{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T05:54:09Z","timestamp":1792475649859,"version":"4.5.0"},"reference-count":37,"publisher":"JMIR Publications Inc.","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Traditional Chinese medicine (TCM) practitioners usually follow a 4-step evaluation process during patient diagnosis: observation, auscultation, olfaction, inquiry, pulse feeling, and palpation. The information gathered in this process, along with laboratory test results and other measurements such as vital signs, is recorded in the patient\u2019s electronic health record (EHR). In fact, all the information needed to make a treatment plan is contained in the EHR; however, only a seasoned TCM physician could use this information well to make a good treatment plan as the reasoning process is very complicated, and it takes years of practice for a medical graduate to master the reasoning skill. In this digital medicine era, with a deluge of medical data, ever-increasing computing power, and more advanced artificial neural network models, it is not only desirable but also readily possible for a computerized system to mimic the decision-making process of a TCM physician.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop an assistive tool that can predict prescriptions for inpatients in a hospital based on patients\u2019 clinical EHRs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Clinical health records containing medical histories, as well as current symptoms and diagnosis information, were used to train a transformer-based neural network model using the corresponding physician\u2019s prescriptions as the target. This was accomplished by extracting relevant information, such as the patient\u2019s current illness, medicines taken, nursing care given, vital signs, examinations, and laboratory results from the patient\u2019s EHRs. The obtained information was then sorted chronologically to produce a sequence of data for the patient. These time sequence data were then used as input to a modified transformer network, which was chosen as a prescription prediction model. The output of the model was the prescription for the patient. The ultimate goal is for this tool to generate a prescription that matches what an expert TCM physician would prescribe. To alleviate the issue of overfitting, a generative adversarial network was used to augment the training sample data set by generating noise-added samples from the original training samples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In total, 21,295 copies of inpatient electronic medical records from Guang\u2019anmen Hospital were used in this study. These records were generated between January 2017 and December 2018, covering 6352 types of medicines. These medicines were sorted into 819 types of first-category medicines based on their class relationships. As shown by the test results, the performance of a fully trained transformer model can have an average precision rate of 80.58% and an average recall rate of 68.49%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>As shown by the preliminary test results, the transformer-based TCM prescription recommendation model outperformed the existing conventional methods. The extra training samples generated by the generative adversarial network help to overcome the overfitting issue, leading to further improved recall and precision rates.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/35239","type":"journal-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:54:05Z","timestamp":1649638445000},"page":"e35239","source":"Crossref","is-referenced-by-count":28,"title":["Transformer- and Generative Adversarial Network\u2013Based Inpatient Traditional Chinese Medicine Prescription Recommendation: Development Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-8409","authenticated-orcid":false,"given":"Hong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1244-4701","authenticated-orcid":false,"given":"Jiajun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5488-701X","authenticated-orcid":false,"given":"Wandong","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-5914","authenticated-orcid":false,"given":"Youlin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2160-639X","authenticated-orcid":false,"given":"Kunjing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7193-9950","authenticated-orcid":false,"given":"Daying","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6620-3463","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2022,5,31]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2013.06.004"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/978-3-030-05249-2_5","author":"Hasan, SA","year":"2019","journal-title":"Data Science for Healthcare: Methodologies and Applications"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3119621"},{"key":"ref4","author":"Murphy, KP","year":"2012","journal-title":"Machine Learning: A Probabilistic Perspective"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2767063"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2196\/12239"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/srep26094"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.1826"},{"key":"ref11","author":"Yang, Y","year":"2017","journal-title":"arXiv (forthcoming)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0029-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1056"},{"key":"ref15","first-page":"301","volume":"56","author":"Choi, E","year":"2016","journal-title":"JMLR Workshop Conf Proc"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2196\/17608"},{"issue":"12","key":"ref18","first-page":"1","volume":"38","author":"Zhikui, C","year":"2020","journal-title":"Chinese J Traditional Chinese Med"},{"key":"ref19","first-page":"34","volume":"27","author":"Guo, Y","year":"2015","journal-title":"Med & Pharm J Chin PLA"},{"key":"ref20","unstructured":"PageLBrinSMotwaniRWinogradTThe pagerank citation ranking: bringing order to the WebProceedings of the 7th International Conference on World Wide Web1998WWW7 '981998Brisbane, Australia16172"},{"key":"ref21","first-page":"1257","volume":"5","author":"Zhang, Y","year":"2019","journal-title":"Lishizhen Med and Materia Medica Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32233-5_38"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1508.01991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1030"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx228"},{"issue":"4","key":"ref27","first-page":"3","volume":"40","author":"Gang, L","year":"2020","journal-title":"J Modern Inf"},{"issue":"56","key":"ref28","first-page":"153","volume":"2020","author":"Li, B","year":"2020","journal-title":"Computer Engineering and Applications"},{"key":"ref29","unstructured":"MikolovTChenKCorradoGDeanJEfficient estimation of word representations in vector spaceProceedings of the 2013 International Conference on Learning Representations2013ICLR '13May 2-4, 2013Scottsdale, AZ, USA"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2017.12.024"},{"key":"ref33","unstructured":"Specification for drafting of health information basic dataset (WS 445-2014)SMinistry of Health of the People\u2019s Republic of China20142022-05-04https:\/\/wenku.baidu.com\/view\/4c17892d760bf78a6529647d27284b73f342365b.html"},{"key":"ref34","unstructured":"Specification for sharing documents of electronic medical record - part 1: medical record summary (WS\/t 5001-2016)SMinistry of Health of the People\u2019s Republic of China20162022-04-21https:\/\/ishare.iask.sina.com.cn\/f\/rIcgxKYJb9.html"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/480S82a"},{"key":"ref36","unstructured":"XiongHResearch on the recommendation method of traditional Chinese medicine dynamic diagnosis and treatment plan based on real-world clinical dataBeijing Jiaotong University20202022-05-04https:\/\/www.docin.com\/p-2607021734.html"},{"key":"ref37","unstructured":"XiaoluGApplication of deep learning in electronic health records dataXiamen University20192022-04-21https:\/\/kns.cnki.net\/kcms\/detail\/detail.aspx?dbcode=CMFD&dbname=CMFD202002&filename=1019064889.nh&uniplatform=NZKPT&v= JdsETSDw9TG7mLWRMKxEtYFZWzSE1ntYAQYDF6L2Z3Tl3ccV-citYLrD1g30mRob"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2022\/5\/e35239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:56:25Z","timestamp":1782842185000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2022\/5\/e35239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,31]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2196\/35239","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.35239","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,31]]}}}