{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T14:51:22Z","timestamp":1791471082308,"version":"4.3.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Electronic health records (EHRs) collected from diverse healthcare institutions offer a rich and representative data source for clinical research. Federated learning enables analysis of these distributed data without sharing sensitive patient-level information, preserving privacy. However, missing data remain a major challenge and can introduce substantial bias if not properly addressed. Very few distributed imputation methods currently exist, and they fail to account for two critical aspects of EHR data: correlation within sites and variability across sites. We aim to fill this important methodological gap.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose Distributed Mixed Model-based Multiple Imputation (D3MI), a novel federated imputation method designed to reduce bias in distributed EHRs. D3MI integrates the strengths from federated learning techniques, statistical learning methods for correlated data, and multilevel imputation algorithms to explicitly account for both within-site correlation and between-site heterogeneity using site-specific random effects. It operates under the Missing at Random (MAR) assumption. It preserves privacy by avoiding sharing raw data and features communication and computational efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Through extensive simulation studies, we demonstrate that D3MI outperforms SOTA distributed imputation methods in both accuracy and consistency. We further demonstrate the use of D3MI in a real-world EHR case study involving incomplete and clustered data from participating hospitals in the Georgia Coverdell Acute Stroke Registry.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By explicitly modeling the complex structure of distributed EHR data, D3MI addresses key limitations of existing approaches. It provides a powerful and efficient solution for handling missing data in distributed and privacy-sensitive settings and enhances the rigor and reproducibility of collaborative clinical research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-026-03663-2","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T01:07:41Z","timestamp":1791421661000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["D3MI: an efficient and powerful federated imputation method for bias reduction in the analysis of distributed incomplete data by accounting for within-site correlation and between-site heterogeneity"],"prefix":"10.1186","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7832-5217","authenticated-orcid":false,"given":"Yi","family":"Lian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9933-2205","authenticated-orcid":false,"given":"Xiaoqian","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0660-5230","authenticated-orcid":false,"given":"Qi","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"issue":"4","key":"3663_CR1","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1136\/amiajnl-2014-002751","volume":"21","author":"L Ohno-Machado","year":"2014","unstructured":"Ohno-Machado L, Agha Z, Bell DS, Dahm L, Day ME, Doctor JN, et al. pSCANNER: patient-centered scalable national network for effectiveness research. J Am Med Inf Assoc. 2014;21(4):621\u201326. https:\/\/doi.org\/10.1136\/amiajnl-2014-002751.","journal-title":"J Am Med Inf Assoc"},{"issue":"1","key":"3663_CR2","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","volume":"3","author":"N Rieke","year":"2020","unstructured":"Rieke N, Hancox J, Li W, Milletari F, Roth HR, Albarqouni S, et al. The future of digital health with federated learning. NPJ Digit Med. 2020;3(1):119. https:\/\/doi.org\/10.1038\/s41746-020-00323-1.","journal-title":"NPJ Digit Med"},{"key":"3663_CR3","doi-asserted-by":"publisher","unstructured":"Paul Coverdell Prototype Registries Writing Group. Acute stroke care in the US: results from 4 pilot prototypes of the Paul Coverdell National Acute stroke Registry. Stroke. 2005;36(6):1232\u201340. https:\/\/doi.org\/10.1161\/01.STR.0000165902.18021.5b.","DOI":"10.1161\/01.STR.0000165902.18021.5b"},{"key":"3663_CR4","doi-asserted-by":"publisher","unstructured":"Yamamoto R, Suzuki M, Funabiki T, Sasaki J. Immediate CT after hospital arrival and decreased in-hospital mortality in severely injured trauma patients. BJS Open. 2023;7(1):zrac133. https:\/\/doi.org\/10.1093\/bjsopen\/zrac133.","DOI":"10.1093\/bjsopen\/zrac133"},{"key":"3663_CR5","doi-asserted-by":"publisher","DOI":"10.1214\/cbms\/1462106059","volume-title":"Generalized linear mixed models","author":"CE McCulloch","year":"2003","unstructured":"McCulloch CE. Generalized linear mixed models. Ims; 2003."},{"key":"3663_CR6","doi-asserted-by":"publisher","unstructured":"Zhu R, Jiang C, Wang X, Wang S, Zheng H, Tang H. Privacy-preserving construction of generalized linear mixed model for biomedical computation. Bioinformatics. 2020;36(Supplement_1):i128\u201335. https:\/\/doi.org\/10.1093\/bioinformatics\/btaa478.","DOI":"10.1093\/bioinformatics\/btaa478"},{"issue":"1","key":"3663_CR7","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1186\/s12911-022-02014-1","volume":"22","author":"W Li","year":"2022","unstructured":"Li W, Tong J, Anjum MM, Mohammed N, Chen Y, Jiang X. Federated learning algorithms for generalized mixed-effects model (GLMM) on horizontally partitioned data from distributed sources. BMC Med Inf Decis Mak. 2022;22(1):269. https:\/\/doi.org\/10.1186\/s12911-022-02014-1.","journal-title":"BMC Med Inf Decis Mak"},{"issue":"8","key":"3663_CR8","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1093\/jamia\/ocac067","volume":"29","author":"C Luo","year":"2022","unstructured":"Luo C, Islam MN, Sheils NE, Buresh J, Schuemie MJ, Doshi JA, et al. dPQL: a lossless distributed algorithm for generalized linear mixed model with application to privacy-preserving hospital profiling. J Am Med Inf Assoc. 2022;29(8):1366\u201371. https:\/\/doi.org\/10.1093\/jamia\/ocac067.","journal-title":"J Am Med Inf Assoc"},{"issue":"2","key":"3663_CR9","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.jstrokecerebrovasdis.2011.06.018","volume":"22","author":"JS McKinney","year":"2013","unstructured":"McKinney JS, Mylavarapu K, Lane J, Roberts V, Ohman-Strickland P, Merlin MA. Hospital prenotification of stroke patients by emergency medical services improves stroke time targets. J Stroke Cerebrovascular Dis. 2013;22(2):113\u201318. https:\/\/doi.org\/10.1016\/j.jstrokecerebrovasdis.2011.06.018.","journal-title":"J Stroke CEREBROVASCULAR Dis"},{"issue":"1","key":"3663_CR10","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1198\/106186006X96962","volume":"15","author":"JC Pinheiro","year":"2006","unstructured":"Pinheiro JC, Chao EC. Efficient laplacian and adaptive Gaussian quadrature algorithms for multilevel generalized linear mixed models. J Comput Graphical Stat. 2006;15(1):58\u201381. https:\/\/doi.org\/10.1198\/106186006X96962.","journal-title":"J Comput Graphical Stat"},{"key":"3663_CR11","unstructured":"Van Buuren S. Multiple imputation of multilevel data. In: Handbook of advanced multilevel analysis. Routledge; 2011. p. 173\u201396."},{"issue":"4","key":"3663_CR12","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1177\/1471082X1001100404","volume":"11","author":"RM Yucel","year":"2011","unstructured":"Yucel RM. Random covariances and mixed-effects models for imputing multivariate multilevel continuous data. Stat Modell. 2011;11(4):351\u201370. https:\/\/doi.org\/10.1177\/1471082X1001100404.","journal-title":"Stat Modell"},{"issue":"2","key":"3663_CR13","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1111\/rssa.12022","volume":"177","author":"H Goldstein","year":"2014","unstructured":"Goldstein H, Carpenter JR, Browne WJ. Fitting multilevel multivariate models with missing data in responses and covariates that may include interactions and non-linear terms. J R Stat Soc Ser A: Stat Soc. 2014;177(2):553\u201364. https:\/\/doi.org\/10.1111\/rssa.12022.","journal-title":"J R Stat Soc Ser A: Stat Soc"},{"key":"3663_CR14","volume-title":"Multilevel models for categorical data using SAS\u00ae PROC GLIMMIX: the basics","author":"M Ene","year":"2015","unstructured":"Ene M, Leighton EA, Blue GL, Bell BA. Multilevel models for categorical data using SAS\u00ae PROC GLIMMIX: the basics. SAS Global Forum; 2015."},{"issue":"11","key":"3663_CR15","doi-asserted-by":"publisher","first-page":"1841","DOI":"10.1002\/sim.6451","volume":"34","author":"S Jolani","year":"2015","unstructured":"Jolani S, Debray TPA, Koffijberg H, van Buuren S, Moons KGM. Imputation of systematically missing predictors in an individual participant data meta-analysis: a generalized approach using MICE. Stat Med. 2015;34(11):1841\u201363. https:\/\/doi.org\/10.1002\/sim.6451.","journal-title":"Stat Med"},{"issue":"2","key":"3663_CR16","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1002\/bimj.201600220","volume":"60","author":"S Jolani","year":"2018","unstructured":"Jolani S. Hierarchical imputation of systematically and sporadically missing data: an approximate Bayesian approach using chained equations. Biom J. 2018;60(2):333\u201351. https:\/\/doi.org\/10.1002\/bimj.201600220.","journal-title":"Biom J"},{"issue":"6","key":"3663_CR17","doi-asserted-by":"publisher","first-page":"1634","DOI":"10.1177\/0962280216666564","volume":"27","author":"M Resche-Rigon","year":"2018","unstructured":"Resche-Rigon M, White IR. Multiple imputation by chained equations for systematically and sporadically missing multilevel data. Stat Methods Med Res. 2018;27(6):1634\u201349. https:\/\/doi.org\/10.1177\/0962280216666564.","journal-title":"Stat Methods Med Res"},{"issue":"1","key":"3663_CR18","doi-asserted-by":"publisher","first-page":"5467","DOI":"10.1038\/s41467-020-19270-2","volume":"11","author":"C Chang","year":"2020","unstructured":"Chang C, Deng Y, Jiang X, Long Q. Multiple imputation for analysis of incomplete data in distributed health data networks. Nat Commun. 2020;11(1):5467. https:\/\/doi.org\/10.1038\/s41467-020-19270-2.","journal-title":"Nat Commun"},{"key":"3663_CR19","first-page":"703","volume":"2024","author":"Yi Lian","year":"2025","unstructured":"Lian Y, Jiang X, Long Q. Federated multiple imputation for variables that are missing not at random in distributed electronic health records. AMIA Annu Symp Proc. 2025;2024:703.","journal-title":"AMIA Annual Symposium Proceedings"},{"issue":"17","key":"3663_CR20","doi-asserted-by":"publisher","first-page":"3807","DOI":"10.1080\/00949655.2024.2404220","volume":"94","author":"R Thiesmeier","year":"2024","unstructured":"Thiesmeier R, Bottai M, Orsini N. Systematically missing data in distributed data networks: multiple imputation when data cannot be pooled. J Stat Comput Simul. 2024;94(17):3807\u201325. https:\/\/doi.org\/10.1080\/00949655.2024.2404220.","journal-title":"J Stat Comput Simul"},{"key":"3663_CR21","doi-asserted-by":"publisher","first-page":"104780","DOI":"10.1016\/j.jbi.2025.104780","volume":"165","author":"S Li","year":"2025","unstructured":"Li S, Yan M, Yuan R, Liu M, Liu N, Hong C. FedIMPUTE: privacy-preserving missing value imputation for multi-site heterogeneous electronic health records. J Biomed Inf. 2025;165:104780. https:\/\/doi.org\/10.1016\/j.jbi.2025.104780.","journal-title":"J Biomed Inf"},{"issue":"526","key":"3663_CR22","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1080\/01621459.2018.1429274","volume":"114","author":"MI Jordan","year":"2019","unstructured":"Jordan MI, Lee JD, Yang Y. Communication-efficient distributed statistical inference. J Am Stat Assoc. 2019;114(526):668\u201381. https:\/\/doi.org\/10.1080\/01621459.2018.1429274.","journal-title":"J Am Stat Assoc"},{"issue":"2","key":"3663_CR23","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1093\/biostatistics\/kxaa031","volume":"23","author":"C Hong","year":"2022","unstructured":"Hong C, Wang Y, Cai T. A divide-and-conquer method for sparse risk prediction and evaluation. Biostatistics. 2022;23(2):397\u2013411. https:\/\/doi.org\/10.1093\/biostatistics\/kxaa031.","journal-title":"Biostatistics"},{"key":"3663_CR24","first-page":"2020","volume":"2","author":"C Luo","year":"2020","unstructured":"Luo C, Duan R, Edmondson M, Tong J, Chen Y. PDA: privacy-preserving distributed algorithms. R Package 10. 2020;2:2020\u201312.","journal-title":"R Package 10"},{"key":"3663_CR25","volume-title":"Multivariate imputation by chained equations","author":"S Van Buuren","year":"2000","unstructured":"Van Buuren S, Oudshoorn CG. Multivariate imputation by chained equations. Leiden: TNO; 2000."},{"key":"3663_CR26","volume-title":"Multiple imputation for nonresponse in surveys","author":"DB Rubin","year":"2004","unstructured":"Rubin DB. Multiple imputation for nonresponse in surveys. John Wiley & Sons; 2004."},{"key":"3663_CR27","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wainwright MJ, Duchi JC. Communication-efficient algorithms for statistical optimization. Adv Neural Inf Process Syst. 2012, 25.","DOI":"10.1109\/CDC.2012.6426691"},{"issue":"3","key":"3663_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","volume":"45","author":"S Van Buuren","year":"2011","unstructured":"Van Buuren S, Groothuis-Oudshoorn K. Mice: multivariate imputation by chained equations in R. J Stat Soft. 2011;45(3):1\u201367. https:\/\/doi.org\/10.18637\/jss.v045.i03.","journal-title":"J Stat Soft"},{"issue":"5","key":"3663_CR29","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1177\/0962280213511027","volume":"25","author":"Y Zhao","year":"2016","unstructured":"Zhao Y, Long Q. Multiple imputation in the presence of high-dimensional data. Stat Methods Med Res. 2016;25(5):2021\u201335. https:\/\/doi.org\/10.1177\/0962280213511027.","journal-title":"Stat Methods Med Res"},{"key":"3663_CR30","doi-asserted-by":"publisher","unstructured":"St-Pierre J, Oualkacha K, Bhatnagar SR. Efficient penalized generalized linear mixed models for variable selection and genetic risk prediction in high-dimensional data. Bioinformatics. 2023;39(2):btad063. https:\/\/doi.org\/10.1093\/bioinformatics\/btad063.","DOI":"10.1093\/bioinformatics\/btad063"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03663-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-026-03663-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03663-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T14:03:16Z","timestamp":1791468196000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12911-026-03663-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3663"],"URL":"https:\/\/doi.org\/10.1186\/s12911-026-03663-2","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]},"assertion":[{"value":"18 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Relevant guidelines and regulations","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"396"}}