{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T14:37:11Z","timestamp":1784385431238,"version":"3.55.0"},"reference-count":54,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:00:00Z","timestamp":1649635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004587","name":"Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["PI18\/01895"],"award-info":[{"award-number":["PI18\/01895"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004587","name":"Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["DTS21\/00064"],"award-info":[{"award-number":["DTS21\/00064"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004587","name":"Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["RD16\/0011\/0029"],"award-info":[{"award-number":["RD16\/0011\/0029"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Red de Investigaci\u00f3n Cooperativa Orientada a Resultados en Salud \u2013 RICORS TERAV","award":["RD21\/0017\/0002"],"award-info":[{"award-number":["RD21\/0017\/0002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>The maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity drivers in endocardial electrograms (EGMs) with convolutional recurrent neural networks (CRNNs). The CRNN model was compared with two other state-of-the-art methods (SimpleCNN and attention-based time-incremental convolutional neural network (ATI-CNN)) for different input signals (unipolar EGMs, bipolar EGMs, and unipolar local activation times), sampling frequencies, and signal lengths. The proposed CRNN obtained a detection score based on the Matthews correlation coefficient of 0.680, an ATI-CNN score of 0.401, and a SimpleCNN score of 0.118, with bipolar EGMs as input signals exhibiting better overall performance. In terms of signal length and sampling frequency, no significant differences were found. The proposed architecture opens the way for new ablation strategies and driver detection methods to better understand the AF problem and its treatment.<\/jats:p>","DOI":"10.3390\/ijms23084216","type":"journal-article","created":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T00:23:11Z","timestamp":1649722991000},"page":"4216","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2446-3045","authenticated-orcid":false,"given":"Gonzalo Ricardo","family":"R\u00edos-Mu\u00f1oz","sequence":"first","affiliation":[{"name":"Department of Cardiology, Instituto de Investigaci\u00f3n Sanitaria Gregorio Mara\u00f1\u00f3n (IiSGM), Hospital General Universitario Gregorio Mara\u00f1\u00f3n, 28007 Madrid, Spain"},{"name":"Center for Biomedical Research in Cardiovascular Disease Network (CIBERCV), 28029 Madrid, Spain"},{"name":"Departamento de Bioingenier\u00eda e Ingenier\u00eda Aeroespacial, Universidad Carlos III de Madrid, 28911 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco","family":"Fern\u00e1ndez-Avil\u00e9s","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Instituto de Investigaci\u00f3n Sanitaria Gregorio Mara\u00f1\u00f3n (IiSGM), Hospital General Universitario Gregorio Mara\u00f1\u00f3n, 28007 Madrid, Spain"},{"name":"Center for Biomedical Research in Cardiovascular Disease Network (CIBERCV), 28029 Madrid, Spain"},{"name":"Facultad de Medicina, Universidad Complutense de Madrid, 28040 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1ngel","family":"Arenal","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Instituto de Investigaci\u00f3n Sanitaria Gregorio Mara\u00f1\u00f3n (IiSGM), Hospital General Universitario Gregorio Mara\u00f1\u00f3n, 28007 Madrid, Spain"},{"name":"Center for Biomedical Research in Cardiovascular Disease Network (CIBERCV), 28029 Madrid, Spain"},{"name":"Facultad de Medicina, Universidad Complutense de Madrid, 28040 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: A comprehensive review","volume":"29","author":"Rawat","year":"2017","journal-title":"Neural Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10462-018-9654-y","article-title":"A review on deep learning for recommender systems: Challenges and remedies","volume":"52","author":"Batmaz","year":"2019","journal-title":"Artif. Intell. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"713","DOI":"10.21037\/atm.2020.02.44","article-title":"A review of the application of deep learning in medical image classification and segmentation","volume":"8","author":"Cai","year":"2020","journal-title":"Ann. Transl. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2189","DOI":"10.1109\/TCBB.2019.2932416","article-title":"Prediction of FMN Binding Sites in Electron Transport Chains Based on 2-D CNN and PSSM Profiles","volume":"18","author":"Le","year":"2021","journal-title":"IEEE ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Le, N.Q.K., and Ho, Q.T. (2021). Deep transformers and convolutional neural network in identifying DNA N6-methyladenine sites in cross-species genomes. Methods.","DOI":"10.1016\/j.ymeth.2021.12.004"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.inffus.2019.06.024","article-title":"Multi-class Arrhythmia detection from 12-lead varied-length ECG using Attention-based Time-Incremental Convolutional Neural Network","volume":"53","author":"Yao","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106","DOI":"10.3389\/fncom.2020.564015","article-title":"A Study on Arrhythmia via ECG Signal Classification Using the Convolutional Neural Network","volume":"14","author":"Wu","year":"2021","journal-title":"Front. Comput. Neurosci."},{"key":"ref_8","first-page":"1333","article-title":"Detection of Brief Episodes of Atrial Fibrillation Based on Electrocardiomatrix and Convolutional Neural Network","volume":"12","author":"Marzocchi","year":"2021","journal-title":"Front. Physiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102194","DOI":"10.1016\/j.bspc.2020.102194","article-title":"Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets","volume":"63","author":"Petmezas","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"13","DOI":"10.3389\/fdgth.2021.639444","article-title":"Trends in Heart-Rate Variability Signal Analysis","volume":"3","author":"Ishaque","year":"2021","journal-title":"Front. Digit. Health"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"86","DOI":"10.3389\/fcvm.2020.00086","article-title":"Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs","volume":"7","author":"Jamart","year":"2020","journal-title":"Front. Cardiovasc. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1016\/j.hrthm.2020.02.023","article-title":"Wearables in cardiology: Here to stay","volume":"17","author":"Dagher","year":"2020","journal-title":"Hear. Rhythm"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.3389\/fphys.2021.704122","article-title":"Deep Learning Classification of Unipolar Electrograms in Human Atrial Fibrillation: Application in Focal Source Mapping","volume":"12","author":"Liao","year":"2021","journal-title":"Front. Physiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1161\/CIRCEP.119.008249","article-title":"Optical mapping-validated machine learning improves atrial fibrillation driver detection by multi-electrode mapping","volume":"13","author":"Zolotarev","year":"2020","journal-title":"Circ. Arrhythmia Electrophysiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3904","DOI":"10.1093\/eurheartj\/ehab544","article-title":"Artificial intelligence in the diagnosis and management of arrhythmias","volume":"42","author":"Nagarajan","year":"2021","journal-title":"Eur. Heart J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e56","DOI":"10.1161\/CIR.0000000000000659","article-title":"Heart Disease and Stroke Statistics\u20142019 Update: A Report From the American Heart Association","volume":"139","author":"Benjamin","year":"2019","journal-title":"Circulation"},{"key":"ref_17","first-page":"183","article-title":"On the Multiple Wavelet Hypothesis of Atrial Fibrillation","volume":"140","author":"Moe","year":"1962","journal-title":"Arch. Int. Phamacodyn. Ther."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1056\/NEJM199809033391003","article-title":"Spontaneous Initiation of Atrial Fibrillation by Ectopic Beats Originating in the Pulmonary Veins","volume":"339","author":"Shah","year":"1998","journal-title":"N. Engl. J. Med."},{"key":"ref_19","first-page":"S2","article-title":"Mechanisms of atrial fibrillation: Mother rotors or multiple daughter wavelets, or both?","volume":"9","author":"Jalife","year":"1998","journal-title":"J. Cardiovasc. Electrophysiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1161\/CIRCULATIONAHA.117.028981","article-title":"Sex Differences and Similarities in Atrial Fibrillation Epidemiology, Risk Factors, and Mortality in Community Cohorts","volume":"136","author":"Magnussen","year":"2017","journal-title":"Circulation"},{"key":"ref_21","first-page":"310","article-title":"Identification of Rotors during Human Atrial Fibrillation Using Contact Mapping and Phase Singularity Detection: Technical Considerations","volume":"64","author":"Kuklik","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.jacep.2016.08.001","article-title":"Identification of Repetitive Activation Patterns Using Novel Computational Analysis of Multielectrode Recordings During Atrial Fibrillation and Flutter in Humans","volume":"3","author":"Daoud","year":"2017","journal-title":"JACC Clin. Electrophysiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"208","DOI":"10.3389\/fphys.2018.00208","article-title":"Real-Time Rotational Activity Detection in Atrial Fibrillation","volume":"9","author":"Arenal","year":"2018","journal-title":"Front. Physiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/JBHI.2018.2805773","article-title":"Hierarchical Algorithms for Causality Retrieval in Atrial Fibrillation Intracavitary Electrograms","volume":"23","author":"Luengo","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.3389\/fphys.2019.01138","article-title":"Directed Networks as a Novel Way to Describe and Analyze Cardiac Excitation: Directed Graph Mapping","volume":"10","author":"Vandersickel","year":"2019","journal-title":"Front. Physiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2455","DOI":"10.1016\/j.jacc.2014.09.053","article-title":"Comparison of Radiofrequency Catheter Ablation of Drivers and Circumferential Pulmonary Vein Isolation in Atrial Fibrillation: A Noninferiority Randomized Multicenter RADAR-AF Trial","volume":"64","author":"Atienza","year":"2014","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.repc.2017.02.012","article-title":"Relationship between rotors and complex fractionated electrograms in atrial fibrillation using a novel computational analysis","volume":"36","author":"Carmo","year":"2017","journal-title":"Rev. Port. Cardiol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1053\/j.gastro.2020.04.062","article-title":"Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial","volume":"159","author":"Repici","year":"2020","journal-title":"Gastroenterology"},{"key":"ref_29","unstructured":"Lu, X.H. (2015). Application of Machine Learning and Grocery Transaction Data."},{"key":"ref_30","unstructured":"Wallach, H., Larochelle, H., Beygelzimer, A., de Alch\u00e9-Buc, F., Fox, E., and Garnett, R. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32, Curran Associates Inc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"768468","DOI":"10.3389\/fphys.2021.768468","article-title":"Artificial Intelligence-Driven Algorithm for Drug Effect Prediction on Atrial Fibrillation: An in silico Population of Models Approach","volume":"12","author":"Arenal","year":"2021","journal-title":"Front. Physiol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"869","DOI":"10.3389\/fphys.2020.00869","article-title":"Standardizing Single-Frame Phase Singularity Identification Algorithms and Parameters in Phase Mapping During Human Atrial Fibrillation","volume":"11","author":"Li","year":"2020","journal-title":"Front. Physiol."},{"key":"ref_33","first-page":"1249","article-title":"Non-invasive identification of stable rotors and focal sources for human atrial fibrillation: Mechanistic classification of atrial fibrillation from the electrocardiogram","volume":"15","author":"Jones","year":"2013","journal-title":"EP Eur."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Narayan, S.M., Krummen, D.E., Enyeart, M.W., and Rappel, W.J. (2012). Computational Mapping Identifies Localized Mechanisms for Ablation of Atrial Fibrillation. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0046034"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e21","DOI":"10.15420\/ecr.2020.39","article-title":"Mapping Technologies for Catheter Ablation of Atrial Fibrillation Beyond Pulmonary Vein Isolation","volume":"16","author":"Rosa","year":"2021","journal-title":"Eur. Cardiol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1161\/CIRCRESAHA.119.314930","article-title":"Instantaneous Amplitude and Frequency Modulations Detect the Footprint of Rotational Activity and Reveal Stable Driver Regions as Targets for Persistent Atrial Fibrillation Ablation","volume":"125","author":"Quintanilla","year":"2019","journal-title":"Circ. Res."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1161\/CIRCRESAHA.111.247494","article-title":"Optical imaging of voltage and calcium in cardiac cells & tissues","volume":"110","author":"Herron","year":"2012","journal-title":"Circ. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1093\/europace\/euaa041","article-title":"Predicting recurrent atrial fibrillation after catheter ablation: A systematic review of prognostic models","volume":"22","author":"Dretzke","year":"2020","journal-title":"Europace"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"235","DOI":"10.2459\/JCM.0b013e328358554b","article-title":"Risk factors for atrial fibrillation recurrence: A literature review","volume":"15","author":"Vizzardi","year":"2014","journal-title":"J. Cardiovasc. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1111\/j.1540-8167.2012.02332.x","article-title":"Clinical Mapping Approach to Diagnose Electrical Rotors and Focal Impulse Sources for Human Atrial Fibrillation","volume":"23","author":"Narayan","year":"2012","journal-title":"J. Cardiovasc. Electrophysiol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1016\/j.jacc.2016.11.079","article-title":"Clinical Benefit of Ablating Localized Sources for Human Atrial Fibrillation: The Indiana University FIRM Registry","volume":"69","author":"Miller","year":"2017","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1302","DOI":"10.1093\/europace\/euw168","article-title":"Multicentre evaluation of non-invasive biatrial mapping for persistent atrial fibrillation ablation: The AFACART study","volume":"19","author":"Knecht","year":"2017","journal-title":"Europace"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e005740","DOI":"10.1161\/CIRCEP.117.005740","article-title":"Ablation of Rotor Domains Effectively Modulates Dynamics of Human: Long-Standing Persistent Atrial Fibrillation","volume":"10","author":"Calvo","year":"2017","journal-title":"Circ. Arrhythm. Electrophysiol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1296","DOI":"10.1016\/j.hrthm.2018.04.020","article-title":"Characterization of drivers maintaining atrial fibrillation: Correlation with markers of rapidity and organization on spectral analysis","volume":"15","author":"Honarbakhsh","year":"2018","journal-title":"Hear. Rhythm"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"e007233","DOI":"10.1161\/CIRCEP.119.007233","article-title":"Targeting Nonpulmonary Vein Sources in Persistent Atrial Fibrillation Identified by Noncontact Charge Density Mapping: UNCOVER AF Trial","volume":"12","author":"Willems","year":"2019","journal-title":"Circ. Arrhythm. Electrophysiol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e007825","DOI":"10.1161\/CIRCEP.119.007825","article-title":"RADAR: A Multicenter Food and Drug Administration Investigational Device Exemption Clinical Trial of Persistent Atrial Fibrillation","volume":"13","author":"Choudry","year":"2020","journal-title":"Circ. Arrhythm. Electrophysiol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1093\/eurheartj\/eht267","article-title":"Epicardial Wave Mapping in Human Long-Lasting Persistent Atrial Fibrillation: Transient Rotational Circuits, Complex Wavefronts, and Disorganized Activity","volume":"35","author":"Lee","year":"2014","journal-title":"Eur. Heart J."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1093\/eurheartj\/ehaa612","article-title":"2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association of Cardio-Thoracic Surgery (EACTS)","volume":"42","author":"Hindricks","year":"2021","journal-title":"Eur. Heart J."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"819429","DOI":"10.3389\/fcvm.2022.819429","article-title":"Structural Remodeling and Rotational Activity in Persistent\/Long-Lasting Atrial Fibrillation: Gender-Effect Differences and Impact on Post-Ablation Outcome","volume":"9","author":"Soto","year":"2022","journal-title":"Front. Cardiovasc. Med."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"157892","DOI":"10.1109\/ACCESS.2020.3020099","article-title":"A CRNN system for sound event detection based on gastrointestinal sound dataset collected by wearable auscultation devices","volume":"8","author":"Zheng","year":"2020","journal-title":"IEEE Access"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/j.eswa.2018.08.011","article-title":"A deep learning approach for real-time detection of atrial fibrillation","volume":"115","author":"Andersen","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_53","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference Learning Representations ICLR 2015, San Diego, CA, USA."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Chicco, D., and Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom., 21.","DOI":"10.1186\/s12864-019-6413-7"}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/23\/8\/4216\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:52:00Z","timestamp":1760136720000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/23\/8\/4216"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,11]]},"references-count":54,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["ijms23084216"],"URL":"https:\/\/doi.org\/10.3390\/ijms23084216","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,11]]}}}