Advanced

Classification of paroxysmal and persistent atrial fibrillation in ambulatory ECG recordings

Alcaraz Martinez, Raul; Sandberg, Frida LU ; Sörnmo, Leif LU and Rieta, José Joaquín (2011) In IEEE Transactions on Biomedical Engineering 58. p.1441-1449
Abstract
The problem of classifying short atrial fibrillatory segments in ambulatory ECG recordings as being either paroxysmal or persistent is addressed by investigating a robust approach to signal characterization. The method comprises preprocessing, estimation of the dominant atrial frequency for the purpose of controlling the subbands of a filter bank, and computation of the relative subband (harmonics) energy and the subband sample entropy. Using minimum-error-rate classification of different feature vectors, a dataset consisting of 24-h ambulatory recordings from 50 subjects with either paroxysmal (26) or persistent (24) atrial fibrillation (AF) was analyzed on a 10-s segment basis; a total of 212196 segments were classified. The best... (More)
The problem of classifying short atrial fibrillatory segments in ambulatory ECG recordings as being either paroxysmal or persistent is addressed by investigating a robust approach to signal characterization. The method comprises preprocessing, estimation of the dominant atrial frequency for the purpose of controlling the subbands of a filter bank, and computation of the relative subband (harmonics) energy and the subband sample entropy. Using minimum-error-rate classification of different feature vectors, a dataset consisting of 24-h ambulatory recordings from 50 subjects with either paroxysmal (26) or persistent (24) atrial fibrillation (AF) was analyzed on a 10-s segment basis; a total of 212196 segments were classified. The best performance in terms of area under the receiver operating characteristic curve was obtained for a feature vector defined by the subband sample entropy of the dominant atrial frequency and the relative harmonics energy, resulting in a value of 0.923, whereas that of the dominant atrial frequency was equal to 0.826. It is concluded that paroxysmal and persistent AF can be discriminated from short segments with good accuracy at any time of an ambulatory recording. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Atrial fibrillation, atrial organization, dominant atrial frequency, electrocardiogram, filter bank, hidden Markov model, sample entropy
in
IEEE Transactions on Biomedical Engineering
volume
58
pages
1441 - 1449
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • wos:000289807300035
  • scopus:79955538914
ISSN
0018-9294
DOI
10.1109/TBME.2011.2112658
language
English
LU publication?
yes
id
59f606f5-7640-46a0-b5d9-81d4d78ed477 (old id 1790306)
date added to LUP
2011-03-01 14:18:43
date last changed
2017-07-23 04:59:24
@article{59f606f5-7640-46a0-b5d9-81d4d78ed477,
  abstract     = {The problem of classifying short atrial fibrillatory segments in ambulatory ECG recordings as being either paroxysmal or persistent is addressed by investigating a robust approach to signal characterization. The method comprises preprocessing, estimation of the dominant atrial frequency for the purpose of controlling the subbands of a filter bank, and computation of the relative subband (harmonics) energy and the subband sample entropy. Using minimum-error-rate classification of different feature vectors, a dataset consisting of 24-h ambulatory recordings from 50 subjects with either paroxysmal (26) or persistent (24) atrial fibrillation (AF) was analyzed on a 10-s segment basis; a total of 212196 segments were classified. The best performance in terms of area under the receiver operating characteristic curve was obtained for a feature vector defined by the subband sample entropy of the dominant atrial frequency and the relative harmonics energy, resulting in a value of 0.923, whereas that of the dominant atrial frequency was equal to 0.826. It is concluded that paroxysmal and persistent AF can be discriminated from short segments with good accuracy at any time of an ambulatory recording.},
  author       = {Alcaraz Martinez, Raul and Sandberg, Frida and Sörnmo, Leif and Rieta, José Joaquín},
  issn         = {0018-9294},
  keyword      = {Atrial fibrillation,atrial organization,dominant atrial frequency,electrocardiogram,filter bank,hidden Markov model,sample entropy},
  language     = {eng},
  pages        = {1441--1449},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  series       = {IEEE Transactions on Biomedical Engineering},
  title        = {Classification of paroxysmal and persistent atrial fibrillation in ambulatory ECG recordings},
  url          = {http://dx.doi.org/10.1109/TBME.2011.2112658},
  volume       = {58},
  year         = {2011},
}