Cargando…

Abnormal ECG detection based on an adversarial autoencoder

Automatic detection and alarm of abnormal electrocardiogram (ECG) events play an important role in an ECG monitor system; however, popular classification models based on supervised learning fail to detect abnormal ECG effectively. Thus, we propose an ECG anomaly detection framework (ECG-AAE) based o...

Descripción completa

Detalles Bibliográficos
Autores principales: Shan, Lianfeng, Li, Yu, Jiang, Hua, Zhou, Peng, Niu, Jing, Liu, Ran, Wei, Yuanyuan, Peng, Jiao, Yu, Huizhen, Sha, Xianzheng, Chang, Shijie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9481281/
https://www.ncbi.nlm.nih.gov/pubmed/36117713
http://dx.doi.org/10.3389/fphys.2022.961724
_version_ 1784791228862169088
author Shan, Lianfeng
Li, Yu
Jiang, Hua
Zhou, Peng
Niu, Jing
Liu, Ran
Wei, Yuanyuan
Peng, Jiao
Yu, Huizhen
Sha, Xianzheng
Chang, Shijie
author_facet Shan, Lianfeng
Li, Yu
Jiang, Hua
Zhou, Peng
Niu, Jing
Liu, Ran
Wei, Yuanyuan
Peng, Jiao
Yu, Huizhen
Sha, Xianzheng
Chang, Shijie
author_sort Shan, Lianfeng
collection PubMed
description Automatic detection and alarm of abnormal electrocardiogram (ECG) events play an important role in an ECG monitor system; however, popular classification models based on supervised learning fail to detect abnormal ECG effectively. Thus, we propose an ECG anomaly detection framework (ECG-AAE) based on an adversarial autoencoder and temporal convolutional network (TCN) which consists of three modules (autoencoder, discriminator, and outlier detector). The ECG-AAE framework is trained only with normal ECG data. Normal ECG signals could be mapped into latent feature space and then reconstructed as the original ECG signal back in our model, while abnormal ECG signals could not. Here, the TCN is employed to extract features of normal ECG data. Then, our model is evaluated on an MIT-BIH arrhythmia dataset and CMUH dataset, with an accuracy, precision, recall, F1-score, and AUC of 0.9673, 0.9854, 0.9486, 0.9666, and 0.9672 and of 0.9358, 0.9816, 0.8882, 0.9325, and 0.9358, respectively. The result indicates that the ECG-AAE can detect abnormal ECG efficiently, with its performance better than other popular outlier detection methods.
format Online
Article
Text
id pubmed-9481281
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-94812812022-09-17 Abnormal ECG detection based on an adversarial autoencoder Shan, Lianfeng Li, Yu Jiang, Hua Zhou, Peng Niu, Jing Liu, Ran Wei, Yuanyuan Peng, Jiao Yu, Huizhen Sha, Xianzheng Chang, Shijie Front Physiol Physiology Automatic detection and alarm of abnormal electrocardiogram (ECG) events play an important role in an ECG monitor system; however, popular classification models based on supervised learning fail to detect abnormal ECG effectively. Thus, we propose an ECG anomaly detection framework (ECG-AAE) based on an adversarial autoencoder and temporal convolutional network (TCN) which consists of three modules (autoencoder, discriminator, and outlier detector). The ECG-AAE framework is trained only with normal ECG data. Normal ECG signals could be mapped into latent feature space and then reconstructed as the original ECG signal back in our model, while abnormal ECG signals could not. Here, the TCN is employed to extract features of normal ECG data. Then, our model is evaluated on an MIT-BIH arrhythmia dataset and CMUH dataset, with an accuracy, precision, recall, F1-score, and AUC of 0.9673, 0.9854, 0.9486, 0.9666, and 0.9672 and of 0.9358, 0.9816, 0.8882, 0.9325, and 0.9358, respectively. The result indicates that the ECG-AAE can detect abnormal ECG efficiently, with its performance better than other popular outlier detection methods. Frontiers Media S.A. 2022-09-02 /pmc/articles/PMC9481281/ /pubmed/36117713 http://dx.doi.org/10.3389/fphys.2022.961724 Text en Copyright © 2022 Shan, Li, Jiang, Zhou, Niu, Liu, Wei, Peng, Yu, Sha and Chang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Physiology
Shan, Lianfeng
Li, Yu
Jiang, Hua
Zhou, Peng
Niu, Jing
Liu, Ran
Wei, Yuanyuan
Peng, Jiao
Yu, Huizhen
Sha, Xianzheng
Chang, Shijie
Abnormal ECG detection based on an adversarial autoencoder
title Abnormal ECG detection based on an adversarial autoencoder
title_full Abnormal ECG detection based on an adversarial autoencoder
title_fullStr Abnormal ECG detection based on an adversarial autoencoder
title_full_unstemmed Abnormal ECG detection based on an adversarial autoencoder
title_short Abnormal ECG detection based on an adversarial autoencoder
title_sort abnormal ecg detection based on an adversarial autoencoder
topic Physiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9481281/
https://www.ncbi.nlm.nih.gov/pubmed/36117713
http://dx.doi.org/10.3389/fphys.2022.961724
work_keys_str_mv AT shanlianfeng abnormalecgdetectionbasedonanadversarialautoencoder
AT liyu abnormalecgdetectionbasedonanadversarialautoencoder
AT jianghua abnormalecgdetectionbasedonanadversarialautoencoder
AT zhoupeng abnormalecgdetectionbasedonanadversarialautoencoder
AT niujing abnormalecgdetectionbasedonanadversarialautoencoder
AT liuran abnormalecgdetectionbasedonanadversarialautoencoder
AT weiyuanyuan abnormalecgdetectionbasedonanadversarialautoencoder
AT pengjiao abnormalecgdetectionbasedonanadversarialautoencoder
AT yuhuizhen abnormalecgdetectionbasedonanadversarialautoencoder
AT shaxianzheng abnormalecgdetectionbasedonanadversarialautoencoder
AT changshijie abnormalecgdetectionbasedonanadversarialautoencoder