Bayesian classification of myocardial excitation abnormality using magnetocardiogram maps for mass screening.

Yumie Ono, A. Ishiyama, N. Kasai, S. Yamada, K. On, S. Watanabe, I. Yamaguchi, T. Miyashita, Keiji Tsukada

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We propose a novel classification method based on the Bayes rule to utilize the magnetocardiogram (MCG) in noninvasive mass screening. The cardiac excitation is directly tracked by maps of the MCG field generated by myocardial excitation current through the excited wave front. To adopt the characteristics of the excited wave fronts as a parameter for the Bayes theorem, we developed a parameterization procedure that consists of a two-dimensional wavelet approximation and a cluster analysis of magnetic field maps. With the parameter determined by this procedure, the probability of a subject to belong to a disease group or to the normal group is estimated by the Bayes theorem. The subject is classified into the group of the highest probability. We applied the proposed method to ST-T period of MCG data of 6 old myocardial infarction (OMI) patients and 15 normal controls. The method showed sensitivity of 83%; specificity, 100%; positive predictive value, 100%; and negative predictive value, 94% in the classification of OMI patients and normal controls. The processing time is less than 5 seconds per one subject. It suggests a possible application of the proposed method in mass screening of abnormal MCG patterns.

Original languageEnglish
Pages (from-to)43
Number of pages1
JournalNeurology and Clinical Neurophysiology
Volume2004
Publication statusPublished - 2004

Fingerprint

Mass Screening
Bayes Theorem
Myocardial Infarction
Magnetic Fields
Cluster Analysis

Keywords

  • Bayes criterion
  • Excited wave front
  • Gaussian mixture modeling
  • Magnetocardiogram
  • Myocardial infarction
  • Screening
  • Wavelet approximation

ASJC Scopus subject areas

  • Neuroscience(all)
  • Medicine(all)

Cite this

Bayesian classification of myocardial excitation abnormality using magnetocardiogram maps for mass screening. / Ono, Yumie; Ishiyama, A.; Kasai, N.; Yamada, S.; On, K.; Watanabe, S.; Yamaguchi, I.; Miyashita, T.; Tsukada, Keiji.

In: Neurology and Clinical Neurophysiology, Vol. 2004, 2004, p. 43.

Research output: Contribution to journalArticle

Ono, Y, Ishiyama, A, Kasai, N, Yamada, S, On, K, Watanabe, S, Yamaguchi, I, Miyashita, T & Tsukada, K 2004, 'Bayesian classification of myocardial excitation abnormality using magnetocardiogram maps for mass screening.', Neurology and Clinical Neurophysiology, vol. 2004, pp. 43.
Ono, Yumie ; Ishiyama, A. ; Kasai, N. ; Yamada, S. ; On, K. ; Watanabe, S. ; Yamaguchi, I. ; Miyashita, T. ; Tsukada, Keiji. / Bayesian classification of myocardial excitation abnormality using magnetocardiogram maps for mass screening. In: Neurology and Clinical Neurophysiology. 2004 ; Vol. 2004. pp. 43.
@article{ff4c95e90900414daa8180e5163418fb,
title = "Bayesian classification of myocardial excitation abnormality using magnetocardiogram maps for mass screening.",
abstract = "We propose a novel classification method based on the Bayes rule to utilize the magnetocardiogram (MCG) in noninvasive mass screening. The cardiac excitation is directly tracked by maps of the MCG field generated by myocardial excitation current through the excited wave front. To adopt the characteristics of the excited wave fronts as a parameter for the Bayes theorem, we developed a parameterization procedure that consists of a two-dimensional wavelet approximation and a cluster analysis of magnetic field maps. With the parameter determined by this procedure, the probability of a subject to belong to a disease group or to the normal group is estimated by the Bayes theorem. The subject is classified into the group of the highest probability. We applied the proposed method to ST-T period of MCG data of 6 old myocardial infarction (OMI) patients and 15 normal controls. The method showed sensitivity of 83{\%}; specificity, 100{\%}; positive predictive value, 100{\%}; and negative predictive value, 94{\%} in the classification of OMI patients and normal controls. The processing time is less than 5 seconds per one subject. It suggests a possible application of the proposed method in mass screening of abnormal MCG patterns.",
keywords = "Bayes criterion, Excited wave front, Gaussian mixture modeling, Magnetocardiogram, Myocardial infarction, Screening, Wavelet approximation",
author = "Yumie Ono and A. Ishiyama and N. Kasai and S. Yamada and K. On and S. Watanabe and I. Yamaguchi and T. Miyashita and Keiji Tsukada",
year = "2004",
language = "English",
volume = "2004",
pages = "43",
journal = "Neurology and Clinical Neurophysiology",
issn = "1526-8748",
publisher = "American Academy of Clinical Neurophysiology",

}

TY - JOUR

T1 - Bayesian classification of myocardial excitation abnormality using magnetocardiogram maps for mass screening.

AU - Ono, Yumie

AU - Ishiyama, A.

AU - Kasai, N.

AU - Yamada, S.

AU - On, K.

AU - Watanabe, S.

AU - Yamaguchi, I.

AU - Miyashita, T.

AU - Tsukada, Keiji

PY - 2004

Y1 - 2004

N2 - We propose a novel classification method based on the Bayes rule to utilize the magnetocardiogram (MCG) in noninvasive mass screening. The cardiac excitation is directly tracked by maps of the MCG field generated by myocardial excitation current through the excited wave front. To adopt the characteristics of the excited wave fronts as a parameter for the Bayes theorem, we developed a parameterization procedure that consists of a two-dimensional wavelet approximation and a cluster analysis of magnetic field maps. With the parameter determined by this procedure, the probability of a subject to belong to a disease group or to the normal group is estimated by the Bayes theorem. The subject is classified into the group of the highest probability. We applied the proposed method to ST-T period of MCG data of 6 old myocardial infarction (OMI) patients and 15 normal controls. The method showed sensitivity of 83%; specificity, 100%; positive predictive value, 100%; and negative predictive value, 94% in the classification of OMI patients and normal controls. The processing time is less than 5 seconds per one subject. It suggests a possible application of the proposed method in mass screening of abnormal MCG patterns.

AB - We propose a novel classification method based on the Bayes rule to utilize the magnetocardiogram (MCG) in noninvasive mass screening. The cardiac excitation is directly tracked by maps of the MCG field generated by myocardial excitation current through the excited wave front. To adopt the characteristics of the excited wave fronts as a parameter for the Bayes theorem, we developed a parameterization procedure that consists of a two-dimensional wavelet approximation and a cluster analysis of magnetic field maps. With the parameter determined by this procedure, the probability of a subject to belong to a disease group or to the normal group is estimated by the Bayes theorem. The subject is classified into the group of the highest probability. We applied the proposed method to ST-T period of MCG data of 6 old myocardial infarction (OMI) patients and 15 normal controls. The method showed sensitivity of 83%; specificity, 100%; positive predictive value, 100%; and negative predictive value, 94% in the classification of OMI patients and normal controls. The processing time is less than 5 seconds per one subject. It suggests a possible application of the proposed method in mass screening of abnormal MCG patterns.

KW - Bayes criterion

KW - Excited wave front

KW - Gaussian mixture modeling

KW - Magnetocardiogram

KW - Myocardial infarction

KW - Screening

KW - Wavelet approximation

UR - http://www.scopus.com/inward/record.url?scp=33645738822&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645738822&partnerID=8YFLogxK

M3 - Article

C2 - 16012686

AN - SCOPUS:29144435065

VL - 2004

SP - 43

JO - Neurology and Clinical Neurophysiology

JF - Neurology and Clinical Neurophysiology

SN - 1526-8748

ER -