Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems

László Szilágyi, S. M. Szilágyi, A. Frigy, L. Dávid, Z. Benyó

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Computer-aided bedside patient monitoring requires real-time vital function analysis. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents all the methods that were conceptualized and implemented at the development of such a monitoring system at Medical Clinic No. 4 of Târgu Mureş. The system performs the following ECG signal processing steps: (1) Decomposition of the ECG signals using multi-resolution wavelet transformation, which also eliminates most of the high and low frequency noises. These components will serve as input for wave classification algorithms. (2) Identification of QRS complexes, P and T waves using two different algorithms: a sequential classification and a neural-network-based clustering algorithm. This latter also distinguishes normal R waves from abnormal cases. (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive (AR) model is applied to estimate the series of R-R intervals. The coefficients of the AR model are predicted using the Kalman filter, and these coefficients will determine a local spectrum for each QRS complex. By analyzing this spectrum, different arrhythmia cases (bigeminy, trigeminy, ventricular flutter, etc.) are identified. The algorithms were tested using the MIT-BIH signal database and own multi-channel ECG registrations. The QRS complex detection ratio is over 99.6%. Using the output of the above mentioned methods, the on-line monitor system performs heart rate variability (HRV) and heart rate turbulence (HRT) analysis, which can help the diagnosis and can predict dangerous states of the patient.

Original languageEnglish
Title of host publicationIFMBE Proceedings
PublisherSpringer Verlag
Pages1021-1025
Number of pages5
Volume14
Edition1
Publication statusPublished - 2007
Event10th World Congress on Medical Physics and Biomedical Engineering, WC 2006 - Seoul, Korea, Republic of
Duration: Aug 27 2006Sep 1 2006

Other

Other10th World Congress on Medical Physics and Biomedical Engineering, WC 2006
CountryKorea, Republic of
CitySeoul
Period8/27/069/1/06

Fingerprint

Electrocardiography
Monitoring
Signal processing
Patient monitoring
Clustering algorithms
Kalman filters
Turbulence
Neural networks
Decomposition

Keywords

  • Arrhythmia detection
  • Kalman filter
  • QRS complex detection

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Szilágyi, L., Szilágyi, S. M., Frigy, A., Dávid, L., & Benyó, Z. (2007). Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems. In IFMBE Proceedings (1 ed., Vol. 14, pp. 1021-1025). Springer Verlag.

Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems. / Szilágyi, László; Szilágyi, S. M.; Frigy, A.; Dávid, L.; Benyó, Z.

IFMBE Proceedings. Vol. 14 1. ed. Springer Verlag, 2007. p. 1021-1025.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Szilágyi, L, Szilágyi, SM, Frigy, A, Dávid, L & Benyó, Z 2007, Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems. in IFMBE Proceedings. 1 edn, vol. 14, Springer Verlag, pp. 1021-1025, 10th World Congress on Medical Physics and Biomedical Engineering, WC 2006, Seoul, Korea, Republic of, 8/27/06.
Szilágyi L, Szilágyi SM, Frigy A, Dávid L, Benyó Z. Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems. In IFMBE Proceedings. 1 ed. Vol. 14. Springer Verlag. 2007. p. 1021-1025
Szilágyi, László ; Szilágyi, S. M. ; Frigy, A. ; Dávid, L. ; Benyó, Z. / Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems. IFMBE Proceedings. Vol. 14 1. ed. Springer Verlag, 2007. pp. 1021-1025
@inproceedings{e3cb4f2d69804649b893ea771c651cd2,
title = "Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems",
abstract = "Computer-aided bedside patient monitoring requires real-time vital function analysis. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents all the methods that were conceptualized and implemented at the development of such a monitoring system at Medical Clinic No. 4 of T{\^a}rgu Mureş. The system performs the following ECG signal processing steps: (1) Decomposition of the ECG signals using multi-resolution wavelet transformation, which also eliminates most of the high and low frequency noises. These components will serve as input for wave classification algorithms. (2) Identification of QRS complexes, P and T waves using two different algorithms: a sequential classification and a neural-network-based clustering algorithm. This latter also distinguishes normal R waves from abnormal cases. (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive (AR) model is applied to estimate the series of R-R intervals. The coefficients of the AR model are predicted using the Kalman filter, and these coefficients will determine a local spectrum for each QRS complex. By analyzing this spectrum, different arrhythmia cases (bigeminy, trigeminy, ventricular flutter, etc.) are identified. The algorithms were tested using the MIT-BIH signal database and own multi-channel ECG registrations. The QRS complex detection ratio is over 99.6{\%}. Using the output of the above mentioned methods, the on-line monitor system performs heart rate variability (HRV) and heart rate turbulence (HRT) analysis, which can help the diagnosis and can predict dangerous states of the patient.",
keywords = "Arrhythmia detection, Kalman filter, QRS complex detection",
author = "L{\'a}szl{\'o} Szil{\'a}gyi and Szil{\'a}gyi, {S. M.} and A. Frigy and L. D{\'a}vid and Z. Beny{\'o}",
year = "2007",
language = "English",
volume = "14",
pages = "1021--1025",
booktitle = "IFMBE Proceedings",
publisher = "Springer Verlag",
edition = "1",

}

TY - GEN

T1 - Quick ECG segmentation, artifact detection and risk estimation methods for on-line holter monitoring systems

AU - Szilágyi, László

AU - Szilágyi, S. M.

AU - Frigy, A.

AU - Dávid, L.

AU - Benyó, Z.

PY - 2007

Y1 - 2007

N2 - Computer-aided bedside patient monitoring requires real-time vital function analysis. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents all the methods that were conceptualized and implemented at the development of such a monitoring system at Medical Clinic No. 4 of Târgu Mureş. The system performs the following ECG signal processing steps: (1) Decomposition of the ECG signals using multi-resolution wavelet transformation, which also eliminates most of the high and low frequency noises. These components will serve as input for wave classification algorithms. (2) Identification of QRS complexes, P and T waves using two different algorithms: a sequential classification and a neural-network-based clustering algorithm. This latter also distinguishes normal R waves from abnormal cases. (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive (AR) model is applied to estimate the series of R-R intervals. The coefficients of the AR model are predicted using the Kalman filter, and these coefficients will determine a local spectrum for each QRS complex. By analyzing this spectrum, different arrhythmia cases (bigeminy, trigeminy, ventricular flutter, etc.) are identified. The algorithms were tested using the MIT-BIH signal database and own multi-channel ECG registrations. The QRS complex detection ratio is over 99.6%. Using the output of the above mentioned methods, the on-line monitor system performs heart rate variability (HRV) and heart rate turbulence (HRT) analysis, which can help the diagnosis and can predict dangerous states of the patient.

AB - Computer-aided bedside patient monitoring requires real-time vital function analysis. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents all the methods that were conceptualized and implemented at the development of such a monitoring system at Medical Clinic No. 4 of Târgu Mureş. The system performs the following ECG signal processing steps: (1) Decomposition of the ECG signals using multi-resolution wavelet transformation, which also eliminates most of the high and low frequency noises. These components will serve as input for wave classification algorithms. (2) Identification of QRS complexes, P and T waves using two different algorithms: a sequential classification and a neural-network-based clustering algorithm. This latter also distinguishes normal R waves from abnormal cases. (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive (AR) model is applied to estimate the series of R-R intervals. The coefficients of the AR model are predicted using the Kalman filter, and these coefficients will determine a local spectrum for each QRS complex. By analyzing this spectrum, different arrhythmia cases (bigeminy, trigeminy, ventricular flutter, etc.) are identified. The algorithms were tested using the MIT-BIH signal database and own multi-channel ECG registrations. The QRS complex detection ratio is over 99.6%. Using the output of the above mentioned methods, the on-line monitor system performs heart rate variability (HRV) and heart rate turbulence (HRT) analysis, which can help the diagnosis and can predict dangerous states of the patient.

KW - Arrhythmia detection

KW - Kalman filter

KW - QRS complex detection

UR - http://www.scopus.com/inward/record.url?scp=84958251328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958251328&partnerID=8YFLogxK

M3 - Conference contribution

VL - 14

SP - 1021

EP - 1025

BT - IFMBE Proceedings

PB - Springer Verlag

ER -