{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:45:15Z","timestamp":1785249915903,"version":"3.55.0"},"reference-count":61,"publisher":"JMIR Publications Inc.","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Without timely diagnosis and treatment, tachycardia, also called tachyarrhythmia, can cause serious complications such as heart failure, cardiac arrest, and even death. The predictive performance of conventional clinical diagnostic procedures needs improvement in order to assist physicians in detecting risk early on.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We aimed to develop a deep tachycardia onset prediction (TOP-Net) model based on deep learning (ie, bidirectional long short-term memory) for early tachycardia diagnosis with easily accessible data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>TOP-Net leverages 2 easily accessible data sources: vital signs, including heart rate, respiratory rate, and blood oxygen saturation (SpO2) acquired continuously by wearable embedded systems, and electronic health records, containing age, gender, admission type, first care unit, and cardiovascular disease history. The model was trained with a large data set from an intensive care unit and then transferred to a real-world scenario in the general ward. In this study, 3 experiments incorporated merging patients\u2019 personal information, temporal memory, and different feature combinations. Six metrics (area under the receiver operating characteristic curve [AUROC], sensitivity, specificity, accuracy, F1 score, and precision) were used to evaluate predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>TOP-Net outperformed the baseline models on the large critical care data set (AUROC 0.796, 95% CI 0.768-0.824; sensitivity 0.753, 95% CI 0.663-0.793; specificity 0.720, 95% CI 0.645-0.758; accuracy 0.721; F1 score 0.718; precision 0.686) when predicting tachycardia onset 6 hours in advance. When predicting tachycardia onset 2 hours in advance with data acquired from our hospital using the transferred TOP-Net, the 6 metrics were 0.965, 0.955, 0.881, 0.937, 0.793, and 0.680, respectively. The best performance was achieved using comprehensive vital signs (heart rate, respiratory rate, and SpO2) statistical information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>TOP-Net is an early tachycardia prediction model that uses 8 types of data from wearable sensors and electronic health records. When validated in clinical scenarios, the model achieved a prediction performance that outperformed baseline models 0 to 6 hours before tachycardia onset in the intensive care unit and 2 hours before tachycardia onset in the general ward. Because of the model\u2019s implementation and use of easily accessible data from wearable sensors, the model can assist physicians with early discovery of patients at risk in general wards and houses.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/18803","type":"journal-article","created":{"date-parts":[[2021,2,21]],"date-time":"2021-02-21T20:52:52Z","timestamp":1613940772000},"page":"e18803","source":"Crossref","is-referenced-by-count":22,"title":["TOP-Net Prediction Model Using Bidirectional Long Short-term Memory and Medical-Grade Wearable Multisensor System for Tachycardia Onset: Algorithm Development Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9592-9020","authenticated-orcid":false,"given":"Xiaoli","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5451-8935","authenticated-orcid":false,"given":"Tongbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9218-5644","authenticated-orcid":false,"given":"Zhengbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4020-3147","authenticated-orcid":false,"given":"Po-Chih","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4953-2473","authenticated-orcid":false,"given":"Haoran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-9814","authenticated-orcid":false,"given":"Zhicheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0423-5520","authenticated-orcid":false,"given":"Ke","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7829-6321","authenticated-orcid":false,"given":"Peiyao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1304-5366","authenticated-orcid":false,"given":"Zhenchao","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2412-9581","authenticated-orcid":false,"given":"Yeuk Lam","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5059-8694","authenticated-orcid":false,"given":"Wei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7465-7433","authenticated-orcid":false,"given":"Deyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2021,4,15]]},"reference":[{"key":"ref1","first-page":"1","author":"Awtry, E","year":"2006","journal-title":"Blueprints Cardiology"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-8159.1984.tb04948.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0207215"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15420\/aer.2018:15:2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1161\/01.cir.0000072767.89944.6e"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2006.10.062"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1308\/003588406x130615"},{"key":"ref8","author":"Gotlibovych, I","journal-title":"arXiv."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2217\/pme-2018-0044"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/s40560-017-0261-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.resuscitation.2014.01.013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aab3719"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.5909"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1056\/nejmp1702071"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/percom.2016.7456519"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2016.12.019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/srep32390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/springsim.2019.8732885"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0268-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2017.2767063"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"GhassemiMPimentelMAFNaumannTA multivariate timeseries modeling approach to severity of illness assessment and forecasting in ICU with sparse, heterogeneous clinical data2015Proceedings of the Twenty-Ninth AAAI Conference on Artificial IntelligenceJanuary 25-30Austin, Texas","DOI":"10.1609\/aaai.v29i1.9209"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/51.932724"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/rbme.2018.2885714"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0268-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/bhi.2017.7897225"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.22489\/cinc.2017.166-054"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1007\/978-3-030-00320-3_20","author":"Cho, J","year":"2018","journal-title":"Predictive Intelligence in Medicine"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2017.03.571"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/jcdd6020019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2018.11.063"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5694\/j.1326-5377.2008.tb01825.x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.rec.2012.02.021"},{"key":"ref35","unstructured":"LanKLiuXXuHDeePTOP: personalized tachycardia onset prediction using bi-directional LSTM in wearable embedded systems2019International Conference on Embedded Wireless Systems and NetworksFebruary 25-27Beijing, China216217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1161\/01.cir.101.23.e215"},{"key":"ref37","unstructured":"TOP-NetGitHub2021-04-09https:\/\/github.com\/liuxiaoliXRZS\/TOP-Net"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-020-01653-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy068"},{"key":"ref41","unstructured":"ShiXChenZWangHYeungDYWongWKWooWCConvolutional LSTM network: a machine learning approach for precipitation nowcasting2015Advances in neural information processing systemsDecember 7-12Montreal, Canada802810"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/1941218"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1103\/physreve.55.5443"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ichi.2019.8904641"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/infcomw.2019.8845115"},{"key":"ref47","unstructured":"FutomaJHariharanSHellerKSendakMBrajerNClementMBedoyaAO'BrienCAn improved multi-output gaussian process RNN with real-time validation for early sepsis detectionProceedings of the 2nd Machine Learning for Healthcare Conference2017Machine Learning for Healthcare ConferenceAugust 18-19Boston, Massachusetts243254"},{"key":"ref48","first-page":"460","volume":"2018","author":"Ge, Wendong","year":"2018","journal-title":"AMIA Annu Symp Proc"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10877-015-9790-8"},{"key":"ref51","author":"Pan, Z","journal-title":"arXiv."},{"key":"ref52","unstructured":"FutomaJHarihanSHellerKLearning to detect sepsis with a multitask Gaussian process RNN classifier201734th International Conference on Machine LearningAugust 6-11Sydney, Australia"},{"key":"ref53","unstructured":"TonekaboniSMazwiMLaussenPEytanDGreerRGoodfellowSDGoodwinABrudnoMGoldenbergAPrediction of cardiac arrest from physiological signals in the pediatric ICUProceedings of the 3rd Machine Learning for Healthcare Conference20183rd Machine Learning for HealthcareAugust 16-18Stanford, California534550"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10877-019-00277-0"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220051"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000002936"},{"key":"ref58","first-page":"301","volume":"56","author":"Choi, E","year":"2016","journal-title":"JMLR Workshop Conf Proc"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw112"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/access.2017.2789324"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103801"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2021\/4\/e18803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:24:16Z","timestamp":1782840256000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2021\/4\/e18803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,15]]},"references-count":61,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.2196\/18803","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.18803","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,15]]}}}