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-citationWebDISCO: a web service for distributed cox model learning without patient-level data sharing
Lu, C.-L., Wang, S., Ji, Z., Wu, Y. S., Xiong, L., Jiang, X., & Lucila Ohno-machado, A. (2015) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv083 · Cited by 174 · 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.”
BackgroundGrid 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-citationDecker, 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: 1
- 2017, R: A Language and Environment for Statistical Com-Puting
Cited by
Federated 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
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].”
MethodWhy 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 132
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 196
“maintaining the confidentiality of the data itself [108-113].”
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm. https://app.cochat.ai/papers/10.1093/jamia/ocz199
- The paper
- 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. (2020). Learning from electronic health records across multiple sites: A communication-efficient and privacy-preserving distributed algorithm. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocz199
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.