{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T21:40:24Z","timestamp":1793569224931,"version":"4.5.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T00:00:00Z","timestamp":1710201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T00:00:00Z","timestamp":1710201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001774","name":"University of Sydney","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001774","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. of Cardiovasc. Trans. Res."],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study introduces two models, ConvLSTM2D-liquid time-constant network (CLTC) and ConvLSTM2D-closed-form continuous-time neural network (CCfC), designed for abnormality identification using electrocardiogram (ECG) data. Trained on the Telehealth Network of Minas Gerais (TNMG) subset dataset, both models were evaluated for their performance, generalizability capacity, and resilience. They demonstrated comparable results in terms of F1 scores and AUROC values. The CCfC model achieved slightly higher accuracy, while the CLTC model showed better handling of empty channels. Remarkably, the models were successfully deployed on a resource-constrained microcontroller, proving their suitability for edge device applications. Generalization capabilities were confirmed through the evaluation on the China Physiological Signal Challenge 2018 (CPSC) dataset. The models\u2019 efficient resource utilization, occupying 70.6% of memory and 9.4% of flash memory, makes them promising candidates for real-world healthcare applications. Overall, this research advances abnormality identification in ECG data, contributing to the progress of AI in healthcare.<\/jats:p>\n                  <jats:p>\n                    <jats:bold>Graphical Abstract<\/jats:bold>\n                  <\/jats:p>","DOI":"10.1007\/s12265-024-10504-y","type":"journal-article","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T20:02:37Z","timestamp":1710273757000},"page":"879-892","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Efficient Edge-AI Models for Robust ECG Abnormality Detection on Resource-Constrained Hardware"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2796-6734","authenticated-orcid":false,"given":"Zhaojing","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luis Fernando","family":"Herbozo Contreras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wing Hang","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leping","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nhan Duy","family":"Truong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armin","family":"Nikpour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omid","family":"Kavehei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,12]]},"reference":[{"issue":"7334","key":"10504_CR1","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1136\/bmj.324.7334.415","volume":"324","author":"S Meek","year":"2002","unstructured":"Meek S, Morris F. ABC of clinical electrocardiography: Introduction. I-Leads, rate, rhythm, and cardiac axis. BMJ: British Medical Journal. 2002;324(7334):415.","journal-title":"BMJ: British Medical Journal."},{"issue":"10","key":"10504_CR2","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1038\/s42256-020-00237-3","volume":"2","author":"M Lechner","year":"2020","unstructured":"Lechner M, Hasani R, Amini A, Henzinger TA, Rus D, Grosu R. Neural circuit policies enabling auditable autonomy. Nat Mach Intell. 2020;2(10):642\u201352.","journal-title":"Nat Mach Intell"},{"key":"10504_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102194","volume":"63","author":"G Petmezas","year":"2021","unstructured":"Petmezas G, Haris K, Stefanopoulos L, Kilintzis V, Tzavelis A, Rogers JA, Katsaggelos AK, Maglaveras N. Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets. Biomedical Signal Processing and Control. 2021;63: 102194.","journal-title":"Biomedical Signal Processing and Control."},{"key":"10504_CR4","doi-asserted-by":"crossref","unstructured":"Gupta V, Mittal M, Mittal V. A novel FrWT based arrhythmia detection in ECG signal using YWARA and PCA. Wireless Personal Communications. 2022, pages 1\u201318.","DOI":"10.1007\/s11277-021-09403-1"},{"key":"10504_CR5","doi-asserted-by":"crossref","unstructured":"Chen T-M, Huang C-H, Shih ESC, 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).","DOI":"10.1016\/j.isci.2020.100886"},{"key":"10504_CR6","doi-asserted-by":"crossref","unstructured":"Huang J-S, Chen B-Q, Zeng N-Y, Cao X-C, Li Y. Accurate classification of ECG arrhythmia using MOWPT enhanced fast compression deep learning networks. Journal of Ambient Intelligence and Humanized Computing. 2020, pages 1\u201318.","DOI":"10.1007\/s12652-020-02110-y"},{"key":"10504_CR7","doi-asserted-by":"crossref","unstructured":"Huang Z, Herbozo Contreras LF, Yu L et al. S4D-ECG: A shallow state-of-the-art model for cardiac abnormality classification. Cardiovasc Eng Tech 2024.","DOI":"10.1101\/2023.06.30.23292069"},{"key":"10504_CR8","doi-asserted-by":"crossref","unstructured":"Hasani R, Lechner M, Amini A, Rus D, Grosu R. Liquid time-constant networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume\u00a035, pages 7657\u20137666, 2021.","DOI":"10.1609\/aaai.v35i9.16936"},{"issue":"11","key":"10504_CR9","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1038\/s42256-022-00556-7","volume":"4","author":"R Hasani","year":"2022","unstructured":"Hasani R, Lechner M, Amini A, Liebenwein L, Ray A, Tschaikowski M, Teschl G, Rus D. Closed-form continuous-time neural networks. Nat Mach Intell. 2022;4(11):992\u20131003.","journal-title":"Nat Mach Intell."},{"issue":"7","key":"10504_CR10","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."},{"issue":"1","key":"10504_CR11","doi-asserted-by":"publisher","first-page":"1760","DOI":"10.1038\/s41467-020-15432-4","volume":"11","author":"AH Ribeiro","year":"2020","unstructured":"Ribeiro AH, Ribeiro MH, Paix\u00e3o GMM, Oliveira DM, Gomes PR, Canazart JA, Ferreira MPS, Andersson CR, Macfarlane PW, Meira W Jr, et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun. 2020;11(1):1760.","journal-title":"Nat Commun."},{"issue":"5","key":"10504_CR12","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1016\/j.amjcard.2018.05.015","volume":"122","author":"Z Wang","year":"2018","unstructured":"Wang Z, Chen Z, Wang X, Zhang L, Li S, Tian Y, Shao L, Hu H, Gao R, et al. The disease burden of atrial fibrillation in China from a national cross-sectional survey. Am J Cardiol. 2018;122(5):793\u20138.","journal-title":"Am J Cardiol."},{"issue":"3","key":"10504_CR13","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1016\/j.jpeds.2013.03.054","volume":"163","author":"SN Chiu","year":"2013","unstructured":"Chiu SN, Lin LY, Wang JK, Lu CW, Chang CW, Lin MT, Hua YC, Lue HC, Wu MH. Long-term outcomes of pediatric sinus bradycardia. J Pediatr. 2013;163(3):885\u20139.","journal-title":"J Pediatr."},{"issue":"2","key":"10504_CR14","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.eupc.2004.12.007","volume":"7","author":"A-M Still","year":"2005","unstructured":"Still A-M, Raatikainen P, Ylitalo A, Kauma H, Ik\u00e4heimo M, Kes\u00e4niemi YA, Huikuri HV. Prevalence, characteristics and natural course of inappropriate sinus tachycardia. EP Europace. 2005;7(2):104\u201312.","journal-title":"EP Europace."},{"issue":"10","key":"10504_CR15","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1002\/clc.22454","volume":"38","author":"Y Xiong","year":"2015","unstructured":"Xiong Y, Wang L, Liu W, Hankey GJ, Xu B, Wang S. The prognostic significance of right bundle branch block: a meta-analysis of prospective cohort studies. Clin Cardiol. 2015;38(10):604\u201313.","journal-title":"Clin Cardiol."},{"key":"10504_CR16","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Riera AR, Barbosa-Barros R, de Rezende Barbosa MPC, Daminello-Raimundo R, de Abreu LC, Nikus K. Left bundle branch block: epidemiology, etiology, anatomic features, electrovectorcardiography, and classification proposal. Ann Noninvasive Electrocardiol. 2019;24(2).","DOI":"10.1111\/anec.12572"},{"issue":"2","key":"10504_CR17","first-page":"181","volume":"2","author":"T Nikolaidou","year":"2016","unstructured":"Nikolaidou T, Ghosh JM, Clark AL. Outcomes related to first-degree atrioventricular block and therapeutic implications in patients with heart failure. JACC: Clinical Electrophysiology. 2016;2(2):181\u201392.","journal-title":"JACC: Clinical Electrophysiology."},{"key":"10504_CR18","doi-asserted-by":"crossref","unstructured":"Huang Z, MacLachlan S, Yu L, Herbozo\u00a0Contreras LF, Truong ND, Ribeiro AH, Kavehei O. Generalization challenges in ECG deep learning: insights from dataset characteristics and attention mechanism. medRxiv. 2023b;2023\u201307.","DOI":"10.1101\/2023.07.05.23292238"},{"issue":"6","key":"10504_CR19","first-page":"536","volume":"7","author":"S Butterworth","year":"1930","unstructured":"Butterworth S, et al. On the theory of filter amplifiers. Wireless Engineer. 1930;7(6):536\u201341.","journal-title":"Wireless Engineer."},{"issue":"6","key":"10504_CR20","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.jelectrocard.2015.08.034","volume":"48","author":"LG Tereshchenko","year":"2015","unstructured":"Tereshchenko LG, Josephson ME. Frequency content and characteristics of ventricular conduction. J Electrocardiol. 2015;48(6):933\u20137.","journal-title":"J Electrocardiol."},{"key":"10504_CR21","first-page":"33","volume-title":"Han S","author":"J Lin","year":"2020","unstructured":"Lin J, Chen W-M, Lin Y, Gan C. Han S. Mcunet: Tiny deep learning on IoT devices. Adv Neural Inf Process Syst; 2020. p. 33."},{"key":"10504_CR22","unstructured":"Lin J, Chen W-M, Cai H, Gan C, Han S. MCUNetV2: memory-efficient patch-based inference for tiny deep learning. In: Annual Conference on Neural Information Processing Systems (NeurIPS). 2021."},{"key":"10504_CR23","doi-asserted-by":"crossref","unstructured":"Mukhopadhyay S, Dey S, Ghose A, Tyagi A. Automated generation of tiny model for real-time ECG classification on tiny edge devices. Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems. 2022;756\u2013757.","DOI":"10.1145\/3560905.3568081"},{"key":"10504_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119407","volume":"216","author":"J Chen","year":"2023","unstructured":"Chen J, Jiang M, Zhang X, da Silva DS, de Albuquerque VHC, Wu W. Implementing ultra-lightweight co-inference model in ubiquitous edge device for atrial fibrillation detection. Expert Syst Appl. 2023;216: 119407.","journal-title":"Expert Syst Appl."}],"container-title":["Journal of Cardiovascular Translational Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12265-024-10504-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12265-024-10504-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12265-024-10504-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T11:35:51Z","timestamp":1725363351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12265-024-10504-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,12]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10504"],"URL":"https:\/\/doi.org\/10.1007\/s12265-024-10504-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.08.31.23294925","asserted-by":"object"}]},"ISSN":["1937-5387","1937-5395"],"issn-type":[{"value":"1937-5387","type":"print"},{"value":"1937-5395","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,12]]},"assertion":[{"value":"10 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}