{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T15:03:13Z","timestamp":1793977393757,"version":"4.8.0"},"reference-count":33,"publisher":"IOP Publishing","issue":"7","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Science and Technology R & D Fund of Shenzhen","award":["JCYJ20180302150148666"],"award-info":[{"award-number":["JCYJ20180302150148666"]}]},{"name":"Shenzhen Strategic Emerging Industry Development Special Funding","award":["ZDYBH201900000007"],"award-info":[{"award-number":["ZDYBH201900000007"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2022,7,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . As cardiovascular diseases are a leading cause of death, early and accurate diagnosis of cardiac abnormalities for a lower cost becomes particularly important. Given electrocardiogram (ECG) datasets from multiple sources, there exist many challenges to the development of generalized models that can identify multiple types of cardiac abnormalities from both 12-lead ECG signals and reduced-lead ECG signals. In this study, our objective is to build robust models that can accurately classify 30 types of abnormalities from various lead combinations of ECG signals.\n                    <jats:italic>Approach<\/jats:italic>\n                    . Given the challenges of this problem, we propose a framework for building robust models for ECG signal classification. Firstly, a preprocessing workflow is adopted for each ECG dataset to mitigate the problem of data divergence. Secondly, to capture the lead-wise relations, we use a squeeze-and-excitation deep residual network as our base model. Thirdly, we propose a cross-relabeling strategy and apply the sign-augmented loss function to tackle the corrupted labels in the data. Furthermore, we utilize a pos-if-any-pos ensemble strategy and a dataset-wise cross-evaluation strategy to handle the uncertainty of the data distribution in the application.\n                    <jats:italic>Main results<\/jats:italic>\n                    . In the Physionet\/Computing in Cardiology Challenge 2021, our approach achieved the challenge metric scores of 0.57, 0.59, 0.59, 0.58, 0.57 on 12-, 6-, 4-, 3- and 2-lead versions and an averaged challenge metric score of 0.58 over all the lead versions.\n                    <jats:italic>Significance<\/jats:italic>\n                    . Using the proposed framework, we have developed the models from several large datasets with sufficiently labeled abnormalities. Our models are able to identify 30 ECG abnormalities accurately based on various lead combinations of ECG signals. The performance on hidden test data demonstrates the effectiveness of the proposed approaches.\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/ac70a4","type":"journal-article","created":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T18:34:11Z","timestamp":1652812451000},"page":"074002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Abnormality classification from electrocardiograms with various lead combinations"],"prefix":"10.1088","volume":"43","author":[{"given":"Zhuoyang","family":"Xu","sequence":"first","affiliation":[{"name":"Ping An Healthcare Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangming","family":"Guo","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingting","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Liu","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guotong","family":"Xie","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology"},{"name":"Ping An Healthcare and Technology Co., Ltd"},{"name":"Ping An International Smart City Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichong","family":"Li","sequence":"additional","affiliation":[{"name":"Fuwai Hospital Chinese Academy of Medical Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2022,7,18]]},"reference":[{"key":"pmeaac70a4bib1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/abc960","type":"journal-article","article-title":"Classification of 12-lead ECGs: the Physionet\/Computing in Cardiology Challenge 2020","volume":"41","author":"Alday","year":"2020","journal-title":"Physiol. Meas."},{"key":"pmeaac70a4bib2","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/S0002-9149(87)80062-0","type":"journal-article","article-title":"Identification of the optimal electrocardiographic leads for detecting acute epicardial injury in acute myocardial infarction","volume":"59","author":"Aldrich","year":"1987","journal-title":"Am. J. Cardiol."},{"key":"pmeaac70a4bib3","first-page":"537","author":"Alexakis","year":"2003","type":"conference-proceedings"},{"key":"pmeaac70a4bib4","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1111\/pace.13062","type":"journal-article","article-title":"Early detection and treatment of atrial arrhythmias alleviates the arrhythmic burden in paced patients: the setam study","volume":"40","author":"Amara","year":"2017","journal-title":"Pacing Clin. Electrophysiol."},{"key":"pmeaac70a4bib5","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/aadf0f","type":"journal-article","article-title":"Classification of short single-lead electrocardiograms (ECGs) for atrial fibrillation detection using piecewise linear spline and xgboost","volume":"39","author":"Chen","year":"2018","journal-title":"Physiol. Meas."},{"key":"pmeaac70a4bib6","first-page":"1","type":"conference-proceedings","article-title":"AF classification from a short single lead ECG recording: the Physionet\/Computing in Cardiology Challenge 2017","author":"Clifford","year":"2017"},{"key":"pmeaac70a4bib7","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1054\/jelc.2002.37150","type":"journal-article","article-title":"Comparison of a new reduced lead set ECG with the standard ECG for diagnosing cardiac arrhythmias and myocardial ischemia","volume":"35","author":"Drew","year":"2002","journal-title":"J. Electrocardiol."},{"key":"pmeaac70a4bib8","doi-asserted-by":"publisher","first-page":"153","DOI":"10.2174\/1573403X14666180222102312","type":"journal-article","article-title":"Management of measurable variable cardiovascular disease\u2019risk factors","volume":"14","author":"Francula-Zaninovic","year":"2018","journal-title":"Curr. Cardiol. Rev."},{"key":"pmeaac70a4bib9","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","type":"journal-article","article-title":"Physiotoolkit and Pphysionet: components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"pmeaac70a4bib10","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.jelectrocard.2006.12.011","type":"journal-article","article-title":"Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome","volume":"40","author":"Green","year":"2007","journal-title":"J. Electrocardiol."},{"key":"pmeaac70a4bib11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CinC53138.2021.9662737","type":"conference-proceedings","article-title":"Towards high generalization performance on electrocardiogram classification","volume":"48","author":"Han","year":"2021"},{"key":"pmeaac70a4bib12","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","type":"journal-article","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018","journal-title":"Proc. IEEE Conf. on Computer Vision and Pattern Recognition"},{"key":"pmeaac70a4bib13","doi-asserted-by":"publisher","first-page":"123-9","DOI":"10.1054\/jelc.2002.37169","type":"journal-article","article-title":"The centennial of the Einthoven electrocardiogram","volume":"35","author":"Kligfield","year":"2002","journal-title":"J. Electrocardiol."},{"key":"pmeaac70a4bib14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CinC53138.2021.9662822","type":"conference-proceedings","article-title":"Towards generalization of cardiac abnormality classification using ECG signal","volume":"48","author":"Li","year":"2021"},{"key":"pmeaac70a4bib15","first-page":"343","type":"conference-proceedings","article-title":"ECG feature extraction using Daubechies wavelets","author":"Mahmoodabadi","year":"2005"},{"key":"pmeaac70a4bib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2020.107","type":"conference-proceedings","article-title":"Wide and deep transformer neural network for 12-lead ECG classification","author":"Natarajan","year":"2020"},{"key":"pmeaac70a4bib17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CinC53138.2021.9662723","type":"conference-proceedings","article-title":"Classification of ECG using ensemble of residual CNNS with attention mechanism","volume":"48","author":"Nejedly","year":"2021"},{"key":"pmeaac70a4bib18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2020.063","type":"conference-proceedings","article-title":"Electrocardiogram classification by modified Efficientnet with data augmentation","author":"Nonaka","year":"2020"},{"key":"pmeaac70a4bib19","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TBME.1985.325532","type":"journal-article","article-title":"A real-time QRS detection algorithm","volume":"BME-32","author":"Pan","year":"1985","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaac70a4bib20","author":"Qui\u00f1onero-Candela","year":"2009","type":"book"},{"key":"pmeaac70a4bib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CinC53138.2021.9662687","type":"conference-proceedings","article-title":"Will two do? Varying dimensions in electrocardiography: the Physionet\/Computing in Cardiology Challenge 2021","author":"Reyna","year":"2021"},{"key":"pmeaac70a4bib22","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1088\/1361-6579\/ac79fd","type":"journal-article","article-title":"Issues in the automated classification of multilead ECGs using heterogeneous labels and populations","volume":"4","author":"Reyna","year":"2022","journal-title":"Personnel"},{"key":"pmeaac70a4bib23","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/ICCV48922.2021.00015","type":"conference-proceedings","article-title":"Asymmetric loss for multi-label classification","author":"Ridnik","year":"2021"},{"key":"pmeaac70a4bib24","doi-asserted-by":"publisher","first-page":"4377","DOI":"10.3390\/s19204377","type":"journal-article","article-title":"Single-lead ECG recordings including Einthoven and Wilson leads by a smartwatch: a new era of patient directed early ECG differential diagnosis of cardiac diseases?","volume":"19","author":"Samol","year":"2019","journal-title":"Sensors"},{"key":"pmeaac70a4bib25","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1016\/j.procs.2018.05.045","type":"journal-article","article-title":"Classification of ECG arrhythmia using recurrent neural networks","volume":"132","author":"Singh","year":"2018","journal-title":"Proc. Comput. Sci."},{"key":"pmeaac70a4bib26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3316781.3317918","type":"conference-proceedings","article-title":"System-level hardware failure prediction using deep learning","author":"Sun","year":"2019"},{"key":"pmeaac70a4bib27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2017.166-054","type":"conference-proceedings","article-title":"Arrhythmia classification from the abductive interpretation of short single-lead ECG records","author":"Teijeiro","year":"2017"},{"key":"pmeaac70a4bib28","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.bspc.2014.08.010","type":"journal-article","article-title":"Heart diseases prediction based on ecg signals\u2019 classification using a genetic-fuzzy system and dynamical model of ECG signals","volume":"14","author":"Vafaie","year":"2014","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaac70a4bib29","first-page":"5998","type":"journal-article","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"pmeaac70a4bib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2017.161-460","type":"conference-proceedings","article-title":"Cardiac arrhythmia detection from ECG combining convolutional and long short-term memory networks","author":"Warrick","year":"2017"},{"key":"pmeaac70a4bib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CinC53138.2021.9662787","type":"conference-proceedings","article-title":"Multi-label cardiac abnormality classification from electrocardiogram using deep convolutional neural networks","volume":"48","author":"Wickramasinghe","year":"2021"},{"key":"pmeaac70a4bib32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CinC53138.2021.9662746","type":"conference-proceedings","article-title":"Multi-label cardiac abnormalities classification on selected leads of ECG signals","volume":"48","author":"Xu","year":"2021"},{"key":"pmeaac70a4bib33","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ac08e6","type":"journal-article","article-title":"Identification of 27 abnormalities from multi-lead ECG signals: an ensembled Se_ResNet framework with sign loss function","volume":"42","author":"Zhu","year":"2021","journal-title":"Physiol. Meas."}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:59:20Z","timestamp":1778777960000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ac70a4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,7,18]]},"published-print":{"date-parts":[[2022,7,29]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/ac70a4","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,18]]},"assertion":[{"value":"Abnormality classification from electrocardiograms with various lead combinations","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-01-11","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-05-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-07-18","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}