Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

ECG Modeling for Simulation of Arrhythmias in Time-Varying Conditions

Bachi, Lorenzo ; Halvaei, Hesam LU ; Perez, Cristina ; Martin-Yebra, Alba ; Petrenas, Andrius ; Solosenko, Andrius ; Johnson, Linda LU ; Marozas, Vaidotas ; Martinez, Juan Pablo and Pueyo, Esther , et al. (2023) In IEEE Transactions on Biomedical Engineering 70(12). p.3449-3460
Abstract

The 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... (More)

The 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.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Arrhythmia, arrhythmias, Biological system modeling, Databases, ECG signals, Electrocardiography, Morphology, noise, respiration, Rhythm, simulation models, Training
in
IEEE Transactions on Biomedical Engineering
volume
70
issue
12
pages
12 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • pmid:37347631
  • scopus:85163503682
ISSN
0018-9294
DOI
10.1109/TBME.2023.3288701
language
English
LU publication?
yes
id
b673b11b-201d-45c0-980f-1e94a8bf03a5
date added to LUP
2023-10-13 09:49:50
date last changed
2025-01-12 05:15:46
@article{b673b11b-201d-45c0-980f-1e94a8bf03a5,
  abstract     = {{<p>The 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.</p>}},
  author       = {{Bachi, Lorenzo and Halvaei, Hesam and Perez, Cristina and Martin-Yebra, Alba and Petrenas, Andrius and Solosenko, Andrius and Johnson, Linda and Marozas, Vaidotas and Martinez, Juan Pablo and Pueyo, Esther and Stridh, Martin and Laguna, Pablo and Sornmo, Leif}},
  issn         = {{0018-9294}},
  keywords     = {{Arrhythmia; arrhythmias; Biological system modeling; Databases; ECG signals; Electrocardiography; Morphology; noise; respiration; Rhythm; simulation models; Training}},
  language     = {{eng}},
  number       = {{12}},
  pages        = {{3449--3460}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Biomedical Engineering}},
  title        = {{ECG Modeling for Simulation of Arrhythmias in Time-Varying Conditions}},
  url          = {{http://dx.doi.org/10.1109/TBME.2023.3288701}},
  doi          = {{10.1109/TBME.2023.3288701}},
  volume       = {{70}},
  year         = {{2023}},
}