Pattern recognition in evaluation of haemorheological and haemodynamical measurements in the cardiological diagnostics.

K. Tóth, B. Mezey, I. Juricskay, T. Jávor

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The non-invasive differential diagnosis of ischaemic heart disease (IHD) and acute myocarditis or secondary cardiomyopathy following myocarditis can be difficult on the basis of the complaints, resting and exercise ECG and nuclear cardiological tests. 92 patients (mean age: 46 years) in the first step and 100 patients (mean age: 44 years) in the second step all with heart troubles, were examined. Besides determination of the routine parameters, nuclear haemodynamical and haemorheological measurements were carried out. Then each group of the patients was classified into 4 subgroups: 1) myocardial infarction /n:9/, 2) IHD /52/, 3) myocarditis /28/, 4) chronic cor pulmonale (CCP) /3/ subgroups in the first group and 1) normal /n:20/, 2) IHD /50/, 3) myocarditis /16/, 4) chronic cor pulmonale /14/ subgroups in the second group. The patients were reclassified by our multivariate pattern recognition algorithm (PRIMA). The average effectiveness of our method was over 80%, the recognition abilities for the subgroups (classes) ranged between 71 and 100%. An analysis of the discrimination power of the properties has made it evident that the haemorheological features were more characteristic than the haemodynamic ones in distinguishing the two differential-diagnostically critical groups. Our results show that our multivariate statistical method can be useful for the computer-aided decision in cardiological diagnostics.

Original languageEnglish
Pages (from-to)31-42
Number of pages12
JournalActa Medica Hungarica
Volume47
Issue number1-2
Publication statusPublished - 1990

Fingerprint

Myocarditis
Myocardial Ischemia
Pulmonary Heart Disease
Cardiomyopathies
Electrocardiography
Differential Diagnosis
Hemodynamics
Myocardial Infarction
Exercise

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Pattern recognition in evaluation of haemorheological and haemodynamical measurements in the cardiological diagnostics. / Tóth, K.; Mezey, B.; Juricskay, I.; Jávor, T.

In: Acta Medica Hungarica, Vol. 47, No. 1-2, 1990, p. 31-42.

Research output: Contribution to journalArticle

@article{6b04c12ec74041b3ab87610ce571c76b,
title = "Pattern recognition in evaluation of haemorheological and haemodynamical measurements in the cardiological diagnostics.",
abstract = "The non-invasive differential diagnosis of ischaemic heart disease (IHD) and acute myocarditis or secondary cardiomyopathy following myocarditis can be difficult on the basis of the complaints, resting and exercise ECG and nuclear cardiological tests. 92 patients (mean age: 46 years) in the first step and 100 patients (mean age: 44 years) in the second step all with heart troubles, were examined. Besides determination of the routine parameters, nuclear haemodynamical and haemorheological measurements were carried out. Then each group of the patients was classified into 4 subgroups: 1) myocardial infarction /n:9/, 2) IHD /52/, 3) myocarditis /28/, 4) chronic cor pulmonale (CCP) /3/ subgroups in the first group and 1) normal /n:20/, 2) IHD /50/, 3) myocarditis /16/, 4) chronic cor pulmonale /14/ subgroups in the second group. The patients were reclassified by our multivariate pattern recognition algorithm (PRIMA). The average effectiveness of our method was over 80{\%}, the recognition abilities for the subgroups (classes) ranged between 71 and 100{\%}. An analysis of the discrimination power of the properties has made it evident that the haemorheological features were more characteristic than the haemodynamic ones in distinguishing the two differential-diagnostically critical groups. Our results show that our multivariate statistical method can be useful for the computer-aided decision in cardiological diagnostics.",
author = "K. T{\'o}th and B. Mezey and I. Juricskay and T. J{\'a}vor",
year = "1990",
language = "English",
volume = "47",
pages = "31--42",
journal = "Acta Medica Hungarica",
issn = "0236-5286",
publisher = "Akademiai Kiado",
number = "1-2",

}

TY - JOUR

T1 - Pattern recognition in evaluation of haemorheological and haemodynamical measurements in the cardiological diagnostics.

AU - Tóth, K.

AU - Mezey, B.

AU - Juricskay, I.

AU - Jávor, T.

PY - 1990

Y1 - 1990

N2 - The non-invasive differential diagnosis of ischaemic heart disease (IHD) and acute myocarditis or secondary cardiomyopathy following myocarditis can be difficult on the basis of the complaints, resting and exercise ECG and nuclear cardiological tests. 92 patients (mean age: 46 years) in the first step and 100 patients (mean age: 44 years) in the second step all with heart troubles, were examined. Besides determination of the routine parameters, nuclear haemodynamical and haemorheological measurements were carried out. Then each group of the patients was classified into 4 subgroups: 1) myocardial infarction /n:9/, 2) IHD /52/, 3) myocarditis /28/, 4) chronic cor pulmonale (CCP) /3/ subgroups in the first group and 1) normal /n:20/, 2) IHD /50/, 3) myocarditis /16/, 4) chronic cor pulmonale /14/ subgroups in the second group. The patients were reclassified by our multivariate pattern recognition algorithm (PRIMA). The average effectiveness of our method was over 80%, the recognition abilities for the subgroups (classes) ranged between 71 and 100%. An analysis of the discrimination power of the properties has made it evident that the haemorheological features were more characteristic than the haemodynamic ones in distinguishing the two differential-diagnostically critical groups. Our results show that our multivariate statistical method can be useful for the computer-aided decision in cardiological diagnostics.

AB - The non-invasive differential diagnosis of ischaemic heart disease (IHD) and acute myocarditis or secondary cardiomyopathy following myocarditis can be difficult on the basis of the complaints, resting and exercise ECG and nuclear cardiological tests. 92 patients (mean age: 46 years) in the first step and 100 patients (mean age: 44 years) in the second step all with heart troubles, were examined. Besides determination of the routine parameters, nuclear haemodynamical and haemorheological measurements were carried out. Then each group of the patients was classified into 4 subgroups: 1) myocardial infarction /n:9/, 2) IHD /52/, 3) myocarditis /28/, 4) chronic cor pulmonale (CCP) /3/ subgroups in the first group and 1) normal /n:20/, 2) IHD /50/, 3) myocarditis /16/, 4) chronic cor pulmonale /14/ subgroups in the second group. The patients were reclassified by our multivariate pattern recognition algorithm (PRIMA). The average effectiveness of our method was over 80%, the recognition abilities for the subgroups (classes) ranged between 71 and 100%. An analysis of the discrimination power of the properties has made it evident that the haemorheological features were more characteristic than the haemodynamic ones in distinguishing the two differential-diagnostically critical groups. Our results show that our multivariate statistical method can be useful for the computer-aided decision in cardiological diagnostics.

UR - http://www.scopus.com/inward/record.url?scp=0025616642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025616642&partnerID=8YFLogxK

M3 - Article

C2 - 2280994

AN - SCOPUS:0025616642

VL - 47

SP - 31

EP - 42

JO - Acta Medica Hungarica

JF - Acta Medica Hungarica

SN - 0236-5286

IS - 1-2

ER -