000128125 001__ 128125 000128125 005__ 20241125101132.0 000128125 0247_ $$2doi$$a10.1109/TBME.2023.3288701 000128125 0248_ $$2sideral$$a134844 000128125 037__ $$aART-2023-134844 000128125 041__ $$aeng 000128125 100__ $$aBachi, Lorenzo 000128125 245__ $$aECG modeling for simulation of arrhythmias in time-varying conditions 000128125 260__ $$c2023 000128125 5060_ $$aAccess copy available to the general public$$fUnrestricted 000128125 5203_ $$aThe present paper proposes an ECG simulator that advances modeling of arrhythmias and noise by introducing time-varying signal characteristics. The simulator is built around a discrete-time Markov chain model for simulating atrial and ventricular arrhythmias of particular relevance when analyzing atrial fibrillation (AF). Each state is associated with statistical information on episode duration and heartbeat characteristics. Statistical, time-varying modeling of muscle noise, motion artifacts, and the influence of respiration is introduced to increase the complexity of simulated ECGs, making the simulator well suited for data augmentation in machine learning. Modeling of how the PQ and QT intervals depend on heart rate is also introduced. The realism of simulated ECGs is assessed by three experienced doctors, showing that simulated ECGs are difficult to distinguish from real ECGs. Simulator usefulness is illustrated in terms of AF detection performance when either simulated or real ECGs are used to train a neural network for signal quality control. The results show that both types of training lead to similar performance. 000128125 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FEDER/T39-17R-BSICoS$$9info:eu-repo/grantAgreement/ES/MICINN/PID2019-104881RB-I00$$9info:eu-repo/grantAgreement/ES/MICINN/PID2019-105674RB-I00 000128125 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000128125 590__ $$a4.4$$b2023 000128125 592__ $$a1.239$$b2023 000128125 591__ $$aENGINEERING, BIOMEDICAL$$b36 / 123 = 0.293$$c2023$$dQ2$$eT1 000128125 593__ $$aBiomedical Engineering$$c2023$$dQ1 000128125 594__ $$a9.4$$b2023 000128125 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000128125 700__ $$aHalvaei, Hesam 000128125 700__ $$0(orcid)0000-0002-8334-4786$$aPérez, Cristina$$uUniversidad de Zaragoza 000128125 700__ $$0(orcid)0000-0003-0226-4950$$aMartín-Yebra, Alba$$uUniversidad de Zaragoza 000128125 700__ $$aPetrenas, Andrius 000128125 700__ $$aSološenko, Andrius 000128125 700__ $$aJohnson, Linda 000128125 700__ $$aMarozas, Vaidotas 000128125 700__ $$0(orcid)0000-0002-7503-3339$$aMartínez, Juan Pablo$$uUniversidad de Zaragoza 000128125 700__ $$0(orcid)0000-0002-1960-407X$$aPueyo, Esther$$uUniversidad de Zaragoza 000128125 700__ $$aStridh, Martin 000128125 700__ $$0(orcid)0000-0003-3434-9254$$aLaguna, Pablo$$uUniversidad de Zaragoza 000128125 700__ $$aSörnmo, Leif 000128125 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac. 000128125 773__ $$g70, 12 (2023), 3449 - 3460$$pIEEE trans. biomed. eng.$$tIEEE Transactions on Biomedical Engineering$$x0018-9294 000128125 8564_ $$s4682662$$uhttps://zaguan.unizar.es/record/128125/files/texto_completo.pdf$$yPostprint 000128125 8564_ $$s3489955$$uhttps://zaguan.unizar.es/record/128125/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000128125 909CO $$ooai:zaguan.unizar.es:128125$$particulos$$pdriver 000128125 951__ $$a2024-11-22-11:59:25 000128125 980__ $$aARTICLE