{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T13:45:11Z","timestamp":1781790311169,"version":"3.54.5"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Heart disease diagnosis is a challenging task and it is important to explore useful information from the massive amount of electrocardiogram (ECG) records of patients. The high-precision diagnostic identification of ECG can save clinicians and cardiologists considerable time while helping reduce the possibility of misdiagnosis at the same time.Currently, some deep learning-based methods can effectively perform feature selection and classification prediction, reducing the consumption of manpower.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>In this work, an end-to-end deep learning framework based on convolutional neural network (CNN) is proposed for ECG signal processing and arrhythmia classification. In the framework, a transformer network is embedded in CNN to capture the temporal information of ECG signals and a new link constraint is introduced to the loss function to enhance the classification ability of the embedding vector.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>To evaluate the proposed method, extensive experiments based on real-world data were conducted. Experimental results show that the proposed model achieve better performance than most baselines. The experiment results also proved that the transformer network pays more attention to the temporal continuity of the data and captures the hidden deep features of the data well. The link constraint strengthens the constraint on the embedded features and effectively suppresses the effect of data imbalance on the results.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>In this paper, an end-to-end model is used to process ECG signal and classify arrhythmia. The model combine CNN and Transformer network to extract temporal information in ECG signal and is capable of performing arrhythmia classification with acceptable accuracy. The model can help cardiologists perform assisted diagnosis of heart disease and improve the efficiency of healthcare delivery.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12911-021-01546-2","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T17:11:12Z","timestamp":1623258672000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":159,"title":["Constrained transformer network for ECG signal processing and arrhythmia classification"],"prefix":"10.1186","volume":"21","author":[{"given":"Chao","family":"Che","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiliang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,6,9]]},"reference":[{"issue":"9","key":"1546_CR1","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1016\/S1474-4422(16)30073-4","volume":"15","author":"VL Feigin","year":"2016","unstructured":"Feigin VL, Roth GA, Naghavi M, Parmar P, Krishnamurthi R, Chugh S, Mensah GA, Norrving B, Shiue I, Ng M, et al. Global burden of stroke and risk factors in 188 countries, during 1990\u20132013: a systematic analysis for the global burden of disease study 2013. Lancet Neurol. 2016;15(9):913\u201324.","journal-title":"Lancet Neurol"},{"issue":"6","key":"1546_CR2","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.jelectrocard.2018.08.008","volume":"51","author":"J Rubin","year":"2018","unstructured":"Rubin J, Parvaneh S, Rahman A, Conroy B, Babaeizadeh S. Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings. J Electrocardiol. 2018;51(6):18\u201321.","journal-title":"J Electrocardiol"},{"issue":"2","key":"1546_CR3","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/JBHI.2016.2631247","volume":"22","author":"T Teijeiro","year":"2018","unstructured":"Teijeiro T, F\u00e9lix P, Presedo J, Castro D. Heartbeat classification using abstract features from the abductive interpretation of the ECG. IEEE J Biomed Health Inform. 2018;22(2):409\u201320.","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"1546_CR4","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1109\/TBME.2009.2013934","volume":"56","author":"T Ince","year":"2009","unstructured":"Ince T, Kiranyaz S, Gabbouj M. A generic and robust system for automated patient-specific classification of ECG signals. IEEE Trans Biomed Eng. 2009;56(5):1415\u201326.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"3","key":"1546_CR5","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","volume":"63","author":"S Kiranyaz","year":"2015","unstructured":"Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng. 2015;63(3):664\u201375.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"5","key":"1546_CR6","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1109\/10.918594","volume":"48","author":"R Hoekema","year":"2001","unstructured":"Hoekema R, Uijen GJ, Van Oosterom A. Geometrical aspects of the interindividual variability of multilead ECG recordings. IEEE Trans Biomed Eng. 2001;48(5):551\u20139.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"2","key":"1546_CR7","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1109\/TNB.2021.3056351","volume":"20","author":"B Cao","year":"2021","unstructured":"Cao B, Zhang X, Wu J, Wang B, Zhang Q, Wei X. Minimum free energy coding for DNA storage. IEEE Trans Nanobiosci. 2021;20(2):212\u201322. https:\/\/doi.org\/10.1109\/TNB.2021.3056351.","journal-title":"IEEE Trans Nanobiosci"},{"key":"1546_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2020.3011582","author":"B Cao","year":"2020","unstructured":"Cao B, Li X, Zhang X, Wang B, Zhang Q, Wei X. Designing uncorrelated address constrain for DNA storage by DMVO algorithm. IEEE\/ACM Trans Comput Biol Bioinform. 2020. https:\/\/doi.org\/10.1109\/TCBB.2020.3011582.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"12","key":"1546_CR9","doi-asserted-by":"publisher","first-page":"2535","DOI":"10.1109\/TBME.2006.883802","volume":"53","author":"P De Chazal","year":"2006","unstructured":"De Chazal P, Reilly RB. A patient-adapting heartbeat classifier using ECG morphology and heartbeat interval features. IEEE Trans Biomed Eng. 2006;53(12):2535\u201343.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"7","key":"1546_CR10","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1109\/TBME.2004.827359","volume":"51","author":"P De Chazal","year":"2004","unstructured":"De Chazal P, O\u2019Dwyer M, Reilly RB. Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans Biomed Eng. 2004;51(7):1196\u2013206.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"8","key":"1546_CR11","doi-asserted-by":"publisher","first-page":"10195","DOI":"10.1007\/s11042-017-5318-1","volume":"77","author":"R Varatharajan","year":"2018","unstructured":"Varatharajan R, Manogaran G, Priyan M. A big data classification approach using LDA with an enhanced SVM method for ECG signals in cloud computing. Multimed Tools Appl. 2018;77(8):10195\u2013215.","journal-title":"Multimed Tools Appl"},{"key":"1546_CR12","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.bspc.2015.10.008","volume":"25","author":"S Shadmand","year":"2016","unstructured":"Shadmand S, Mashoufi B. A new personalized ECG signal classification algorithm using block-based neural network and particle swarm optimization. Biomed Signal Process Control. 2016;25:12\u201323.","journal-title":"Biomed Signal Process Control"},{"key":"1546_CR13","doi-asserted-by":"crossref","unstructured":"Zhang J-w, Wang L-P, Liu X, Zhu H-H, Dong J. Chinese cardiovascular disease database (CCDD) and its management tool. In: IEEE international conference on bioinformatics and bioengineering. IEEE; 2010. p. 66\u20132","DOI":"10.1109\/BIBE.2010.19"},{"issue":"3","key":"1546_CR14","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1360\/N112014-00060","volume":"45","author":"L Jin","year":"2015","unstructured":"Jin L, Dong J. Deep learning research on clinical electrocardiogram analysis. Sci Sin Inform. 2015;45(3):398.","journal-title":"Sci Sin Inform"},{"issue":"1","key":"1546_CR15","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","volume":"25","author":"AY Hannun","year":"2019","unstructured":"Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, Ng AY. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med. 2019;25(1):65.","journal-title":"Nat Med"},{"key":"1546_CR16","doi-asserted-by":"crossref","unstructured":"Shashikumar SP, Shah AJ, Clifford GD, Nemati S. Detection of paroxysmal atrial fibrillation using attention-based bidirectional recurrent neural networks. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. ACM; 2018. p. 715\u201323","DOI":"10.1145\/3219819.3219912"},{"key":"1546_CR17","unstructured":"Ribeiro AH, Ribeiro MH, Paix\u00e3o G, Oliveira D, Gomes PR, Canazart JA, Pifano M, Meira\u00a0Jr W, Sch\u00f6n TB, Ribeiro AL. Automatic diagnosis of short-duration 12-lead ECG using a deep convolutional network. 2018. arXiv preprint arXiv:1811.12194"},{"key":"1546_CR18","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.inffus.2019.06.024","volume":"53","author":"Q Yao","year":"2020","unstructured":"Yao Q, Wang R, Fan X, Liu J, Li Y. Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network. Inform Fusion. 2020;53:174\u201382.","journal-title":"Inform Fusion"},{"key":"1546_CR19","unstructured":"Jun TJ, Nguyen HM, Kang D, Kim D, Kim D, Kim Y-H. ECG arrhythmia classification using a 2-d convolutional neural network. 2018. arXiv preprint arXiv:1804.06812"},{"issue":"1","key":"1546_CR20","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/10.650355","volume":"64","author":"P Li","year":"2016","unstructured":"Li P, Wang Y, He J, Wang L, Tian Y, Zhou T-S, Li T, Li J-S. High-performance personalized heartbeat classification model for long-term ECG signal. IEEE Trans Biomed Eng. 2016;64(1):78\u201386.","journal-title":"IEEE Trans Biomed Eng"},{"key":"1546_CR21","unstructured":"Mostayed A, Luo J, Shu X, Wee W. Classification of 12-lead ECG signals with bi-directional LSTM network. 2018. arXiv preprint arXiv:1811.02090"},{"key":"1546_CR22","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/JBHI.2019.2911367","volume":"24","author":"S Saadatnejad","year":"2019","unstructured":"Saadatnejad S, Oveisi M, Hashemi M. LSTM-based ECG classification for continuous monitoring on personal wearable devices. IEEE J Biomed Health Inform. 2019;24:515\u201323.","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"1546_CR23","doi-asserted-by":"publisher","first-page":"100886","DOI":"10.1016\/j.isci.2020.100886","volume":"23","author":"T-M Chen","year":"2020","unstructured":"Chen T-M, Huang C-H, Shih ES, Hu Y-F, Hwang M-J. Detection and classification of cardiac arrhythmias by a challenge-best deep learning neural network model. Iscience. 2020;23(3):100886.","journal-title":"Iscience"},{"key":"1546_CR24","unstructured":"Rajpurkar P, Hannun AY, Haghpanahi M, Bourn C, Ng AY. Cardiologist-level arrhythmia detection with convolutional neural networks. 2017. arXiv preprint arXiv:1707.01836"},{"issue":"7","key":"1546_CR25","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1166\/jmihi.2018.2442","volume":"8","author":"F Liu","year":"2018","unstructured":"Liu F, Liu C, Zhao L, Zhang X, Wu X, Xu X, Liu Y, Ma C, Wei S, He Z, et al. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection. J Med Imaging Health Inform. 2018;8(7):1368\u201373.","journal-title":"J Med Imaging Health Inform"},{"key":"1546_CR26","doi-asserted-by":"publisher","unstructured":"Qu Y, Liu C, Zhang K, Xiao K, Jin B, Xiong H. Diagnostic sparse connectivity networks with regularization template. IEEE Trans Knowledge Data Eng. https:\/\/doi.org\/10.1109\/TKDE.2021.3075668.","DOI":"10.1109\/TKDE.2021.3075668"},{"issue":"1","key":"1546_CR27","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1109\/TMI.2018.2863670","volume":"38","author":"C Qin","year":"2019","unstructured":"Qin C, Schlemper J, Caballero J, Price AN, Hajnal JV, Rueckert D. Convolutional recurrent neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging. 2019;38(1):280\u201390.","journal-title":"IEEE Trans Med Imaging"},{"key":"1546_CR28","doi-asserted-by":"crossref","unstructured":"Hershey S, Chaudhuri S, Ellis DP, Gemmeke JF, Jansen A, Moore RC, Plakal M, Platt D, Saurous RA, Seybold B, et al. CNN architectures for large-scale audio classification. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE; 2017. p. 131\u201335","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"1546_CR29","doi-asserted-by":"crossref","unstructured":"Shang L, Yang Q, Wang J, Li S, Lei W. Detection of rail surface defects based on CNN image recognition and classification. In: 20th International conference on advanced communication technology (ICACT). IEEE; 2018. p. 45\u201351","DOI":"10.23919\/ICACT.2018.8323642"},{"key":"1546_CR30","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. 2015. arXiv preprint arXiv:1502.03167"},{"key":"1546_CR31","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I. Attention is all you need. In: Advances in neural information processing systems. 2017. p. 5998\u20136008"},{"issue":"1","key":"1546_CR32","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1109\/TMI.2018.2863670","volume":"38","author":"C Qin","year":"2018","unstructured":"Qin C, Schlemper J, Caballero J, Price AN, Hajnal JV, Rueckert D. Convolutional recurrent neural networks for dynamic MR image reconstruction. IEEE Trans Med Imaging. 2018;38(1):280\u201390.","journal-title":"IEEE Trans Med Imaging"},{"key":"1546_CR33","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D. Show and tell: a neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015, p. 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1546_CR34","first-page":"123","volume-title":"Adaptive switching circuits","author":"B Widrow","year":"1988","unstructured":"Widrow B, Hoff ME. Adaptive switching circuits. Cambridge: MIT Press; 1988. p. 123\u201334."},{"issue":"24","key":"1546_CR35","doi-asserted-by":"publisher","first-page":"2571","DOI":"10.1001\/jama.2009.888","volume":"301","author":"S Cheng","year":"2009","unstructured":"Cheng S, Keyes MJ, Larson MG, McCabe EL, Newton-Cheh C, Levy D, Benjamin EJ, Vasan RS, Wang TJ. Long-term outcomes in individuals with prolonged PR interval or first-degree atrioventricular block. JAMA. 2009;301(24):2571\u20137.","journal-title":"JAMA"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-021-01546-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-021-01546-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-021-01546-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T17:11:20Z","timestamp":1623258680000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-021-01546-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,9]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["1546"],"URL":"https:\/\/doi.org\/10.1186\/s12911-021-01546-2","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,9]]},"assertion":[{"value":"27 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"184"}}