Quick ECG analysis for on-line holter monitoring systems

László Szilágyi, Sándor M. Szilágyi, Gergely Fördos, Z. Benyó

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

6 Citations (Scopus)

Abstract

Computer-aided bedside patient monitoring requires real-time analysis of vital functions. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents 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 transform, 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 clustering and a neural-network-based classification. This latter also distinguishes normal R waves from abnormal cases; (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive 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 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 99.5%.

Original languageEnglish
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Pages1678-1681
Number of pages4
DOIs
Publication statusPublished - 2006
Event28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 - New York, NY, United States
Duration: Aug 30 2006Sep 3 2006

Other

Other28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
CountryUnited States
CityNew York, NY
Period8/30/069/3/06

Fingerprint

Electrocardiography
Monitoring
Signal processing
Patient monitoring
Kalman filters
Wavelet transforms
Neural networks
Decomposition

ASJC Scopus subject areas

  • Bioengineering

Cite this

Szilágyi, L., Szilágyi, S. M., Fördos, G., & Benyó, Z. (2006). Quick ECG analysis for on-line holter monitoring systems. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings (pp. 1678-1681). [4029470] https://doi.org/10.1109/IEMBS.2006.259583

Quick ECG analysis for on-line holter monitoring systems. / Szilágyi, László; Szilágyi, Sándor M.; Fördos, Gergely; Benyó, Z.

Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. 2006. p. 1678-1681 4029470.

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

Szilágyi, L, Szilágyi, SM, Fördos, G & Benyó, Z 2006, Quick ECG analysis for on-line holter monitoring systems. in Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings., 4029470, pp. 1678-1681, 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06, New York, NY, United States, 8/30/06. https://doi.org/10.1109/IEMBS.2006.259583
Szilágyi L, Szilágyi SM, Fördos G, Benyó Z. Quick ECG analysis for on-line holter monitoring systems. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. 2006. p. 1678-1681. 4029470 https://doi.org/10.1109/IEMBS.2006.259583
Szilágyi, László ; Szilágyi, Sándor M. ; Fördos, Gergely ; Benyó, Z. / Quick ECG analysis for on-line holter monitoring systems. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. 2006. pp. 1678-1681
@inproceedings{614697f522064420b9ff4abdedc21847,
title = "Quick ECG analysis for on-line holter monitoring systems",
abstract = "Computer-aided bedside patient monitoring requires real-time analysis of vital functions. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents 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 transform, 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 clustering and a neural-network-based classification. This latter also distinguishes normal R waves from abnormal cases; (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive 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 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 99.5{\%}.",
author = "L{\'a}szl{\'o} Szil{\'a}gyi and Szil{\'a}gyi, {S{\'a}ndor M.} and Gergely F{\"o}rdos and Z. Beny{\'o}",
year = "2006",
doi = "10.1109/IEMBS.2006.259583",
language = "English",
isbn = "1424400325",
pages = "1678--1681",
booktitle = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

}

TY - GEN

T1 - Quick ECG analysis for on-line holter monitoring systems

AU - Szilágyi, László

AU - Szilágyi, Sándor M.

AU - Fördos, Gergely

AU - Benyó, Z.

PY - 2006

Y1 - 2006

N2 - Computer-aided bedside patient monitoring requires real-time analysis of vital functions. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents 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 transform, 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 clustering and a neural-network-based classification. This latter also distinguishes normal R waves from abnormal cases; (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive 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 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 99.5%.

AB - Computer-aided bedside patient monitoring requires real-time analysis of vital functions. On-line Holter monitors need reliable and quick algorithms to perform all the necessary signal processing tasks. This paper presents 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 transform, 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 clustering and a neural-network-based classification. This latter also distinguishes normal R waves from abnormal cases; (3) Localization of several kinds of arrhythmia using a spectral method. An autoregressive 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 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 99.5%.

UR - http://www.scopus.com/inward/record.url?scp=34047155670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047155670&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2006.259583

DO - 10.1109/IEMBS.2006.259583

M3 - Conference contribution

C2 - 17946060

AN - SCOPUS:34047155670

SN - 1424400325

SN - 9781424400324

SP - 1678

EP - 1681

BT - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

ER -