Advanced

Detection of body position changes from the ECG using a Laplacian noise model

Minchole, Ana; Sörnmo, Leif LU and Laguna, Pablo (2014) In Biomedical Signal Processing and Control 14. p.189-196
Abstract
Body position changes (BPCs) are manifested as shifts in the electrical axis of the heart, which may lead to ST changes in the ECG, misclassified as ischemic events. This paper presents a novel BPC detector based on a Laplacian noise model. It is assumed that a BPC can be modelled as a step-like change in the two coefficient series that result from the Karhunen-Loeve transform of the QRS complex and the ST-T segment. The generalized likelihood ratio test is explored for detection, where the statistical parameters of the Laplacian model are subject to estimation. Two databases are studied: one for assessing detection performance in healthy subjects who perform BPCs, and another for assessing the false alarm rate in ECGs recorded during... (More)
Body position changes (BPCs) are manifested as shifts in the electrical axis of the heart, which may lead to ST changes in the ECG, misclassified as ischemic events. This paper presents a novel BPC detector based on a Laplacian noise model. It is assumed that a BPC can be modelled as a step-like change in the two coefficient series that result from the Karhunen-Loeve transform of the QRS complex and the ST-T segment. The generalized likelihood ratio test is explored for detection, where the statistical parameters of the Laplacian model are subject to estimation. Two databases are studied: one for assessing detection performance in healthy subjects who perform BPCs, and another for assessing the false alarm rate in ECGs recorded during percutaneous transluminal coronary angiography. The resulting probability of detection (P-D) and probability of false alarm (P-F) are 0.94 and 0.00, respectively, whereas the false alarm rate in ischemic recordings is 1 event/h. The proposed detector outperforms an existing detector based on the Gaussian noise model which achieved a P-D/P-F of 0.90/0.01 and a false alarm rate of 2 events/h. Analysis of the log-likelihood function for the Gaussian and Laplacian noise models show that latter model is more adequate. (C) 2014 Published by Elsevier Ltd. (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
Postural changes, Laplacian noise, Detection theory, Ischemia detection
in
Biomedical Signal Processing and Control
volume
14
pages
189 - 196
publisher
Elsevier
external identifiers
  • wos:000347019500018
  • scopus:84907858207
ISSN
1746-8094
DOI
10.1016/j.bspc.2014.08.002
language
English
LU publication?
yes
id
2727728a-8ee0-4c28-a334-6e4f4020d71c (old id 5091465)
date added to LUP
2015-02-24 10:57:46
date last changed
2017-07-30 04:19:44
@article{2727728a-8ee0-4c28-a334-6e4f4020d71c,
  abstract     = {Body position changes (BPCs) are manifested as shifts in the electrical axis of the heart, which may lead to ST changes in the ECG, misclassified as ischemic events. This paper presents a novel BPC detector based on a Laplacian noise model. It is assumed that a BPC can be modelled as a step-like change in the two coefficient series that result from the Karhunen-Loeve transform of the QRS complex and the ST-T segment. The generalized likelihood ratio test is explored for detection, where the statistical parameters of the Laplacian model are subject to estimation. Two databases are studied: one for assessing detection performance in healthy subjects who perform BPCs, and another for assessing the false alarm rate in ECGs recorded during percutaneous transluminal coronary angiography. The resulting probability of detection (P-D) and probability of false alarm (P-F) are 0.94 and 0.00, respectively, whereas the false alarm rate in ischemic recordings is 1 event/h. The proposed detector outperforms an existing detector based on the Gaussian noise model which achieved a P-D/P-F of 0.90/0.01 and a false alarm rate of 2 events/h. Analysis of the log-likelihood function for the Gaussian and Laplacian noise models show that latter model is more adequate. (C) 2014 Published by Elsevier Ltd.},
  author       = {Minchole, Ana and Sörnmo, Leif and Laguna, Pablo},
  issn         = {1746-8094},
  keyword      = {Postural changes,Laplacian noise,Detection theory,Ischemia detection},
  language     = {eng},
  pages        = {189--196},
  publisher    = {Elsevier},
  series       = {Biomedical Signal Processing and Control},
  title        = {Detection of body position changes from the ECG using a Laplacian noise model},
  url          = {http://dx.doi.org/10.1016/j.bspc.2014.08.002},
  volume       = {14},
  year         = {2014},
}