Advanced

ECG-based detection of body position changes in ischemia monitoring

Garcia, J; Astrom, M; Mendive, J; Laguna, P and Sörnmo, Leif LU (2003) In IEEE Transactions on Biomedical Engineering 50(6). p.677-685
Abstract
The purpose of this gaper is to analyze and detect changes in body position (BPC) during electrocardiogram (ECG) recording. These changes are often manifested as shifts in the, electrical axis and may be misclassified as ischemic changes during. ambulatory monitoring. We investigate two ECG signal processing methods for detecting BPCs. Different schemes for feature extraction are used (spatial and scalar), while preprocessing, trend postprocessing and detection are identical. The spatial approach is based on VCG loop rotation angles and the scalar approach is based on the Karhunen-Loeve transform (KLT) coefficients. The methods are evaluated on two different databases: a database with annotated BPCs and the STAFF III database with... (More)
The purpose of this gaper is to analyze and detect changes in body position (BPC) during electrocardiogram (ECG) recording. These changes are often manifested as shifts in the, electrical axis and may be misclassified as ischemic changes during. ambulatory monitoring. We investigate two ECG signal processing methods for detecting BPCs. Different schemes for feature extraction are used (spatial and scalar), while preprocessing, trend postprocessing and detection are identical. The spatial approach is based on VCG loop rotation angles and the scalar approach is based on the Karhunen-Loeve transform (KLT) coefficients. The methods are evaluated on two different databases: a database with annotated BPCs and the STAFF III database with recordings from rest and during angioplasty-induced ischemia but not including BPCs. The angle-based detector results in performance values of detection probability P-D = 95%, false alarm probability P-F = 3% in the BPC database and false alarm rate in the STAFF III database in control ECCs during rest R-F(c) = 2 h(-1) (episodes per hour) and in ischemia recordings during angioplasty R-F(a) = 7 h(-1), whereas the KLT-based detector produces values of P-D = 89%, P-F = 3%, R-F(c) = 4 h(-1), and RF(a) = 11 h-1, respectively. Including information on noise level in the detection process to reduce the number of false alarms, performance values of P-D similar or equal to 90%, P-F similar or equal to 1%, R-F(c) similar or equal to 1 h(-1) and R-F(a) similar or equal to 2 h(-1) are obtained with both methods. It is concluded that reliable detection of BPCs may be achieved using the ECG signal and should work in parallel to ischemia detectors. (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
ischemia, body position changes, ECG, alarms, detection
in
IEEE Transactions on Biomedical Engineering
volume
50
issue
6
pages
677 - 685
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • wos:000183413100004
  • scopus:0012895207
ISSN
0018-9294
DOI
10.1109/TBME.2003.812208
language
English
LU publication?
yes
id
e78ac6af-a67c-4a5e-b313-616eb1f7bdb0 (old id 308909)
date added to LUP
2007-09-25 09:05:47
date last changed
2018-10-03 11:51:58
@article{e78ac6af-a67c-4a5e-b313-616eb1f7bdb0,
  abstract     = {The purpose of this gaper is to analyze and detect changes in body position (BPC) during electrocardiogram (ECG) recording. These changes are often manifested as shifts in the, electrical axis and may be misclassified as ischemic changes during. ambulatory monitoring. We investigate two ECG signal processing methods for detecting BPCs. Different schemes for feature extraction are used (spatial and scalar), while preprocessing, trend postprocessing and detection are identical. The spatial approach is based on VCG loop rotation angles and the scalar approach is based on the Karhunen-Loeve transform (KLT) coefficients. The methods are evaluated on two different databases: a database with annotated BPCs and the STAFF III database with recordings from rest and during angioplasty-induced ischemia but not including BPCs. The angle-based detector results in performance values of detection probability P-D = 95%, false alarm probability P-F = 3% in the BPC database and false alarm rate in the STAFF III database in control ECCs during rest R-F(c) = 2 h(-1) (episodes per hour) and in ischemia recordings during angioplasty R-F(a) = 7 h(-1), whereas the KLT-based detector produces values of P-D = 89%, P-F = 3%, R-F(c) = 4 h(-1), and RF(a) = 11 h-1, respectively. Including information on noise level in the detection process to reduce the number of false alarms, performance values of P-D similar or equal to 90%, P-F similar or equal to 1%, R-F(c) similar or equal to 1 h(-1) and R-F(a) similar or equal to 2 h(-1) are obtained with both methods. It is concluded that reliable detection of BPCs may be achieved using the ECG signal and should work in parallel to ischemia detectors.},
  author       = {Garcia, J and Astrom, M and Mendive, J and Laguna, P and Sörnmo, Leif},
  issn         = {0018-9294},
  keyword      = {ischemia,body position changes,ECG,alarms,detection},
  language     = {eng},
  number       = {6},
  pages        = {677--685},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  series       = {IEEE Transactions on Biomedical Engineering},
  title        = {ECG-based detection of body position changes in ischemia monitoring},
  url          = {http://dx.doi.org/10.1109/TBME.2003.812208},
  volume       = {50},
  year         = {2003},
}