Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction

Reza Tafreshi, Jongil Lim, Jaleed Abdul, Leyla Tafreshi

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

3 Citations (Scopus)

Abstract

Electrocardiogram (ECG), as a noninvasive electrical recording of the heart rhythm, is one of the most reliable diagnostic tools for identifying patients with suspected myocardial infarction (MI). We propose a novel detection algorithm based on the use of simple pattern matching techniques in order to increase the accuracy of MI detection. The algorithm classifies the waveforms into five fundamental types of ECG. It then improves the detections using temporal correlation between successive ECG beats for further corrections. ST elevation is then calculated as the difference in magnitudes between the isoelectric line and the ST point and used as an indication of MI. The algorithm was tested using 20 MI patient data and resulted in a true QRS detection rate of 98.9%. The algorithm successfully classifies 199 out of 220 leads in 20 data sets into the five major groups. This proved to be a key step towards improving the accuracy of the algorithm as most of the waveforms belong to these major groups.

Original languageEnglish
Title of host publicationProceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012
Pages143-148
Number of pages6
DOIs
Publication statusPublished - 2012
Event9th IASTED International Conference on Biomedical Engineering, BioMed 2012 - Innsbruck, Austria
Duration: 15 Feb 201217 Feb 2012

Other

Other9th IASTED International Conference on Biomedical Engineering, BioMed 2012
CountryAustria
CityInnsbruck
Period15/2/1217/2/12

Fingerprint

Electrocardiography
Pattern matching

Keywords

  • Electrocardiogram
  • Myocardial Infarction
  • QRS detection
  • ST elevation

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Tafreshi, R., Lim, J., Abdul, J., & Tafreshi, L. (2012). Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction. In Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012 (pp. 143-148) https://doi.org/10.2316/P.2012.764-141

Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction. / Tafreshi, Reza; Lim, Jongil; Abdul, Jaleed; Tafreshi, Leyla.

Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012. 2012. p. 143-148.

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

Tafreshi, R, Lim, J, Abdul, J & Tafreshi, L 2012, Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction. in Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012. pp. 143-148, 9th IASTED International Conference on Biomedical Engineering, BioMed 2012, Innsbruck, Austria, 15/2/12. https://doi.org/10.2316/P.2012.764-141
Tafreshi R, Lim J, Abdul J, Tafreshi L. Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction. In Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012. 2012. p. 143-148 https://doi.org/10.2316/P.2012.764-141
Tafreshi, Reza ; Lim, Jongil ; Abdul, Jaleed ; Tafreshi, Leyla. / Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction. Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012. 2012. pp. 143-148
@inproceedings{dc0551155aab46f49f958b3c72830b54,
title = "Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction",
abstract = "Electrocardiogram (ECG), as a noninvasive electrical recording of the heart rhythm, is one of the most reliable diagnostic tools for identifying patients with suspected myocardial infarction (MI). We propose a novel detection algorithm based on the use of simple pattern matching techniques in order to increase the accuracy of MI detection. The algorithm classifies the waveforms into five fundamental types of ECG. It then improves the detections using temporal correlation between successive ECG beats for further corrections. ST elevation is then calculated as the difference in magnitudes between the isoelectric line and the ST point and used as an indication of MI. The algorithm was tested using 20 MI patient data and resulted in a true QRS detection rate of 98.9{\%}. The algorithm successfully classifies 199 out of 220 leads in 20 data sets into the five major groups. This proved to be a key step towards improving the accuracy of the algorithm as most of the waveforms belong to these major groups.",
keywords = "Electrocardiogram, Myocardial Infarction, QRS detection, ST elevation",
author = "Reza Tafreshi and Jongil Lim and Jaleed Abdul and Leyla Tafreshi",
year = "2012",
doi = "10.2316/P.2012.764-141",
language = "English",
isbn = "9780889869097",
pages = "143--148",
booktitle = "Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012",

}

TY - GEN

T1 - Electrocardiogram QRS detection using temporal correlation for diagnosis of myocardial infarction

AU - Tafreshi, Reza

AU - Lim, Jongil

AU - Abdul, Jaleed

AU - Tafreshi, Leyla

PY - 2012

Y1 - 2012

N2 - Electrocardiogram (ECG), as a noninvasive electrical recording of the heart rhythm, is one of the most reliable diagnostic tools for identifying patients with suspected myocardial infarction (MI). We propose a novel detection algorithm based on the use of simple pattern matching techniques in order to increase the accuracy of MI detection. The algorithm classifies the waveforms into five fundamental types of ECG. It then improves the detections using temporal correlation between successive ECG beats for further corrections. ST elevation is then calculated as the difference in magnitudes between the isoelectric line and the ST point and used as an indication of MI. The algorithm was tested using 20 MI patient data and resulted in a true QRS detection rate of 98.9%. The algorithm successfully classifies 199 out of 220 leads in 20 data sets into the five major groups. This proved to be a key step towards improving the accuracy of the algorithm as most of the waveforms belong to these major groups.

AB - Electrocardiogram (ECG), as a noninvasive electrical recording of the heart rhythm, is one of the most reliable diagnostic tools for identifying patients with suspected myocardial infarction (MI). We propose a novel detection algorithm based on the use of simple pattern matching techniques in order to increase the accuracy of MI detection. The algorithm classifies the waveforms into five fundamental types of ECG. It then improves the detections using temporal correlation between successive ECG beats for further corrections. ST elevation is then calculated as the difference in magnitudes between the isoelectric line and the ST point and used as an indication of MI. The algorithm was tested using 20 MI patient data and resulted in a true QRS detection rate of 98.9%. The algorithm successfully classifies 199 out of 220 leads in 20 data sets into the five major groups. This proved to be a key step towards improving the accuracy of the algorithm as most of the waveforms belong to these major groups.

KW - Electrocardiogram

KW - Myocardial Infarction

KW - QRS detection

KW - ST elevation

UR - http://www.scopus.com/inward/record.url?scp=84863684151&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863684151&partnerID=8YFLogxK

U2 - 10.2316/P.2012.764-141

DO - 10.2316/P.2012.764-141

M3 - Conference contribution

AN - SCOPUS:84863684151

SN - 9780889869097

SP - 143

EP - 148

BT - Proceedings of the 9th IASTED International Conference on Biomedical Engineering, BioMed 2012

ER -