{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:41:54Z","timestamp":1792514514248,"version":"4.5.0"},"reference-count":81,"publisher":"JMIR Publications Inc.","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute diseases present severe complications that develop rapidly, exhibit distinct phenotypes, and have profound effects on patient outcomes. Predictive analytics can enhance physicians\u2019 care and management of patients with acute diseases by predicting crucial complication phenotypes for a timely diagnosis and treatment. However, effective phenotype predictions require several challenges to be overcome. First, patient data collected in the early stages of an acute disease (eg, clinical data and laboratory results) are less informative for predicting phenotypic outcomes. Second, patient data are temporal and heterogeneous; for example, patients receive laboratory tests at different time intervals and frequencies. Third, imbalanced distributions of patient outcomes create additional complexity for predicting complication phenotypes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To predict crucial complication phenotypes among patients with acute diseases, we propose a novel, deep learning\u2013based method that uses recurrent neural network\u2013based sequence embedding to represent disease progression while considering temporal heterogeneities in patient data. Our method incorporates a latent regulator to alleviate data insufficiency constraints by accounting for the underlying mechanisms that are not observed in patient data. The proposed method also includes cost-sensitive learning to address imbalanced outcome distributions in patient data for improved predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>From a major health care organization in Taiwan, we obtained a sample of 10,354 electronic health records that pertained to 6545 patients with peritonitis. The proposed method projects these temporal, heterogeneous, and clinical data into a substantially reduced feature space and then incorporates a latent regulator (latent parameter matrix) to obviate data insufficiencies and account for variations in phenotypic expressions. Moreover, our method employs cost-sensitive learning to further increase the predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We evaluated the efficacy of the proposed method for predicting two hepatic complication phenotypes in patients with peritonitis: acute hepatic encephalopathy and hepatorenal syndrome. The following three benchmark techniques were evaluated: temporal multiple measurement case-based reasoning (MMCBR), temporal short long-term memory (T-SLTM) networks, and time fusion convolutional neural network (CNN). For acute hepatic encephalopathy predictions, our method attained an area under the curve (AUC) value of 0.82, which outperforms temporal MMCBR by 64%, T-SLTM by 26%, and time fusion CNN by 26%. For hepatorenal syndrome predictions, our method achieved an AUC value of 0.64, which is 29% better than that of temporal MMCBR (0.54). Overall, the evaluation results show that the proposed method significantly outperforms all the benchmarks, as measured by recall, F-measure, and AUC while maintaining comparable precision values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed method learns a short-term temporal representation from patient data to predict complication phenotypes and offers greater predictive utilities than prevalent data-driven techniques. This method is generalizable and can be applied to different acute disease (illness) scenarios that are characterized by insufficient patient clinical data availability, temporal heterogeneities, and imbalanced distributions of important patient outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/18372","type":"journal-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T17:28:23Z","timestamp":1608571703000},"page":"e18372","source":"Crossref","is-referenced-by-count":28,"title":["Predictive Analytics for Care and Management of Patients With Acute Diseases: Deep Learning\u2013Based Method to Predict Crucial Complication Phenotypes"],"prefix":"10.2196","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4418-1109","authenticated-orcid":false,"given":"Jessica Qiuhua","family":"Sheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4981-895X","authenticated-orcid":false,"given":"Paul Jen-Hwa","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-4701","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2932-6878","authenticated-orcid":false,"given":"Ting-Shuo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9751-2250","authenticated-orcid":false,"given":"Yu Hsien","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2021,2,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/s0168-8278(00)80201-9"},{"key":"ref2","unstructured":"Acute (medicine)Wikipedia20172021-04-02https:\/\/en.wikipedia.org\/wiki\/Acute_(medicine)"},{"key":"ref3","first-page":"116","volume":"2009","author":"Scheuermann, RH","year":"2009","journal-title":"Summit Transl Bioinform"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.arbres.2011.10.007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/14737159.2018.1439380"},{"key":"ref6","author":"Srinivasan, A","year":"1981","journal-title":"Computer Science"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1572-0241.2001.03964.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-018-0035-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/s0016-5085(03)01051-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2015.01.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097997"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/bibm.2017.8217759"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-05214-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/1475-2840-12-20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-002428"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1086\/514940"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2016.4638"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2007.06.065"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.advms.2016.11.009"},{"issue":"1","key":"ref20","first-page":"11","volume":"28","author":"Ng, CKF","year":"2007","journal-title":"Clin Biochem Rev"},{"key":"ref21","first-page":"7","volume":"22 Suppl 2","author":"Venkataraman, S","year":"2003","journal-title":"Indian J Gastroenterol"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/j.1746-6342.2006.03216.x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1056\/nejm199708143370707"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/hep.23500"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/ng0893-398"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199804093381503"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-001930"},{"key":"ref28","unstructured":"RichessonRSmerekMRethinking Clinical Trials: A Living Textbook of Pragmatic Clinical Trials: Duke UniversityDuke University20142021-01-22https:\/\/sites.duke.edu\/rethinkingclinicaltrials\/"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/gim.2013.72"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2017.01.017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0102987"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783352"},{"issue":"9","key":"ref33","doi-asserted-by":"crossref","first-page":"2423","DOI":"10.1109\/TKDE.2016.2561278","volume":"28","author":"Chen, L","year":"2016","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/bibm.2017.8217761"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.10.001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2016.2608782"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623658"},{"key":"ref40","unstructured":"KaleDCheZBahadoriMLiWLiuYWetzelRCausal phenotype discovery via deep networksAMIA Annual Symposium Proceedings2015115American Medical Informatics Association2015San Francisco67786"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1101\/135574"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1172\/jci124611"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/dese.2015.52"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0066341"},{"key":"ref47","first-page":"180701705","author":"Gupta, P","journal-title":"arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098088"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa040"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357884"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37456-2_24"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2010.5596486"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1177\/193229680800200112"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200906-0896oc"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200711-1754oc"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1186\/1477-7525-12-13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.b2393"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103576"},{"key":"ref59","first-page":"-","author":"Zhang, H","year":"2018","journal-title":"Computer Science, Machine Learning"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007735"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1080\/08998280.2017.11929516"},{"key":"ref62","unstructured":"National Health Insurance Research Database, Taiwan20142021-01-22https:\/\/nhird.nhri.org.tw\/en\/"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2015.3540"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1002\/pds.4713"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1097\/01.mlr.0000182534.19832.83"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0090539"},{"key":"ref67","unstructured":"FletcherJWhat to know about hepatic encephalopathyMedical News Today20191162021-01-11https:\/\/www.medicalnewstoday.com\/articles\/326919"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2147\/tcrm.s205328"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/bf02990104"},{"issue":"4","key":"ref70","first-page":"153","volume":"49","author":"Omagari, K","year":"2004","journal-title":"Acta Medica Nagasakiensia"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1136\/gut.2006.107789"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1053\/gast.1997.v113.pm9322524"},{"key":"ref73","unstructured":"DomhanTSpringenbergJHutterFSpeeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curvesUniversity of Freiburg2015Twenty-Fourth International Joint Conference on Artificial Intelligence2015Buenos Aires, Argentina"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2005.1555963"},{"key":"ref75","unstructured":"MilgramJCherietMSabourinR'One Against One' or 'One Against All': which one is better for handwriting recognition with SVMs?HAL-Inria20062021-01-22https:\/\/hal.inria.fr\/inria-00103955"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.9735\/2229-3981"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i03"},{"key":"ref78","first-page":"2287","volume":"11","author":"Mazumder, R","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.6.520"},{"key":"ref80","author":"Lundberg, S","journal-title":"arXiv"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1586\/egh.09.5"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2021\/2\/e18372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:23:13Z","timestamp":1782840193000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.jmir.org\/2021\/2\/e18372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,12]]},"references-count":81,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.2196\/18372","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.18372","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,12]]}}}