Automatic atrial fibrillation detection based on heart rate variability and spectral features

Zhenning Mei, Xiao Gu, Hongyu Chen, Wei Chen

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

Atrial fibrillation (AF) is one of the most common sustained arrhythmias, affecting about 1% of the population around the world. Rapid popularization of portable and wearable devices in recent years makes widespread personalized and mobile healthcare get closer to reality than ever before. This paper presents a method aiming for automatic detection of AF from short single lead electrocardiogram (ECG) recordings. Since AF is a kind of arrhythmia being likely to alter the dynamics of heart rhythms and/or the morphological characteristics in ECG tracings, heart rate variability (HRV)-based metrics and frequency analysis are adopted as feature extractors. We validate our method on a public available data set comprised of short ECG recordings of normal rhythm (N), AF (A), and other arrhythmias (O) by support vector machine and bagging trees. For two-class classification problems (N versus A), accuracy varies from 92.0% to 96.6% under different additional noise levels. For three-class classification problem (N versus A versus O), accuracy as high as 82.0% is obtained. Experimental results suggest than even for a relatively short ECG recording, nonlinear descriptors of HRV are still efficient and robust for AF detection.

LanguageEnglish
Article number8468160
Pages53566-53575
Number of pages10
JournalIEEE Access
Volume6
DOIs
StatePublished - 1 Jan 2018

Fingerprint

Electrocardiography
Support vector machines
Lead

Keywords

  • Atrial fibrillation
  • biomedical signal processing
  • ECG
  • heart rate variability
  • machine learning

Cite this

@article{5b024479377741cebbf33687f81155c5,
title = "Automatic atrial fibrillation detection based on heart rate variability and spectral features",
abstract = "Atrial fibrillation (AF) is one of the most common sustained arrhythmias, affecting about 1{\%} of the population around the world. Rapid popularization of portable and wearable devices in recent years makes widespread personalized and mobile healthcare get closer to reality than ever before. This paper presents a method aiming for automatic detection of AF from short single lead electrocardiogram (ECG) recordings. Since AF is a kind of arrhythmia being likely to alter the dynamics of heart rhythms and/or the morphological characteristics in ECG tracings, heart rate variability (HRV)-based metrics and frequency analysis are adopted as feature extractors. We validate our method on a public available data set comprised of short ECG recordings of normal rhythm (N), AF (A), and other arrhythmias (O) by support vector machine and bagging trees. For two-class classification problems (N versus A), accuracy varies from 92.0{\%} to 96.6{\%} under different additional noise levels. For three-class classification problem (N versus A versus O), accuracy as high as 82.0{\%} is obtained. Experimental results suggest than even for a relatively short ECG recording, nonlinear descriptors of HRV are still efficient and robust for AF detection.",
keywords = "Atrial fibrillation, biomedical signal processing, ECG, heart rate variability, machine learning",
author = "Zhenning Mei and Xiao Gu and Hongyu Chen and Wei Chen",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2871220",
language = "English",
volume = "6",
pages = "53566--53575",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers",

}

Automatic atrial fibrillation detection based on heart rate variability and spectral features. / Mei, Zhenning; Gu, Xiao; Chen, Hongyu; Chen, Wei.

In: IEEE Access, Vol. 6, 8468160, 01.01.2018, p. 53566-53575.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automatic atrial fibrillation detection based on heart rate variability and spectral features

AU - Mei,Zhenning

AU - Gu,Xiao

AU - Chen,Hongyu

AU - Chen,Wei

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Atrial fibrillation (AF) is one of the most common sustained arrhythmias, affecting about 1% of the population around the world. Rapid popularization of portable and wearable devices in recent years makes widespread personalized and mobile healthcare get closer to reality than ever before. This paper presents a method aiming for automatic detection of AF from short single lead electrocardiogram (ECG) recordings. Since AF is a kind of arrhythmia being likely to alter the dynamics of heart rhythms and/or the morphological characteristics in ECG tracings, heart rate variability (HRV)-based metrics and frequency analysis are adopted as feature extractors. We validate our method on a public available data set comprised of short ECG recordings of normal rhythm (N), AF (A), and other arrhythmias (O) by support vector machine and bagging trees. For two-class classification problems (N versus A), accuracy varies from 92.0% to 96.6% under different additional noise levels. For three-class classification problem (N versus A versus O), accuracy as high as 82.0% is obtained. Experimental results suggest than even for a relatively short ECG recording, nonlinear descriptors of HRV are still efficient and robust for AF detection.

AB - Atrial fibrillation (AF) is one of the most common sustained arrhythmias, affecting about 1% of the population around the world. Rapid popularization of portable and wearable devices in recent years makes widespread personalized and mobile healthcare get closer to reality than ever before. This paper presents a method aiming for automatic detection of AF from short single lead electrocardiogram (ECG) recordings. Since AF is a kind of arrhythmia being likely to alter the dynamics of heart rhythms and/or the morphological characteristics in ECG tracings, heart rate variability (HRV)-based metrics and frequency analysis are adopted as feature extractors. We validate our method on a public available data set comprised of short ECG recordings of normal rhythm (N), AF (A), and other arrhythmias (O) by support vector machine and bagging trees. For two-class classification problems (N versus A), accuracy varies from 92.0% to 96.6% under different additional noise levels. For three-class classification problem (N versus A versus O), accuracy as high as 82.0% is obtained. Experimental results suggest than even for a relatively short ECG recording, nonlinear descriptors of HRV are still efficient and robust for AF detection.

KW - Atrial fibrillation

KW - biomedical signal processing

KW - ECG

KW - heart rate variability

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85053598494&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2871220

DO - 10.1109/ACCESS.2018.2871220

M3 - Article

VL - 6

SP - 53566

EP - 53575

JO - IEEE Access

T2 - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8468160

ER -