{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T01:57:32Z","timestamp":1783475852870,"version":"3.55.0"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T00:00:00Z","timestamp":1544140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objective<\/jats:title><jats:p>The aim of this study was to generate synthetic electronic health records (EHRs). The generated EHR data will be more realistic than those generated using the existing medical Generative Adversarial Network (medGAN) method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>We modified medGAN to obtain two synthetic data generation models\u2014designated as medical Wasserstein GAN with gradient penalty (medWGAN) and medical boundary-seeking GAN (medBGAN)\u2014and compared the results obtained using the three models. We used 2 databases: MIMIC-III and National Health Insurance Research Database (NHIRD), Taiwan. First, we trained the models and generated synthetic EHRs by using these three 3 models. We then analyzed and compared the models\u2019 performance by using a few statistical methods (Kolmogorov\u2013Smirnov test, dimension-wise probability for binary data, and dimension-wise average count for count data) and 2 machine learning tasks (association rule mining and prediction).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We conducted a comprehensive analysis and found our models were adequately efficient for generating synthetic EHR data. The proposed models outperformed medGAN in all cases, and among the 3 models, boundary-seeking GAN (medBGAN) performed the best.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>To generate realistic synthetic EHR data, the proposed models will be effective in the medical industry and related research from the viewpoint of providing better services. Moreover, they will eliminate barriers including limited access to EHR data and thus accelerate research on medical informatics.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The proposed models can adequately learn the data distribution of real EHRs and efficiently generate realistic synthetic EHRs. The results show the superiority of our models over the existing model.<\/jats:p><\/jats:sec>","DOI":"10.1093\/jamia\/ocy142","type":"journal-article","created":{"date-parts":[[2018,10,25]],"date-time":"2018-10-25T01:53:22Z","timestamp":1540432402000},"page":"228-241","source":"Crossref","is-referenced-by-count":203,"title":["Synthesizing electronic health records using improved generative adversarial networks"],"prefix":"10.1093","volume":"26","author":[{"given":"Mrinal Kanti","family":"Baowaly","sequence":"first","affiliation":[{"name":"Social Networks and Human-Centered Computing, Taiwan International Graduate Program, Institute of Information Science, Academia Sinica, Taipei, Taiwan"},{"name":"Department of Computer Science, National Chengchi University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Ching","family":"Lin","sequence":"additional","affiliation":[{"name":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"},{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Chengchi University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan-Ta","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,12,7]]},"reference":[{"key":"2020110613054995200_ocy142-B1","year":"2013"},{"issue":"12","key":"2020110613054995200_ocy142-B2","article-title":"A systematic review of re-identification attacks on health data","volume":"6","author":"Emam","year":"2011","journal-title":"PLoS One"},{"key":"2020110613054995200_ocy142-B3","article-title":"Anonymising and sharing individual patient data","author":"Emam","year":"2015","journal-title":"Br Med J"},{"issue":"3","key":"2020110613054995200_ocy142-B4","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"},{"issue":"4","key":"2020110613054995200_ocy142-B5","article-title":"A method for generation and distribution of synthetic medical record data for evaluation of disease-monitoring systems","volume":"27","author":"Lombardo","year":"2008","journal-title":"Johns Hopkins APL Tech Digest"},{"issue":"1","key":"2020110613054995200_ocy142-B6","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1186\/1472-6947-10-59","article-title":"Data-driven approach for creating synthetic electronic medical","volume":"10","author":"Buczak","year":"2010","journal-title":"BMC Med Inform Dec Mak"},{"key":"2020110613054995200_ocy142-B7","volume-title":"IEEE International Conference on Healthcare Informatics (ICHI","author":"McLachlan","year":"2016"},{"key":"2020110613054995200_ocy142-B8","volume-title":"2013 IEEE International Conference on Healthcare Informatics","author":"Park","year":"2013"},{"key":"2020110613054995200_ocy142-B9","volume-title":"Realism in Synthetic Data Generation","author":"McLachlan","year":"2017"},{"key":"2020110613054995200_ocy142-B10","article-title":"Generating Multi-label Discrete Patient Records using Generative Adversarial Networks","author":"Choi","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B11","article-title":"Generative Adversarial Networks","author":"Goodfellow","year":"2014","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B12","article-title":"Improved Techniques for Training GANs","author":"Salimans","year":"2016","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B13","article-title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","author":"Radford","year":"2016","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B14","article-title":"Towards the Automatic Anime Characters Creation with Generative Adversarial Networks","author":"Jin","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B15","article-title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","author":"Wang","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B16","article-title":"Generative Adversarial Text to Image Synthesis","author":"Reed","year":"2016","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B17","article-title":"StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks","author":"Zhang","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B18","article-title":"Unsupervised Image-to-Image Translation with Generative Adversarial Networks","author":"Dong","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B19","article-title":"Image-to-Image Translation with Conditional Adversarial Networks","author":"Isola","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B20","article-title":"Multimodal Unsupervised Image-to-Image Translation","author":"Huang","year":"2018","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B21","article-title":"Generating Videos with Scene Dynamics","author":"Vondrick","year":"2016","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B22","article-title":"MoCoGAN: Decomposing Motion and Content for Video Generation","author":"Tulyakov","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B23","article-title":"MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation","author":"Yang","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B24","article-title":"GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution","volume-title":"arXiv:","author":"Kusner","year":"2016"},{"key":"2020110613054995200_ocy142-B25","volume-title":"Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)","author":"Yu","year":"2017"},{"key":"2020110613054995200_ocy142-B26","article-title":"Improved Training of Wasserstein GANs","author":"Gulrajani","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B27","article-title":"Boundary-Seeking Generative Adversarial Networks","author":"Hjelm","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B28","author":"Alistair","year":"2016"},{"key":"2020110613054995200_ocy142-B29","year":"2017"},{"key":"2020110613054995200_ocy142-B30"},{"key":"2020110613054995200_ocy142-B31","year":"2017"},{"key":"2020110613054995200_ocy142-B32","year":"2017"},{"issue":"3","key":"2020110613054995200_ocy142-B33","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1197\/jamia.M2846","article-title":"Prediction of chronic obstructive pulmonary disease (COPD) in asthma patients using electronic medical records","volume":"16","author":"Himes","year":"2009","journal-title":"J Am Med Inform Assoc"},{"issue":"6","key":"2020110613054995200_ocy142-B34","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1097\/MLR.0b013e3181de9e17","article-title":"Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches","volume":"48","author":"Wu","year":"2010","journal-title":"Med Care"},{"issue":"6","key":"2020110613054995200_ocy142-B35","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1136\/amiajnl-2014-002733","article-title":"Toward personalizing treatment for depression: predicting diagnosis and severity","volume":"21","author":"Huang","year":"2014","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2020110613054995200_ocy142-B36","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1093\/jamia\/ocw071","article-title":"Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals","volume":"24","author":"Teixeira","year":"2017","journal-title":"J Am Med Inform Assoc"},{"key":"2020110613054995200_ocy142-B37","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"2020110613054995200_ocy142-B38","author":"LeCun","year":"2017"},{"key":"2020110613054995200_ocy142-B39","article-title":"NIPS 2016 Tutorial: Generative Adversarial Networks","author":"Goodfellow","year":"2017","journal-title":"CoRR"},{"key":"2020110613054995200_ocy142-B40","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2020110613054995200_ocy142-B41","volume-title":"Proceedings of the 25th International Conference on Machine Learning, Helsinki","author":"Vincent","year":"2008"},{"issue":"5786","key":"2020110613054995200_ocy142-B42","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"2020110613054995200_ocy142-B43","article-title":"Wasserstein GAN","author":"Arjovsky","year":"2017","journal-title":"arXiv"},{"key":"2020110613054995200_ocy142-B44","year":"2017"},{"key":"2020110613054995200_ocy142-B45","year":"2017"},{"issue":"6","key":"2020110613054995200_ocy142-B46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3127881","article-title":"Mining electronic health records (EHRs): a survey","volume":"50","author":"Yadav","year":"2018","journal-title":"ACM Comput Surv"},{"issue":"6","key":"2020110613054995200_ocy142-B47","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1016\/j.jbi.2010.09.009","article-title":"An automated technique for identifying associations between medications, laboratory results and problems","volume":"43","author":"Wright","year":"2010","journal-title":"J Biomed Inform"},{"issue":"2","key":"2020110613054995200_ocy142-B48","doi-asserted-by":"crossref","first-page":"77","DOI":"10.4258\/hir.2010.16.2.77","article-title":"Diagnostic analysis of patients with essential hypertension using association rule mining","volume":"16","author":"Shin","year":"2010","journal-title":"Healthc Inform Res"},{"issue":"2","key":"2020110613054995200_ocy142-B49","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1136\/amiajnl-2013-002033","article-title":"Predicting changes in hypertension control using electronic health records from a chronic disease management program","volume":"21","author":"Sun","year":"2014","journal-title":"J Am Med Inform Assoc"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/3\/228\/34151423\/ocy142.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/26\/3\/228\/34151423\/ocy142.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,14]],"date-time":"2020-11-14T00:53:34Z","timestamp":1605315214000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/26\/3\/228\/5235390"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,7]]},"references-count":49,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,12,7]]},"published-print":{"date-parts":[[2019,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocy142","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,3]]},"published":{"date-parts":[[2018,12,7]]}}}