Enhanced acute myocardial infarction detection algorithm using local and global signal morphology

T. H. Joo, P. W. Schmitt, D. R. Hampton, K. Briscoe, Terence D Valenzuela, L. L. Clark

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

One shortcoming of conventional AMI detectors based on local morphologic features is that more subtle, globally distributed ECG changes (from the start of the QRS complex to the end of the T-wave) remain undetected. To characterize these changes, we develop two separate sets of basis vectors which span the subspaces occupied by the nonAMI ECGs and the AMI ECGs, respectively. The maximum likelihood estimate of the signal subspace is derived using the additive Gaussian noise model. A feature vector is computed by projecting the patient's ECG signal vector onto each of the basis vectors. A classification algorithm based on these global feature vectors performs significantly better than the conventional algorithm. Additional improvement is obtained by combining results from an optimized classifier using conventional local morphological measurements with the global feature classifier output to yield a combined decision. Test performance resulting from the local / global algorithm is Sensitivity 55% and Specificity 98% on a database of 1220 ECGs. A conventional ECG interpretive algorithm using localized ST-elevation and a rule-based classifier has Sensitivity 35% and Specificity 98%.

Original languageEnglish (US)
Title of host publicationComputers in Cardiology
Pages285-288
Number of pages4
Volume0
Edition0
StatePublished - 1998

Fingerprint

Electrocardiography
Myocardial Infarction
Classifiers
Likelihood Functions
Sensitivity and Specificity
Maximum likelihood
Databases
Detectors

ASJC Scopus subject areas

  • Software
  • Cardiology and Cardiovascular Medicine

Cite this

Joo, T. H., Schmitt, P. W., Hampton, D. R., Briscoe, K., Valenzuela, T. D., & Clark, L. L. (1998). Enhanced acute myocardial infarction detection algorithm using local and global signal morphology. In Computers in Cardiology (0 ed., Vol. 0, pp. 285-288)

Enhanced acute myocardial infarction detection algorithm using local and global signal morphology. / Joo, T. H.; Schmitt, P. W.; Hampton, D. R.; Briscoe, K.; Valenzuela, Terence D; Clark, L. L.

Computers in Cardiology. Vol. 0 0. ed. 1998. p. 285-288.

Research output: Chapter in Book/Report/Conference proceedingChapter

Joo, TH, Schmitt, PW, Hampton, DR, Briscoe, K, Valenzuela, TD & Clark, LL 1998, Enhanced acute myocardial infarction detection algorithm using local and global signal morphology. in Computers in Cardiology. 0 edn, vol. 0, pp. 285-288.
Joo TH, Schmitt PW, Hampton DR, Briscoe K, Valenzuela TD, Clark LL. Enhanced acute myocardial infarction detection algorithm using local and global signal morphology. In Computers in Cardiology. 0 ed. Vol. 0. 1998. p. 285-288
Joo, T. H. ; Schmitt, P. W. ; Hampton, D. R. ; Briscoe, K. ; Valenzuela, Terence D ; Clark, L. L. / Enhanced acute myocardial infarction detection algorithm using local and global signal morphology. Computers in Cardiology. Vol. 0 0. ed. 1998. pp. 285-288
@inbook{7074506822b64495a5062b831518f62e,
title = "Enhanced acute myocardial infarction detection algorithm using local and global signal morphology",
abstract = "One shortcoming of conventional AMI detectors based on local morphologic features is that more subtle, globally distributed ECG changes (from the start of the QRS complex to the end of the T-wave) remain undetected. To characterize these changes, we develop two separate sets of basis vectors which span the subspaces occupied by the nonAMI ECGs and the AMI ECGs, respectively. The maximum likelihood estimate of the signal subspace is derived using the additive Gaussian noise model. A feature vector is computed by projecting the patient's ECG signal vector onto each of the basis vectors. A classification algorithm based on these global feature vectors performs significantly better than the conventional algorithm. Additional improvement is obtained by combining results from an optimized classifier using conventional local morphological measurements with the global feature classifier output to yield a combined decision. Test performance resulting from the local / global algorithm is Sensitivity 55{\%} and Specificity 98{\%} on a database of 1220 ECGs. A conventional ECG interpretive algorithm using localized ST-elevation and a rule-based classifier has Sensitivity 35{\%} and Specificity 98{\%}.",
author = "Joo, {T. H.} and Schmitt, {P. W.} and Hampton, {D. R.} and K. Briscoe and Valenzuela, {Terence D} and Clark, {L. L.}",
year = "1998",
language = "English (US)",
volume = "0",
pages = "285--288",
booktitle = "Computers in Cardiology",
edition = "0",

}

TY - CHAP

T1 - Enhanced acute myocardial infarction detection algorithm using local and global signal morphology

AU - Joo, T. H.

AU - Schmitt, P. W.

AU - Hampton, D. R.

AU - Briscoe, K.

AU - Valenzuela, Terence D

AU - Clark, L. L.

PY - 1998

Y1 - 1998

N2 - One shortcoming of conventional AMI detectors based on local morphologic features is that more subtle, globally distributed ECG changes (from the start of the QRS complex to the end of the T-wave) remain undetected. To characterize these changes, we develop two separate sets of basis vectors which span the subspaces occupied by the nonAMI ECGs and the AMI ECGs, respectively. The maximum likelihood estimate of the signal subspace is derived using the additive Gaussian noise model. A feature vector is computed by projecting the patient's ECG signal vector onto each of the basis vectors. A classification algorithm based on these global feature vectors performs significantly better than the conventional algorithm. Additional improvement is obtained by combining results from an optimized classifier using conventional local morphological measurements with the global feature classifier output to yield a combined decision. Test performance resulting from the local / global algorithm is Sensitivity 55% and Specificity 98% on a database of 1220 ECGs. A conventional ECG interpretive algorithm using localized ST-elevation and a rule-based classifier has Sensitivity 35% and Specificity 98%.

AB - One shortcoming of conventional AMI detectors based on local morphologic features is that more subtle, globally distributed ECG changes (from the start of the QRS complex to the end of the T-wave) remain undetected. To characterize these changes, we develop two separate sets of basis vectors which span the subspaces occupied by the nonAMI ECGs and the AMI ECGs, respectively. The maximum likelihood estimate of the signal subspace is derived using the additive Gaussian noise model. A feature vector is computed by projecting the patient's ECG signal vector onto each of the basis vectors. A classification algorithm based on these global feature vectors performs significantly better than the conventional algorithm. Additional improvement is obtained by combining results from an optimized classifier using conventional local morphological measurements with the global feature classifier output to yield a combined decision. Test performance resulting from the local / global algorithm is Sensitivity 55% and Specificity 98% on a database of 1220 ECGs. A conventional ECG interpretive algorithm using localized ST-elevation and a rule-based classifier has Sensitivity 35% and Specificity 98%.

UR - http://www.scopus.com/inward/record.url?scp=12844260969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12844260969&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:12844260969

VL - 0

SP - 285

EP - 288

BT - Computers in Cardiology

ER -