{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:22:05Z","timestamp":1773519725126,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T00:00:00Z","timestamp":1590537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["RTI2018-101475-BI100"],"award-info":[{"award-number":["RTI2018-101475-BI100"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["RTI2018-101475-BI100"],"award-info":[{"award-number":["RTI2018-101475-BI100"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Gobierno Vasco","doi-asserted-by":"publisher","award":["IT1229-19"],"award-info":[{"award-number":["IT1229-19"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Gobierno Vasco","doi-asserted-by":"publisher","award":["PRE-2019-2-0066"],"award-info":[{"award-number":["PRE-2019-2-0066"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock\/no-shock decisions during CPR using convolutional neural networks (CNN). A total of 3319 ECG segments of 9    s    extracted during chest compressions were used, whereof 586 were shockable and 2733 nonshockable. Chest compression artifacts were removed using a Recursive Least Squares (RLS) filter, and the filtered ECG was fed to a CNN classifier with three convolutional blocks and two fully connected layers for the shock\/no-shock classification. A 5-fold cross validation architecture was adopted to train\/test the algorithm, and the proccess was repeated 100 times to statistically characterize the performance. The proposed architecture was compared to the most accurate algorithms that include handcrafted ECG features and a random forest classifier (baseline model). The median (90% confidence interval) sensitivity, specificity, accuracy and balanced accuracy of the method were 95.8% (94.6\u201396.8), 96.1% (95.8\u201396.5), 96.1% (95.7\u201396.4) and 96.0% (95.5\u201396.5), respectively. The proposed algorithm outperformed the baseline model by 0.6-points in accuracy. This new approach shows the potential of deep learning methods to provide reliable diagnosis of the cardiac rhythm without interrupting chest compression therapy.<\/jats:p>","DOI":"10.3390\/e22060595","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T08:27:48Z","timestamp":1590654468000},"page":"595","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0312-4469","authenticated-orcid":false,"given":"Iraia","family":"Isasi","sequence":"first","affiliation":[{"name":"Department of Communications Engineering, University of the Basque Country UPV\/EHU, 48013 Bilbao, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9521-1852","authenticated-orcid":false,"given":"Unai","family":"Irusta","sequence":"additional","affiliation":[{"name":"Department of Communications Engineering, University of the Basque Country UPV\/EHU, 48013 Bilbao, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6409-1429","authenticated-orcid":false,"given":"Elisabete","family":"Aramendi","sequence":"additional","affiliation":[{"name":"Department of Communications Engineering, University of the Basque Country UPV\/EHU, 48013 Bilbao, Spain"}]},{"given":"Trygve","family":"Eftest\u00f8l","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of Stavanger, 4036 Stavanger, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7881-1757","authenticated-orcid":false,"given":"Jo","family":"Kramer-Johansen","sequence":"additional","affiliation":[{"name":"Norwegian National Advisory Unit on Prehospital Emergency Medicine (NAKOS), Oslo University Hospital and University of Oslo, 0424 Oslo, Norway"}]},{"given":"Lars","family":"Wik","sequence":"additional","affiliation":[{"name":"Norwegian National Advisory Unit on Prehospital Emergency Medicine (NAKOS), Oslo University Hospital and University of Oslo, 0424 Oslo, Norway"}]}],"member":"1968","published-online":{"date-parts":[[2020,5,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1016\/j.resuscitation.2010.08.006","article-title":"Global incidences of out-of-hospital cardiac arrest and survival rates: Systematic review of 67 prospective studies","volume":"81","author":"Berdowski","year":"2010","journal-title":"Resuscitation"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.resuscitation.2015.02.003","article-title":"Out-of-hospital cardiac arrest survival improving over time: Results from the Resuscitation Outcomes Consortium (ROC)","volume":"91","author":"Daya","year":"2015","journal-title":"Resuscitation"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.resuscitation.2015.07.015","article-title":"European Resuscitation Council Guidelines for Resuscitation 2015: Section 2. Adult basic life support and automated external defibrillation","volume":"95","author":"Perkins","year":"2015","journal-title":"Resuscitation"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"990","DOI":"10.7326\/0003-4819-135-11-200112040-00011","article-title":"Automated external defibrillators: Technical considerations and clinical promise","volume":"135","author":"Takata","year":"2001","journal-title":"Ann. Intern. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1161\/01.CIR.95.6.1677","article-title":"Automatic external defibrillators for public access defibrillation: Recommendations for specifying and reporting arrhythmia analysis algorithm performance, incorporating new waveforms, and enhancing safety: A statement for health professionals from the American Heart Association Task Force on Automatic External Defibrillation, Subcommittee on AED Safety and Efficacy","volume":"95","author":"Kerber","year":"1997","journal-title":"Circulation"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"S421","DOI":"10.1097\/01.CCM.0000134265.35871.2B","article-title":"Wide variation in cardiopulmonary resuscitation interruption intervals among commercially available automated external defibrillators may affect survival despite high defibrillation efficacy","volume":"32","author":"Snyder","year":"2004","journal-title":"Crit. Care Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1067\/S0196-0644(03)00383-4","article-title":"Interruption of cardiopulmonary resuscitation with the use of the automated external defibrillator in out-of-hospital cardiac arrest","volume":"42","author":"Sanou","year":"2003","journal-title":"Ann. Emerg. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1016\/j.resuscitation.2009.09.003","article-title":"Techniques for artefact filtering from chest compression corrupted ECG signals: Good, but not enough","volume":"80","author":"Li","year":"2009","journal-title":"Resuscitation"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1097\/00003246-199705000-00005","article-title":"Adverse effects of interrupting precordial compression during cardiopulmonary resuscitation","volume":"25","author":"Sato","year":"1997","journal-title":"Crit. Care Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1161\/01.CIR.0000016362.42586.FE","article-title":"Effects of interrupting precordial compressions on the calculated probability of defibrillation success during out-of-hospital cardiac arrest","volume":"105","author":"Sunde","year":"2002","journal-title":"Circulation"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.resuscitation.2006.04.008","article-title":"Effects of compression depth and pre-shock pauses predict defibrillation failure during cardiac arrest","volume":"71","author":"Edelson","year":"2006","journal-title":"Resuscitation"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ruiz de Gauna, S., Irusta, U., Ruiz, J., Ayala, U., Aramendi, E., and Eftest\u00f8l, T. (2014). Rhythm analysis during cardiopulmonary resuscitation: Past, present, and future. BioMed Res. Int., 2014.","DOI":"10.1155\/2014\/386010"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1016\/j.resuscitation.2009.07.020","article-title":"Strong corruption of electrocardiograms caused by cardiopulmonary resuscitation reduces efficiency of two-channel methods for removing motion artefacts in non-shockable rhythms","volume":"80","author":"Werther","year":"2009","journal-title":"Resuscitation"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1016\/j.resuscitation.2009.07.013","article-title":"An algorithm to discriminate supraventricular from ventricular tachycardia in automated external defibrillators valid for adult and paediatric patients","volume":"80","author":"Irusta","year":"2009","journal-title":"Resuscitation"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1016\/j.resuscitation.2014.04.007","article-title":"Automatic detection of chest compressions for the assessment of CPR-quality parameters","volume":"85","author":"Ayala","year":"2014","journal-title":"Resuscitation"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1440","DOI":"10.1109\/10.880095","article-title":"CPR artifact removal from human ECG using optimal multichannel filtering","volume":"47","author":"Aase","year":"2000","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.resuscitation.2003.12.019","article-title":"Feasibility of shock advice analysis during CPR through removal of CPR artefacts from the human ECG","volume":"61","author":"Aase","year":"2004","journal-title":"Resuscitation"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.resuscitation.2007.03.007","article-title":"Rhythm discrimination during uninterrupted CPR using motion artifact reduction system","volume":"75","author":"Berger","year":"2007","journal-title":"Resuscitation"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1109\/TBME.2008.2010329","article-title":"A least mean-square filter for the estimation of the cardiopulmonary resuscitation artifact based on the frequency of the compressions","volume":"56","author":"Irusta","year":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/TBME.2007.902235","article-title":"Removal of CPR artifacts from the ventricular fibrillation ECG by adaptive regression on lagged reference signals","volume":"55","author":"Rheinberger","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1016\/j.resuscitation.2010.02.031","article-title":"Cardiopulmonary resuscitation artefact suppression using a Kalman filter and the frequency of chest compressions as the reference signal","volume":"81","author":"Ruiz","year":"2010","journal-title":"Resuscitation"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"872470","DOI":"10.1155\/2014\/872470","article-title":"A reliable method for rhythm analysis during cardiopulmonary resuscitation","volume":"2014","author":"Ayala","year":"2014","journal-title":"BioMed Res. Int."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Figuera, C., Irusta, U., Morgado, E., Aramendi, E., Ayala, U., Wik, L., Kramer-Johansen, J., Eftest\u00f8l, T., and Alonso-Atienza, F. (2016). Machine learning techniques for the detection of shockable rhythms in automated external defibrillators. PLOS ONE, 11.","DOI":"10.1371\/journal.pone.0159654"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2411","DOI":"10.1109\/TBME.2017.2688380","article-title":"ECG-based classification of resuscitation cardiac rhythms for retrospective data analysis","volume":"64","author":"Rad","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"115147","DOI":"10.1109\/ACCESS.2019.2935096","article-title":"Automatic Cardiac Rhythm Classification With Concurrent Manual Chest Compressions","volume":"7","author":"Isasi","year":"2019","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1752","DOI":"10.1109\/TBME.2018.2878910","article-title":"A machine learning shock decision algorithm for use during piston-driven chest compressions","volume":"66","author":"Isasi","year":"2018","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rim, B., Sung, N.J., Min, S., and Hong, M. (2020). Deep Learning in Physiological Signal Data: A Survey. Sensors, 20.","DOI":"10.3390\/s20040969"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hong, S., Zhou, Y., Shang, J., Xiao, C., and Sun, J. (2019). Opportunities and Challenges in Deep Learning Methods on Electrocardiogram Data: A Systematic Review. arXiv.","DOI":"10.1016\/j.compbiomed.2020.103801"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","article-title":"Real-time patient-specific ECG classification by 1-D convolutional neural networks","volume":"63","author":"Kiranyaz","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.ins.2017.04.012","article-title":"Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network","volume":"405","author":"Acharya","year":"2017","journal-title":"Inf. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1007\/s40846-018-0389-7","article-title":"Convolutional neural networks for electrocardiogram classification","volume":"38","author":"Bazi","year":"2018","journal-title":"J. Med. Biol. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.compbiomed.2017.12.007","article-title":"Detecting atrial fibrillation by deep convolutional neural networks","volume":"93","author":"Xia","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2095","DOI":"10.1109\/TSMC.2017.2705582","article-title":"Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients","volume":"48","author":"Pourbabaee","year":"2018","journal-title":"IEEE Trans. Syst. Man. Cybern. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Andreotti, F., Carr, O., Pimentel, M.A., Mahdi, A., and De Vos, M. (2017, January 24\u201327). Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG. Proceedings of the 2017 Computing in Cardiology (CinC), Rennes, France.","DOI":"10.22489\/CinC.2017.360-239"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Picon, A., Irusta, U., \u00c1lvarez-Gila, A., Aramendi, E., Alonso-Atienza, F., Figuera, C., Ayala, U., Garrote, E., Wik, L., and Kramer-Johansen, J. (2019). Mixed convolutional and long short-term memory network for the detection of lethal ventricular arrhythmia. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0216756"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Elola, A., Aramendi, E., Irusta, U., Pic\u00f3n, A., Alonso, E., Owens, P., and Idris, A. (2019). Deep neural networks for ECG-based pulse detection during out-of-hospital cardiac arrest. Entropy, 21.","DOI":"10.3390\/e21030305"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1001\/jama.293.3.299","article-title":"Quality of cardiopulmonary resuscitation during out-of-hospital cardiac arrest","volume":"293","author":"Wik","year":"2005","journal-title":"JAMA"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/TBME.2018.2827304","article-title":"A multistage algorithm for ECG rhythm analysis during piston-driven mechanical chest compressions","volume":"66","author":"Isasi","year":"2018","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1016\/j.sigpro.2007.03.003","article-title":"Fast RLS Fourier analyzers capable of accommodating frequency mismatch","volume":"87","author":"Xiao","year":"2007","journal-title":"Signal Process."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.resuscitation.2007.06.032","article-title":"Sensitivity and specificity of an automated external defibrillator algorithm designed for pediatric patients","volume":"76","author":"Atkins","year":"2008","journal-title":"Resuscitation"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.resuscitation.2015.02.031","article-title":"Adaptive rhythm sequencing: A method for dynamic rhythm classification during CPR","volume":"91","author":"Kwok","year":"2015","journal-title":"Resuscitation"},{"key":"ref_43","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_44","unstructured":"Sutskever, I., Martens, J., Dahl, G., and Hinton, G. (2013, January 16\u201321). On the importance of initialization and momentum in deep learning. Proceedings of the International conference on machine learning, Atlanta, GA, USA."},{"key":"ref_45","unstructured":"Kuo, S. (1978). Computer detection of ventricular fibrillation. Proc. Comput. Cardiol. IEEE Comupt. Soc., 347\u2013349."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Gonzalez, L., Walker, K., Challa, S., and Bent, B. (2016\u201315, January 15). Monitoring a skipped heartbeat: A real-time premature ventricular contraction (pvc) monitor. Proceedings of the 2016 IEEE Virtual Conference on Applications of Commercial Sensors (VCACS), Raleigh, NC, USA.","DOI":"10.1109\/VCACS.2016.7888785"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/S0300-9572(00)00259-8","article-title":"Reducing CPR artefacts in ventricular fibrillation in vitro","volume":"48","author":"Langhelle","year":"2001","journal-title":"Resuscitation"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"S148","DOI":"10.1097\/00003246-200204001-00006","article-title":"Determination of the noise source in the electrocardiogram during cardiopulmonary resuscitation","volume":"30","author":"Fitzgibbon","year":"2002","journal-title":"Crit. Care Med."},{"key":"ref_49","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","article-title":"DW 1979. A Cluster Separation Measure","volume":"PAMI-1","author":"Davies","year":"1979","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_51","first-page":"57","article-title":"SOM toolbox for Matlab 5","volume":"216","author":"Vesanto","year":"2000","journal-title":"Hels. Univ. Technol."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1016\/j.resuscitation.2017.11.035","article-title":"An automatic system for the comprehensive retrospective analysis of cardiac rhythms in resuscitation episodes","volume":"122","author":"Rad","year":"2018","journal-title":"Resuscitation"},{"key":"ref_53","first-page":"37","article-title":"Diagn\u00f3stico del ritmo card\u00edaco durante la resucitaci\u00f3n cardiopulmonar mediante t\u00e9cnicas de aprendizaje profundo","volume":"37","year":"2019","journal-title":"Actas del XXXVII Congreso Anual de la Sociedad Espa\u00f1ola de Ingenier\u00eda Biom\u00e9dica"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/6\/595\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:33:10Z","timestamp":1760175190000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/22\/6\/595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,27]]},"references-count":53,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["e22060595"],"URL":"https:\/\/doi.org\/10.3390\/e22060595","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,27]]}}}