Automated analysis of ECG waveforms with atypical QRS complex morphologies

Reza Tafreshi, Abdul Jaleel, Jongil Lim, Leyla Tafreshi

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Automated detection of the various features of an electrocardiogram (ECG) waveform has wide applications in clinical diagnosis. Although detection of typical QRS waveforms has been widely studied, detection oftypical waveforms with complex morphologies remains challenging. The importance of detecting these complex waveforms and their patterns has grown recently due to their clinical implications. In this paper, we propose a novel algorithm for detecting the various peaks of such complex ECG waveforms. It is identified that most of the well-formed ECG waveforms - both typical and complex - fall into nine broad categories according to the standard nomenclature. Motivated by this ECG waveform classification, our algorithm uses signal analysis techniques such as first and second derivatives and adaptive thresholds to classify these waveforms accordingly by detecting the various features present in them. Temporal coherence along a single lead as well as spatial coherence across the 12 leads are used to improve performance. For waveform and pattern analysis, data from 50 healthy subjects and 50 patients with myocardial infarction were randomly selected. Results with an overall sensitivity of 99.06% and overall positive predictive value of 98.89% validate the effectiveness of the approach. Further, the algorithm gives true detections even on waveforms with fluctuations in baseline and wave amplitudes, proving its robustness against such variations.

Original languageEnglish
Pages (from-to)41-49
Number of pages9
JournalBiomedical Signal Processing and Control
Volume10
Issue number1
DOIs
Publication statusPublished - Mar 2014

Fingerprint

Electrocardiography
Signal analysis
Terminology
Healthy Volunteers
Lead
Myocardial Infarction
Derivatives

Keywords

  • ECG analysis
  • QRS detection

ASJC Scopus subject areas

  • Signal Processing
  • Health Informatics

Cite this

Automated analysis of ECG waveforms with atypical QRS complex morphologies. / Tafreshi, Reza; Jaleel, Abdul; Lim, Jongil; Tafreshi, Leyla.

In: Biomedical Signal Processing and Control, Vol. 10, No. 1, 03.2014, p. 41-49.

Research output: Contribution to journalArticle

Tafreshi, Reza ; Jaleel, Abdul ; Lim, Jongil ; Tafreshi, Leyla. / Automated analysis of ECG waveforms with atypical QRS complex morphologies. In: Biomedical Signal Processing and Control. 2014 ; Vol. 10, No. 1. pp. 41-49.
@article{7c142ebbda924b2ca4e428117e4476c3,
title = "Automated analysis of ECG waveforms with atypical QRS complex morphologies",
abstract = "Automated detection of the various features of an electrocardiogram (ECG) waveform has wide applications in clinical diagnosis. Although detection of typical QRS waveforms has been widely studied, detection oftypical waveforms with complex morphologies remains challenging. The importance of detecting these complex waveforms and their patterns has grown recently due to their clinical implications. In this paper, we propose a novel algorithm for detecting the various peaks of such complex ECG waveforms. It is identified that most of the well-formed ECG waveforms - both typical and complex - fall into nine broad categories according to the standard nomenclature. Motivated by this ECG waveform classification, our algorithm uses signal analysis techniques such as first and second derivatives and adaptive thresholds to classify these waveforms accordingly by detecting the various features present in them. Temporal coherence along a single lead as well as spatial coherence across the 12 leads are used to improve performance. For waveform and pattern analysis, data from 50 healthy subjects and 50 patients with myocardial infarction were randomly selected. Results with an overall sensitivity of 99.06{\%} and overall positive predictive value of 98.89{\%} validate the effectiveness of the approach. Further, the algorithm gives true detections even on waveforms with fluctuations in baseline and wave amplitudes, proving its robustness against such variations.",
keywords = "ECG analysis, QRS detection",
author = "Reza Tafreshi and Abdul Jaleel and Jongil Lim and Leyla Tafreshi",
year = "2014",
month = "3",
doi = "10.1016/j.bspc.2013.12.007",
language = "English",
volume = "10",
pages = "41--49",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Automated analysis of ECG waveforms with atypical QRS complex morphologies

AU - Tafreshi, Reza

AU - Jaleel, Abdul

AU - Lim, Jongil

AU - Tafreshi, Leyla

PY - 2014/3

Y1 - 2014/3

N2 - Automated detection of the various features of an electrocardiogram (ECG) waveform has wide applications in clinical diagnosis. Although detection of typical QRS waveforms has been widely studied, detection oftypical waveforms with complex morphologies remains challenging. The importance of detecting these complex waveforms and their patterns has grown recently due to their clinical implications. In this paper, we propose a novel algorithm for detecting the various peaks of such complex ECG waveforms. It is identified that most of the well-formed ECG waveforms - both typical and complex - fall into nine broad categories according to the standard nomenclature. Motivated by this ECG waveform classification, our algorithm uses signal analysis techniques such as first and second derivatives and adaptive thresholds to classify these waveforms accordingly by detecting the various features present in them. Temporal coherence along a single lead as well as spatial coherence across the 12 leads are used to improve performance. For waveform and pattern analysis, data from 50 healthy subjects and 50 patients with myocardial infarction were randomly selected. Results with an overall sensitivity of 99.06% and overall positive predictive value of 98.89% validate the effectiveness of the approach. Further, the algorithm gives true detections even on waveforms with fluctuations in baseline and wave amplitudes, proving its robustness against such variations.

AB - Automated detection of the various features of an electrocardiogram (ECG) waveform has wide applications in clinical diagnosis. Although detection of typical QRS waveforms has been widely studied, detection oftypical waveforms with complex morphologies remains challenging. The importance of detecting these complex waveforms and their patterns has grown recently due to their clinical implications. In this paper, we propose a novel algorithm for detecting the various peaks of such complex ECG waveforms. It is identified that most of the well-formed ECG waveforms - both typical and complex - fall into nine broad categories according to the standard nomenclature. Motivated by this ECG waveform classification, our algorithm uses signal analysis techniques such as first and second derivatives and adaptive thresholds to classify these waveforms accordingly by detecting the various features present in them. Temporal coherence along a single lead as well as spatial coherence across the 12 leads are used to improve performance. For waveform and pattern analysis, data from 50 healthy subjects and 50 patients with myocardial infarction were randomly selected. Results with an overall sensitivity of 99.06% and overall positive predictive value of 98.89% validate the effectiveness of the approach. Further, the algorithm gives true detections even on waveforms with fluctuations in baseline and wave amplitudes, proving its robustness against such variations.

KW - ECG analysis

KW - QRS detection

UR - http://www.scopus.com/inward/record.url?scp=84892772215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892772215&partnerID=8YFLogxK

U2 - 10.1016/j.bspc.2013.12.007

DO - 10.1016/j.bspc.2013.12.007

M3 - Article

VL - 10

SP - 41

EP - 49

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

IS - 1

ER -