self-citationCOMMUTE: Communication-efficient transfer learning for multi-site risk prediction
Gu, T., Lee, P. H., & Duan, R. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2022.104243 · Cited by 37
Self-citationPrivacy of electronic health records: a review of the literature
Gariépy-Saper, K., & Decarie, N. (2021) · Journal of the Canadian Health Libraries Association / Journal de l Association de bilbiothèques de la santé du Canada · doi:10.29173/jchla29496 · Cited by 28
“JCHLA / JABSC 42: 74-84 (2021) doi: 10.29173/jchla29496 Parks et al., 2017 No No No Yes No United States Research Paper Furusa & Coleman, 2018 No Yes Yes Yes No Zimbabwe Research Paper Hong et al., 2018 Yes Yes No Yes Yes No Literature Review Dong et al., 2018 No Yes No Yes No United States Viewpoint (Historical) Alaq…”
BackgroundInfluentialDistributed Cox proportional hazards regression using summary-level information
Li, D., Lu, W., Shu, D., Toh, S., & Wang, R. (2022) · Biostatistics · doi:10.1093/biostatistics/kxac006 · Cited by 24
Tong, J., Luo, C., Islam, M. N., Sheils, N. E., Buresh, J., Edmondson, M. J., Merkel, P. A., Lautenbach, E., Duan, R., & Chen, Y. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00615-8 · Cited by 36
Self-citationEdmondson, M. J., Luo, C., Duan, R., Maltenfort, M., Chen, Z., Locke, K., Justine Shults, A., Bian, J., Ryan, P. B., Forrest, C. B., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-99078-2 · Cited by 24
Self-citationYan, Z., Zachrison, K. S., Schwamm, L. H., Estrada, J., & Duan, R. (2023) · PLoS ONE · doi:10.1371/journal.pone.0280192 · Cited by 28
Self-citationFederated Adaptive Causal Estimation (FACE) of Target Treatment Effects
Han, L., Hou, J., Cho, K., Duan, R., & Cai, T. (2025) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2453249 · Cited by 90
“Most existing literature on federated learning has focused on regression and classification models (Chen et al. 2006; Li, Lin, and Li 2013; Chen and Xie 2014; Lee et al. 2017; Lian and Fan 2017; Wang et al. 2019; Duan et al. 2019).”
Self-citationLi, S., Miao, D., Wu, Q., Hong, C., D’Agostino, D., Li, X., Ning, Y., Shang, Y., Wang, Z., Liu, M., et al. (2024) · Health Data Science · doi:10.34133/hds.0196 · Cited by 29
Li, J., Tian, Y., Li, R., Zhou, T., Li, J., Ding, K., & Li, J. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102024 · Cited by 20
Li, H., Zang, C., Xu, Z., Pan, W., Rajendran, S., Chen, Y., & Wang, F. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01803-y · Cited by 23
Self-citationFedScore: A privacy-preserving framework for federated scoring system development
Li, S., Ning, Y., Ong, M. E. H., Chakraborty, B., Hong, C., Xie, F., Yuan, H., Liu, M., Buckland, D. M., Chen, Y., et al. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104485 · Cited by 14
“different existing FL frameworks, and for demonstration purpose, we have employed a one-shot privacy preserving distributed algorithm called ODAL2[44], which is communication-efficient and has been demonstrated to have low bias and high statistical efficiency[44].”
MethodInfluentialSelf-citationBoland, M. R., Davidson, L., Canelón, S. P., Meeker, J., Penning, T. M., Holmes, J. H., & Moore, J. H. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00494-5 · Cited by 18
Self-citationThe Use of Meta‐analysis in Pharmacoepidemiology
Berlin, J. A. (2000) · Wiley eBooks · doi:10.1002/0470842555.ch38 · Cited by 14
Self-citationCollaborative causal inference on distributed data
Kawamata, Y., Motai, R., Okada, Y., Imakura, A., & Sakurai, T. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.123024 · Cited by 14
“These methods operate with specific parametric models, such as linear (Toh et al., 2018, 2020), logistic (Duan et al., 2020), Poisson (Shu et al., 2019), and Cox (Shu et al., 2020, 2021).”
MethodFederated Causal Inference in Heterogeneous Observational DataPreprint
Xiong, R., Koenecke, A., Powell, M. A., Shen, Z., Vogelstein, J. T., & Athey, S. C. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3888599 · Cited by 25
Leveraging towards Privacy-preserving using Federated Machine Learning for Healthcare Systems
Gandhi, N., Mishra, S., Bharti, S. K., & Bhagat, K. (2021) · 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct52877.2021.9622730 · Cited by 11
Learning competing risks across multiple hospitals: one-shot distributed algorithms
Zhang, D., Tong, J., Jing, N., Yang, Y., Luo, C., Lu, Y., Christakis, D., Güthe, D., Hornig, M., Kelleher, K. J., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae027 · Cited by 13
Self-citationDuan, R., Chen, Z., Tong, J., Luo, C., Lyu, T., Tao, C., Maraganore, D. M., Bian, J., & Chen, Y. (2020) · medRxiv · doi:10.1101/2020.08.03.20167619 · Cited by 14
Self-citationEdge AI Empowered Personalized Privacy-Preserving Glucose Prediction with Federated Deep Learning
Yang, X., & Li, J. (2023) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom56612.2023.10472368 · Cited by 11
Li, S., Yan, M., Yuan, R., Liu, M., Liu, N., & Hong, C. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104780 · Cited by 15
Zhou, Z., Wang, N., Liu, J., Fu, J., & Deng, L. (2024) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.8257 · Cited by 8
Meta-Analysis and Federated Learning over Decentralized Distributed Research Networks
Lu, Y., Zhang, B., Tong, J., & Chen, Y. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-094441 · Cited by 11
Self-citationLiu, X., Duan, R., Luo, C., Ogdie, A., Moore, J. H., Kranzler, H. R., Bian, J., & Chen, Y. (2022) · Scientific Reports · doi:10.1038/s41598-022-14029-9 · Cited by 9
“…This approximation can be improved by further requiring the second-order gradient of L k (β) , which gives us the second-order surrogate function 22 where It is worth mentioning that, by collecting the second-order gradients from all sites, the resulting estimator is robust to the potential…”
BackgroundSelf-citationLi, R., Duan, R., Zhang, X., Lumley, T., Pendergrass, S. A., Bauer, C. R., Hakonarson, H. H., Carrell, D., Smoller, J. W., Wei, W., et al. (2021) · Nature Communications · doi:10.1038/s41467-020-20211-2 · Cited by 7
Self-citationWilson, J. R., Prevedello, L. M. S., Witiw, C. D., Flanders, A. E., & Colak, E. (2023) · Radiology Artificial Intelligence · doi:10.1148/ryai.230006 · Cited by 9
Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous DataPreprint
Cai, T., Liu, M., & Yin, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.06115 · Cited by 8
Lu, Y., Gu, T., & Duan, R. (2024) · Statistics in Biosciences · doi:10.1007/s12561-024-09449-2 · Cited by 10
“The spectrum of existing methodologies in federated learning spans from regression models [15–17], causal inference [18, 19] to more complicated deep neural networks [20, 21].”
Self-citationCollaborative Learning of Different Types of Healthcare Data From Heterogeneous IoT Devices
Zhao, L., Cai, L., & Lu, W.-S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3307675 · Cited by 8
“For example, Vepakomma et al. [18] and Xu et al. [19] adopted FL to address privacy concerns by avoiding the sharing of raw data or model details [20], [21].”
BackgroundLemyre, F. C., Lévesque, S., Domingue, M., Herrmann, K., & Éthier, J. (2024) · JMIR Medical Informatics · doi:10.2196/53622 · Cited by 11
Zhang, D., Tong, J., Stein, R. E., Lu, Y., Jing, N., Yang, Y., Boland, M. R., Luo, C., Baldassano, R. N., Carroll, R. J., et al. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104595 · Cited by 8
Self-citationWu, Q., Reps, J., Li, L., Zhang, B., Lu, Y., Tong, J., Zhang, D., Lumley, T., Brand, M. T., Zandt, M. V., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01781-1 · Cited by 8
“…on surrogate likelihood 15,16 for communication-ef fi cient distributed inference has motivated a sequence of few-shot federated learning algorithms for integrating RWD with various types of outcomes, including binary 17,18 , count 19 , zero-in fl ated counts 20 , and time-to-event outcomes 21,22 .”
Self-citationRare disease data stewardship in Canada
Bernier, A. (2020) · FACETS · doi:10.1139/facets-2020-0050 · Cited by 5
Tong, J., Shen, Y., Xu, A., He, X., Luo, C., Edmondson, M. J., Zhang, D., Lu, Y., Yan, C., Li, R., et al. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae075 · Cited by 5
Self-citationWeight aggregation methods for federated learning in healthcare - A comparative empirical analysis
Alluhaidan, T., & Josyula, D. P. (2024) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit60633.2024.10609860 · Cited by 8
“Duan et al. address data efficiency by introducing the privacy-preserving distributed algorithm ODAL, which allows for efficient logistic regression with less bias [6].”
BackgroundMethodInfluentialAdvancing Interpretable Regression Analysis for Binary Data: A Novel Distributed Algorithm Approach
Tong, J., Li, L., Reps, J., Lorman, V., Jing, N., Edmondson, M. J., Lou, X., Jhaveri, R. R., Kelleher, K. J., Pajor, N. M., et al. (2024) · Statistics in Medicine · doi:10.1002/sim.10250 · Cited by 3
Self-citationReview of Clinical Research Informatics
Solomonides, A. E. (2020) · Yearbook of Medical Informatics · doi:10.1055/s-0040-1701988 · Cited by 5
“A University of Pennsylvania-led team describes two performant algorithms [99, 100], differentiated by resource requirements and performance, which analyze data behind their home firewalls and aggregate statistical results, mainly regression models.”
BackgroundFederated Learning for Data Mining in Healthcare
Sharma, S., Kesarwani, A., Maheshwari, S., & Rai, B. K. (2022) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-85559-8_16 · Cited by 6
Yan, Z., Zachrison, K. S., Schwamm, L. H., Estrada, J. J., & Duan, R. (2022) · medRxiv · doi:10.1101/2022.03.07.22271469 · Cited by 4
Self-citationTraining Policy for Privacy-Preserving Logistic Regression in Federated Learning Environments
Cortés-Mendoza, J. M., Tchernykh, A. N., & González–Vélez, H. (2024) · International Conference on Federated Learning Technologies and Applications (FLTA) · doi:10.1109/flta63145.2024.10839854 · Cited by 3
Jing, N., Liu, X., Wu, Q., Rao, S., Mejías, A., Maltenfort, M., Schuchard, J., Lorman, V., Razzaghi, H., Webb, R. D., et al. (2024) · medRxiv · doi:10.1101/2024.01.26.24301827 · Cited by 3
Self-citationpda: Privacy-Preserving Distributed Algorithms
Duan, R., Edmondson, M. J., Tong, J., Liu, X., Locke, K., Hu, J., Zhang, B., Shen, Y., Wang, Y., Lu, Y., et al. (2020) · doi:10.32614/cran.package.pda · Cited by 3
Self-citationHuang, P., Li, S., & Song, X. (2024) · Statistics and Computing · doi:10.1007/s11222-024-10523-4 · Cited by 2
IoT privacy for the transmission of data in the field of health using blockchain
Askari, A., Bardsiri, A. K., & Ghanatghestani, M. M. (2024) · Archives de l'Institut d'Hessarek. · doi:10.61186/jsdp.21.3.149 · Cited by 2
Developing federated time-to-event scores using heterogeneous real-world survival data
Li, S., Wang, Z., Shang, Y., Wu, Q., Hong, C., Ning, Y., Miao, D., Ong, M. E. H., Chakraborty, B., & Liu, N. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111084 · Cited by 6
“…be realized through a variety of existing FL frameworks, including both engineering-based[40], model-agnostic FL frameworks like FedAvg[41] that requires multiple iterations, and statistics-based[40], model specific FL techniques[42–47] that necessitate only one or a few rounds of communication.”
Lian, Y., Jiang, X., & Long, Q. (2024) · medRxiv · doi:10.1101/2024.09.15.24313479 · Cited by 2
A Distributed Regression Analysis Application Package Using SAS
Her, Q. L., Li, D., Vilk, Y., Young, J. G., Zhang, Z., Malenfant, J., Malek, S., & Toh, S. (2024) · Statistics in Biosciences · doi:10.1007/s12561-024-09445-6 · Cited by 1
Federated Learning in Healthcare: Improving Collaboration and Privacy
Kovačević, A. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-3077-6_28 · Cited by 3
Huang, X., Zhu, S., Lv, Z., Zhou, Q., & Kou, T. (2025) · Digital Health · doi:10.1177/20552076251353694 · Cited by 3
Federated Mixed Effects Logistic Regression Based on One‐Time Shared Summary Statistics
Limpoco, M. A. A., Faes, C., & Hens, N. (2025) · Biometrical Journal · doi:10.1002/bimj.70080 · Cited by 2
“However, it requires access to the full individual-level data of at least one data provider, or, alternatively, sharing gradients of the likelihood among the data providers must be possible.”
Federated Learning Applications in Healthcare Informatics: A Comprehensive Review
Howlader, S. M. R. K., Liu, L., Chen, X., Wu, H., Yuan, B., & Bhattacharjee, A. (2026) · ACM Computing Surveys · doi:10.1145/3809485 · Cited by 5
“Numerous studies have been conducted [21, 39, 71], and several applications have been developed using FL in healthcare in recent years [53, 110].”
Kundu, R., Salvatore, M., Patel, K. K., Ohno-Machado, L., Cho, H., Shi, X., & Mukherjee, B. (2026) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocag083 · Cited by 1
Chen, Y., Tong, J., Lu, Y., Duan, R., Luo, C., Suchard, M. A., Ryan, P. B., Williams, A. E., Holmes, J. H., Moore, J. H., et al. (2026) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocag119 · Cited by 1
“14,19 Furthermore, the PDA framework supports a broad spectrum of analytical tasks, including comparative effectiveness research, causal inference, target trial emulation, health disparities assessment, and health policy evaluation.”
Self-citationLee, K., Kumagai, C., Komuro, M., Miyo, K., & Hoshimoto, H. (2026) · Journal of Medical Systems · doi:10.1007/s10916-026-02447-5 · Cited by 1
“In recent years, distributed analytical approaches such as federated learning, which enable the integration and analysis of EHR data across multiple healthcare institutions, have gained increasing attention, highlighting the grow - ing importance of multicenter data research [1, 2].”
A Lightweight Federated Learning Framework in a One-way Active Communication Environment
Li, W., & Cheng, X. (2022) · Euro-Asia Conference on Frontiers of Computer Science and Information Technology (FCSIT) · doi:10.1109/fcsit57414.2022.00031 · Cited by 1
Federated statistical analysis: non-parametric testing and quantile estimation
Becher, O., Marcus-Kalish, M., & Steinberg, D. M. (2023) · Frontiers in Applied Mathematics and Statistics · doi:10.3389/fams.2023.1267034 · Cited by 1
Tailored Federated Learning: Leveraging Direction Regulation and Knowledge Distillation
Tang, H., Li, C., Yu, H., Kamei, S., & Morimoto, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0814-0_18 · Cited by 1
Liang, C. J., Luo, C., Kranzler, H. R., Bian, J., & Chen, Y. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae313 · Cited by 5
Self-citationHartman, N., & He, K. (2025) · Statistics in Biosciences · doi:10.1007/s12561-025-09496-3 · Cited by 1
The Use of Meta‐analysis in Pharmacoepidemiology
Crowe, B. J., Evans, S. J. W., Xia, H. A., & Berlin, J. A. (2021) · Wiley eBooks · doi:10.1002/9781119701101.ch20 · Cited by 1
Self-citationTong, J., Luo, C., Islam, M. N., Sheils, N. E., Buresh, J., Edmondson, M. J., Merkel, P. A., Lautenbach, E., Duan, R., & Chen, Y. (2020) · medRxiv · doi:10.1101/2020.11.17.20220681
Self-citationAI training for automated data extraction from clinical records
Racedo, J. (2021) · instname:Universidad de los Andes
FedTA: Locally-Differential Federated Learning with Top-k Mechanism and Adam Optimization
Li, Y., Wang, G., Peng, T., & Feng, G. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-0272-9_26 · Cited by 2
Statistical Analysis—Meta-Analysis/Reproducibility
Edmondson, M. J., Luo, C., & Chen, Y. (2023) · Springer eBooks · doi:10.1007/978-3-031-36678-9_8 · Cited by 2
Self-citationLemyre, F. C., Lévesque, S., Domingue, M., Herrmann, K., & Éthier, J. (2023) · medRxiv · doi:10.1101/2023.12.21.23300389
“Among the additional 12 articles obtained through the assessment of references from included articles, it is observed that most of them did not mention statistical inference or related terms in their abstracts (e.g., [14][15][41]).”
BackgroundMethodical IoT-based information system in healthcare industry
Siddiqui, A. T., & Pathak, P. C. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-15452-2.00006-6
Just-in-Time and Real-Time Bug-Inducing Commit Prediction Using a Federated Learning Approach
Islam, M. R., Roy, B., Hassan, M. M., & Nikanjam, A. (2024) · IEEE International Conference on Collaborative Advances in Software and Computing (CASCON) · doi:10.1109/cascon62161.2024.10838190
Consideration of Sociodemographics in Sepsis Risk Prediction: Implications and Next Steps
Ashana, D. C., & Parker, W. F. (2025) · Critical Care Medicine · doi:10.1097/ccm.0000000000006777
Lemyre, F. C., Domingue, M., Morissette, J.-P., Burgun, A., & Éthier, J. (2025) · medRxiv · doi:10.1101/2025.07.15.25331536
Privacy-Enhancing Sequential Learning under Heterogeneous Selection Bias in Multi-Site EHR DataPreprint
Kundu, R., Shi, X., Patel, K. K., Lucila Ohno-machado, A., Salvatore, M., Song, P. X. ‐., & Mukherjee, B. (2025) · medRxiv · doi:10.1101/2025.09.26.25336642
“Likelihood-based federated approaches—such as the surrogate likelihood method by Jordan et al. (2019) and its applications to logistic regression (Duan et al., 2019, 2020, 2022) offer efficient and scalable estimation of global parameters under strict data-sharing constraints.”
Li, S., Ouyang, G., & Li, H. (2025) · Statistics and Computing · doi:10.1007/s11222-025-10770-z
Communication-Efficient Distributed Estimation and Computation Using Skew-Normal Distribution
Wang, D., Liu, Y., & Ma, C. (2025) · Acta Mathematica Sinica English Series · doi:10.1007/s10114-025-3520-z
Self-citationIntegrating high-dimensional censored data under privacy constraints via localized computations
Huang, B., Liu, Y., & Ye, X. (2025) · Lifetime Data Analysis · doi:10.1007/s10985-025-09677-8
“To further exploit data utilization, studies from Duan et al. ( 2019 ) and Duan et al. ( 2020 ) proposed one-shot distributed algorithms for logistic regression based on the surrogate likelihood approach, leveraging the local full data on the lead site and statistics from other sites.”
Self-citationNian, Y., Hu, X., Zhang, R., Feng, J., Du, J., Li, F., Bu, L., Zhang, Y., Chen, Y., & Tao, C. (2022) · Figshare · doi:10.6084/m9.figshare.21256959
Self-citationLemyre, F. C., Domingue, M., Morissette, J.-P., Burgun, A., & Éthier, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-41936-y
“In the literature, a distributed algorithm is often qualified as privacy-preserving if it avoids the direct transmission of individual-level data (see e.g. Duan et al. 22 stating “The algorithms are privacy-preserving in the sense that patient-level data are not required to be transferred across sites”).”
The Federated Estimand: Healthcare Federated Learning as Evidence Synthesis
Veeraragavan, N. R., Lambert, P. C., Aagnes, B., & Nygård, J. F. (2026) · International Conference on Federated Learning and Intelligent Computing Systems (FLICS) · doi:10.1109/flics70075.2026.11621899
“Distributed health research predates modern FL. DataSHIELD [13], [14], GLORE [15], WebDISCO [16], ODAL [17], ODACH [18], OHDSI [19], and Sentinel [20] show that multi-site health analyses can be specified centrally, fit locally, and summarized without pooling all records.”
İnan, G., Göksel, İ., Metin, U., & Üstüntepe, G. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01174-x
Metadata
- Authors
- Duan, R., Boland, M. R., Liu, Z., Liu, Y., Chang, H. H., Xu, H., Chu, H., Schmid, C. H., Forrest, C. B., Holmes, J. H., Schuemie, M. J., Berlin, J. A., Moore, J. H., & Chen, Y.
- Affiliations
- University of Pennsylvania (US)
- Stanford University (US)
- Harvard University (US)
- Emory University (US)
- The University of Texas Health Science Center at Houston (US)
- University of Minnesota (US)
- Brown University (US)
- Children's Hospital of Philadelphia (US)
- Janssen Research and Development LLC, Titusville, New Jersey, USA
- Corresponding author
- Chen, Yong
- ORCID
- Venue
- Journal of the American Medical Informatics Association
- Publisher
- Oxford University Press (OUP)
- Published
- 2019-12-09
- Volume
- 27
- Issue
- 3
- Pages
- 376-385
- ISSN
- 1067-5027 (ISSN-L)
- 1527-974X
- PMC
- PMC7025371
- OpenAlex
- W2996582092
- Cited by
- 99
- References
- 21
- Citations by year
- 2026: 8 · 2025: 17 · 2024: 20 · 2023: 13 · 2022: 16 · 2021: 16 · 2020: 7 · 2019: 1
- FWCI
- 4.68
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Journal of the American Medical Informatics Association (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (1R01LM012607, 1R01AI130460, P50MH113840, 1R01AI116794, R01LM009012)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Keywords
- privacy-preserving distributed learning, electronic health records, logistic regression, multi-site data integration, communication efficiency, individual patient data, fetal death, drug exposure, federated learning
- MeSH terms
- Data Analysis, Algorithms, Computer Simulation, Confidentiality, Female, Fetal Death, Humans, Pregnancy, Logistic Models, Odds Ratio, Electronic Health Records, Drug-Related Side Effects and Adverse Reactions, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.