{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T09:58:25Z","timestamp":1792144705941,"version":"4.4.0"},"reference-count":63,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"content-version":"vor","delay-in-days":366,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1418504"],"award-info":[{"award-number":["1418504"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HG006844"],"award-info":[{"award-number":["R01HG006844"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U2COD023196"],"award-info":[{"award-number":["U2COD023196"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Electronic medical records (EMRs) can support medical research and discovery, but privacy risks limit the sharing of such data on a wide scale. Various approaches have been developed to mitigate risk, including record simulation via generative adversarial networks (GANs). While showing promise in certain application domains, GANs lack a principled approach for EMR data that induces subpar simulation. In this article, we improve EMR simulation through a novel pipeline that (1) enhances the learning model, (2) incorporates evaluation criteria for data utility that informs learning, and (3) refines the training process.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We propose a new electronic health record generator using a GAN with a Wasserstein divergence and layer normalization techniques. We designed 2 utility measures to characterize similarity in the structural properties of real and simulated EMRs in the original and latent space, respectively. We applied a filtering strategy to enhance GAN training for low-prevalence clinical concepts. We evaluated the new and existing GANs with utility and privacy measures (membership and disclosure attacks) using billing codes from over 1 million EMRs at Vanderbilt University Medical Center.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The proposed model outperformed the state-of-the-art approaches with significant improvement in retaining the nature of real records, including prediction performance and structural properties, without sacrificing privacy. Additionally, the filtering strategy achieved higher utility when the EMR training dataset was small.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>These findings illustrate that EMR simulation through GANs can be substantially improved through more appropriate training, modeling, and evaluation criteria.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocz161","type":"journal-article","created":{"date-parts":[[2019,8,15]],"date-time":"2019-08-15T19:11:55Z","timestamp":1565896315000},"page":"99-108","source":"Crossref","is-referenced-by-count":69,"title":["Ensuring electronic medical record simulation through better training, modeling, and evaluation"],"prefix":"10.1093","volume":"27","author":[{"given":"Ziqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego A","family":"Mesa","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimeng","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computing, Georgia Institute of Technology, Atlanta, Georgia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradley A","family":"Malin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, Tennessee, USA"},{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"},{"name":"Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,10,8]]},"reference":[{"issue":"5","key":"2020110620012964900_ocz161-B1","first-page":"2041","article-title":"Saving patient Ryan\u2014can advanced electronic medical records make patient care safer?","volume":"65","author":"Hydari","year":"2018","journal-title":"Manage Sci"},{"issue":"1","key":"2020110620012964900_ocz161-B2","first-page":"43","article-title":"Identifying hospital patient safety problems in real-time with electronic medical record data using an ensemble machine learning model","volume":"1","author":"Li","year":"2018","journal-title":"Int J Clin Med Inform"},{"issue":"1","key":"2020110620012964900_ocz161-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jom.2018.06.003","article-title":"Does the meaningful use of electronic health records improve patient outcomes?","volume":"60","author":"Wani","year":"2018","journal-title":"J Oper Manag"},{"issue":"1","key":"2020110620012964900_ocz161-B4","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.jom.2015.10.001","article-title":"The impact of health information technology bundles on hospital performance: an econometric study","volume":"41","author":"Sharma","year":"2016","journal-title":"J Oper Manag"},{"issue":"4","key":"2020110620012964900_ocz161-B5","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1007\/s10729-015-9329-z","article-title":"The effect of information technology on hospital performance","volume":"19","author":"Williams","year":"2016","journal-title":"Health Care Manag Sci"},{"issue":"7","key":"2020110620012964900_ocz161-B6","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1007\/s11136-014-0903-5","article-title":"Training clinicians in how to use patient-reported outcome measures in routine clinical practice","volume":"24","author":"Santana","year":"2015","journal-title":"Qual Life Res"},{"issue":"1","key":"2020110620012964900_ocz161-B7","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1080\/10401334.2015.1107488","article-title":"Changing medical school IT to support medical education transformation","volume":"28","author":"Spickard","year":"2016","journal-title":"Teach Learn Med"},{"issue":"1","key":"2020110620012964900_ocz161-B8","article-title":"A harmonized data quality assessment terminology and framework for the secondary use of electronic health record data","volume":"4","author":"Kahn","year":"2016","journal-title":"EGEMS (Wash DC)"},{"key":"2020110620012964900_ocz161-B9","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.ijmedinf.2016.10.004","article-title":"Impacts of structuring the electronic health record: Results of a systematic literature review from the perspective of secondary use of patient data","volume":"97","author":"Vuokko","year":"2017","journal-title":"Int J Med Inform"},{"issue":"6","key":"2020110620012964900_ocz161-B10","doi-asserted-by":"crossref","first-page":"e232.","DOI":"10.2196\/jmir.7126","article-title":"Developing and evaluating digital interventions to promote behavior change in health and health care: recommendations resulting from an international workshop","volume":"19","author":"Michie","year":"2017","journal-title":"J Med Internet Res"},{"issue":"10","key":"2020110620012964900_ocz161-B11","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1377\/hlthaff.2017.0546","article-title":"Progress in interoperability: measuring US hospitals\u2019 engagement in sharing patient data","volume":"36","author":"Holmgren","year":"2017","journal-title":"Health Aff (Millwood)"},{"issue":"5","key":"2020110620012964900_ocz161-B12","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1109\/JBHI.2017.2767063","article-title":"Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis","volume":"22","author":"Shickel","year":"2018","journal-title":"IEEE J Biomed Health Inform"},{"issue":"8","key":"2020110620012964900_ocz161-B13","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1002\/phar.1786","article-title":"Implementation of clinical pharmacogenomics within a large health system: from electronic health record decision support to consultation services","volume":"36","author":"Hicks","year":"2016","journal-title":"Pharmacotherapy"},{"issue":"1","key":"2020110620012964900_ocz161-B14","doi-asserted-by":"crossref","first-page":"4.","DOI":"10.1186\/s13336-015-0019-3","article-title":"Clinical decision support systems for improving diagnostic accuracy and achieving precision medicine","volume":"5","author":"Castaneda","year":"2015","journal-title":"J Clin Bioinforma"},{"key":"2020110620012964900_ocz161-B15","first-page":"126","article-title":"Adding value to the electronic health record through secondary use of data for quality assurance, research, and surveillance","volume":"81","author":"Hersh","year":"2007","journal-title":"Clin Pharmacol Ther"},{"issue":"1","key":"2020110620012964900_ocz161-B16","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13040-015-0048-2","article-title":"The effects of electronic medical record phenotyping details on genetic association studies: HDL-C as a case study","volume":"8","author":"Dumitrescu","year":"2015","journal-title":"BioData Min"},{"issue":"e1","key":"2020110620012964900_ocz161-B17","doi-asserted-by":"crossref","first-page":"e147","DOI":"10.1136\/amiajnl-2012-000896","article-title":"Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network","volume":"20","author":"Newton","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"2020110620012964900_ocz161-B18","year":"2003"},{"issue":"5","key":"2020110620012964900_ocz161-B19","doi-asserted-by":"crossref","first-page":"48\u201355.","DOI":"10.1109\/MSP.2011.72","article-title":"Experience-based access management: a life-cycle framework for identity and access management systems","volume":"9","author":"Gunter","year":"2011","journal-title":"IEEE Secur Priv"},{"issue":"7","key":"2020110620012964900_ocz161-B20","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1287\/mnsc.1090.1014","article-title":"Privacy protection and technology diffusion: the case of electronic medical records","volume":"55","author":"Miller","year":"2009","journal-title":"Manage Sci"},{"key":"2020110620012964900_ocz161-B21","first-page":"51","article-title":"Guaranteeing anonymity when sharing medical data, the Datafly system","author":"Sweeney","year":"1997","journal-title":"Proc AMIA Annu Fall Symp"},{"issue":"5","key":"2020110620012964900_ocz161-B22","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1142\/S0218488502001648","article-title":"k-Anonymity: a model for protecting privacy","volume":"10","author":"Sweeney","year":"2002","journal-title":"Int J Uncertain Fuzz Knowl Based Syst"},{"issue":"5","key":"2020110620012964900_ocz161-B23","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1197\/jamia.M3144","article-title":"A globally optimal k-anonymity method for the de-identification of health data","volume":"16","author":"El Emam","year":"2009","journal-title":"J Am Med Inform Assoc"},{"issue":"3\u20134","key":"2020110620012964900_ocz161-B24","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2013","journal-title":"Found Theor Comput Sci"},{"issue":"6245","key":"2020110620012964900_ocz161-B25","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: trends, perspectives, and prospects","volume":"349","author":"Jordan","year":"2015","journal-title":"Science"},{"issue":"5","key":"2020110620012964900_ocz161-B26","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1197\/jamia.M2716","article-title":"Protecting privacy using k-anonymity","volume":"15","author":"El Emam","year":"2008","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2020110620012964900_ocz161-B27","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1136\/amiajnl-2012-001047","article-title":"Toward practicing privacy","volume":"20","author":"Dwork","year":"2013","journal-title":"J Am Med Inform Assoc"},{"key":"2020110620012964900_ocz161-B28","first-page":"158","author":"Dankar","year":"2012"},{"issue":"1","key":"2020110620012964900_ocz161-B29","first-page":"35","article-title":"Practicing differential privacy in health care: a review","volume":"6","author":"Dankar","year":"2013","journal-title":"Trans Data Priv"},{"issue":"12","key":"2020110620012964900_ocz161-B30","doi-asserted-by":"crossref","first-page":"e28071.","DOI":"10.1371\/journal.pone.0028071","article-title":"A systematic review of re-identification attacks on health data","volume":"6","author":"El Emam","year":"2011","journal-title":"PLoS One"},{"issue":"2","key":"2020110620012964900_ocz161-B31","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1136\/jamia.2009.000026","article-title":"Evaluating re-identification risks with respect to the HIPAA privacy rule","volume":"17","author":"Benitez","year":"2010","journal-title":"J Am Med Inform Assoc"},{"key":"2020110620012964900_ocz161-B32","first-page":"439","author":"McLachlan","year":"2016"},{"issue":"3","key":"2020110620012964900_ocz161-B33","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1093\/jamia\/ocx079","article-title":"Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record","volume":"25","author":"Walonoski","year":"2018","journal-title":"J Am Med Inform Assoc"},{"key":"2020110620012964900_ocz161-B34","author":"Avi\u00f1\u00f3","year":"2018"},{"key":"2020110620012964900_ocz161-B35","author":"Kartoun"},{"issue":"2","key":"2020110620012964900_ocz161-B36","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1006\/jbin.2001.1013","article-title":"A knowledge-based, concept-oriented view generation system for clinical data","volume":"34","author":"Zeng","year":"2001","journal-title":"J Biomed Inform"},{"issue":"1","key":"2020110620012964900_ocz161-B37","doi-asserted-by":"crossref","first-page":"43.","DOI":"10.1186\/1471-2105-7-43","article-title":"SynTReN: a generator of synthetic gene expression data for design and analysis of structure learning algorithms","volume":"7","author":"Bulcke","year":"2006","journal-title":"BMC Bioinform"},{"key":"2020110620012964900_ocz161-B38","first-page":"36","author":"Ria\u00f1o","year":"2016"},{"issue":"1","key":"2020110620012964900_ocz161-B39","doi-asserted-by":"crossref","first-page":"59.","DOI":"10.1186\/1472-6947-10-59","article-title":"Data-driven approach for creating synthetic electronic medical records","volume":"10","author":"Buczak","year":"2010","journal-title":"BMC Med Inform Decis Mak"},{"key":"2020110620012964900_ocz161-B40","first-page":"69","author":"Dube","year":"2013"},{"key":"2020110620012964900_ocz161-B41","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"2020110620012964900_ocz161-B42","author":"Radford"},{"key":"2020110620012964900_ocz161-B43","author":"Odena"},{"key":"2020110620012964900_ocz161-B44","first-page":"286","article-title":"Generating multi-label discrete patient records using generative adversarial networks","volume":"68","author":"Choi","year":"2017","journal-title":"Proc Mach Learn Res"},{"key":"2020110620012964900_ocz161-B45","author":"Brock"},{"key":"2020110620012964900_ocz161-B46","author":"Fedus"},{"key":"2020110620012964900_ocz161-B47","author":"Yang","year":"2017"},{"issue":"3","key":"2020110620012964900_ocz161-B48","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1093\/jamia\/ocy142","article-title":"Synthesizing electronic health records using improved generative adversarial networks","volume":"26","author":"Baowaly","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2020110620012964900_ocz161-B49","author":"Yoon","year":"2018"},{"key":"2020110620012964900_ocz161-B50"},{"key":"2020110620012964900_ocz161-B51","author":"Ioffe"},{"key":"2020110620012964900_ocz161-B52","first-page":"770","author":"He","year":"2016"},{"key":"2020110620012964900_ocz161-B53","author":"Borji"},{"key":"2020110620012964900_ocz161-B54","author":"Hjelm"},{"key":"2020110620012964900_ocz161-B55","author":"Arjovsky"},{"key":"2020110620012964900_ocz161-B56","first-page":"5767","article-title":"Improved training of Wasserstein GANs","author":"Gulrajani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"2020110620012964900_ocz161-B57","author":"Ba"},{"key":"2020110620012964900_ocz161-B58","author":"Higgins","year":"2017"},{"key":"2020110620012964900_ocz161-B59","author":"Kingma"},{"key":"2020110620012964900_ocz161-B60","first-page":"1067","author":"Tang","year":"2015"},{"key":"2020110620012964900_ocz161-B61","author":"Dumoulin","year":"2017"},{"key":"2020110620012964900_ocz161-B62","first-page":"271","author":"Nowozin","year":"2016"},{"key":"2020110620012964900_ocz161-B63","volume-title":"Fundamentals of Convex Analysis","author":"Hiriart-Urruty","year":"2012"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/27\/1\/99\/34152076\/ocz161.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/27\/1\/99\/34152076\/ocz161.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,7]],"date-time":"2020-11-07T01:05:35Z","timestamp":1604711135000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/27\/1\/99\/5583723"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,8]]},"references-count":63,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,10,8]]},"published-print":{"date-parts":[[2020,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocz161","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,1]]},"published":{"date-parts":[[2019,10,8]]}}}