Detection of Myocardial Ischemia Using Hidden Markov Models

BARDONOVÁ, Jana, Ivo PROVAZNÍK, Marie NOVÁKOVÁ and Renata VESELÁ. Detection of Myocardial Ischemia Using Hidden Markov Models. In Proceedings of 25th Annual International Conference IEEE EMBS. 25th ed. Cancún, Mexico: IEEE EMBS, 2003, p. 2869-2872. ISBN 0-7803-7789-3.

Basic information

Original name

Detection of Myocardial Ischemia Using Hidden Markov Models

Name in Czech

Detekce ischemie myokardu pomocí Markovových modelů

Authors

BARDONOVÁ, Jana (203 Czech Republic), Ivo PROVAZNÍK (203 Czech Republic), Marie NOVÁKOVÁ (203 Czech Republic, guarantor) and Renata VESELÁ (203 Czech Republic)

Edition

25. vyd. Cancún, Mexico, Proceedings of 25th Annual International Conference IEEE EMBS, p. 2869-2872, 4 pp. 2003

Publisher

IEEE EMBS

---

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

30105 Physiology

Country of publisher

Mexico

Confidentiality degree

není předmětem státního či obchodního tajemství

RIV identification code

RIV/00216224:14110/03:00008391

Organization unit

Faculty of Medicine

ISBN

0-7803-7789-3

ISSN

UT WoS

000189395300745

Keywords in English

Myocardial ischemia; ECG signal; QRS complex; Wavelet transform; Hidden Markov models.

Tags

ECG signal, Hidden Markov models., myocardial ischemia, QRS complex, wavelet transform

Tags

International impact, Reviewed

---

Abstract

V originále

The paper deals with detection of myocardial ischemia by analysis of electrophysiological changes within QRS complexes of electrocardiograms (ECG). ECG signals were analysed by continuous wavelet transform (CWT). Time - frequency spectra of QRS complexes were used as an input of a detection system based on hidden Markov models (HMMs). Parameters of the used HMMs were assessed to recommend their optimal values. The presented results show that HMM analysis of ECGs preprocessed by CWT can be used for early detection of myocardial ischemia. Eleven Langendorff perfused rabbit hearts were used to record training and test data to learn Markov models. An average value of resulting sensitivity and specificity of detection system was around 0.9 depending on parameter setting of the models.

In Czech

Práce se zabývá detekcí ischemie myokardu pomocí analýzy elektrofyziologických změn uvnitř QRS komplexu elektrokardiogramu. EKG signály byly analyzovány kontinuální vlnkovou transformací. Časově-frekvenční spektra QRS komplexů byla použita jako vstup do detekčního systému založeného na Markovových modelech. Do studie bylo zahrnuto 11 srdcí králíka perfundovaných dle Langendorffa.

---

Links

GA102/01/1494, research and development project

Name: Optické snímání akčních potenciálů a jeho využití v kardiologii Investor: Czech Science Foundation, Optical recording of action potentials and its application in cardiology