Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform

Jonathan Goodfellow, OJ Escalona, Vivek Kodoth, Garnesh Manoharan, Antonio Bosnjak

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

Abstract

This work presents a novel approach to ECG R-peak detection based on the Discrete Wavelet Transform. 18,647 beats were analysed from thirty AF patients who underwent DC cardioversion at Royal Victoria Hospital, Belfast. The efficacy of the R-peak detection algorithm for both normal sinus rhythm and atrial fibrillation beats was assessed using three performance parameters: Sensitivity, Positive Predictivity and Accuracy. The preliminary results acquired using the proposed R(peak) detection approach provided results of 99.61%, 99.88% and 99.50% respectively, indicating that the utilization of DWT to assist peak detection is a viable method. The second phase of the study assessed how effectively the algorithm could discriminate between segments presenting normal sinus rhythm and those presenting atrial fibrillation based on RR interval data derived from the R-peak detection method. Fifty segments of normal sinus rhythm and AF-ECG were tested, and 100% successful classification was achieved. This highlights that the DWT R-peak detection method can be utilized in a practical application to differentiate between patients in normal sinus rhythm and those in AF.
LanguageEnglish
Title of host publicationUnknown Host Publication
EditorsAlan Murray
Number of pages4
Volume43
Publication statusE-pub ahead of print - 2 Mar 2017
Event43rd Computing in Cardiology conference, 2016, Vancouver, Canada -
Duration: 2 Mar 2017 → …

Conference

Conference43rd Computing in Cardiology conference, 2016, Vancouver, Canada
Period2/03/17 → …

Fingerprint

Discrete wavelet transforms
Electrocardiography

Keywords

  • Atrial fibrillation ECG denoising
  • discrete wavelet transform
  • mains interference filtering
  • digital filters
  • electrocardiography.

Cite this

Goodfellow, J., Escalona, OJ., Kodoth, V., Manoharan, G., & Bosnjak, A. (2017). Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform. In A. Murray (Ed.), Unknown Host Publication (Vol. 43)
Goodfellow, Jonathan ; Escalona, OJ ; Kodoth, Vivek ; Manoharan, Garnesh ; Bosnjak, Antonio. / Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform. Unknown Host Publication. editor / Alan Murray. Vol. 43 2017.
@inproceedings{ced930e24f1f47f9b42cd372b0f41f0f,
title = "Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform",
abstract = "This work presents a novel approach to ECG R-peak detection based on the Discrete Wavelet Transform. 18,647 beats were analysed from thirty AF patients who underwent DC cardioversion at Royal Victoria Hospital, Belfast. The efficacy of the R-peak detection algorithm for both normal sinus rhythm and atrial fibrillation beats was assessed using three performance parameters: Sensitivity, Positive Predictivity and Accuracy. The preliminary results acquired using the proposed R(peak) detection approach provided results of 99.61{\%}, 99.88{\%} and 99.50{\%} respectively, indicating that the utilization of DWT to assist peak detection is a viable method. The second phase of the study assessed how effectively the algorithm could discriminate between segments presenting normal sinus rhythm and those presenting atrial fibrillation based on RR interval data derived from the R-peak detection method. Fifty segments of normal sinus rhythm and AF-ECG were tested, and 100{\%} successful classification was achieved. This highlights that the DWT R-peak detection method can be utilized in a practical application to differentiate between patients in normal sinus rhythm and those in AF.",
keywords = "Atrial fibrillation ECG denoising, discrete wavelet transform, mains interference filtering, digital filters, electrocardiography.",
author = "Jonathan Goodfellow and OJ Escalona and Vivek Kodoth and Garnesh Manoharan and Antonio Bosnjak",
year = "2017",
month = "3",
day = "2",
language = "English",
volume = "43",
editor = "Alan Murray",
booktitle = "Unknown Host Publication",

}

Goodfellow, J, Escalona, OJ, Kodoth, V, Manoharan, G & Bosnjak, A 2017, Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform. in A Murray (ed.), Unknown Host Publication. vol. 43, 43rd Computing in Cardiology conference, 2016, Vancouver, Canada, 2/03/17.

Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform. / Goodfellow, Jonathan; Escalona, OJ; Kodoth, Vivek; Manoharan, Garnesh; Bosnjak, Antonio.

Unknown Host Publication. ed. / Alan Murray. Vol. 43 2017.

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

TY - GEN

T1 - Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform

AU - Goodfellow, Jonathan

AU - Escalona, OJ

AU - Kodoth, Vivek

AU - Manoharan, Garnesh

AU - Bosnjak, Antonio

PY - 2017/3/2

Y1 - 2017/3/2

N2 - This work presents a novel approach to ECG R-peak detection based on the Discrete Wavelet Transform. 18,647 beats were analysed from thirty AF patients who underwent DC cardioversion at Royal Victoria Hospital, Belfast. The efficacy of the R-peak detection algorithm for both normal sinus rhythm and atrial fibrillation beats was assessed using three performance parameters: Sensitivity, Positive Predictivity and Accuracy. The preliminary results acquired using the proposed R(peak) detection approach provided results of 99.61%, 99.88% and 99.50% respectively, indicating that the utilization of DWT to assist peak detection is a viable method. The second phase of the study assessed how effectively the algorithm could discriminate between segments presenting normal sinus rhythm and those presenting atrial fibrillation based on RR interval data derived from the R-peak detection method. Fifty segments of normal sinus rhythm and AF-ECG were tested, and 100% successful classification was achieved. This highlights that the DWT R-peak detection method can be utilized in a practical application to differentiate between patients in normal sinus rhythm and those in AF.

AB - This work presents a novel approach to ECG R-peak detection based on the Discrete Wavelet Transform. 18,647 beats were analysed from thirty AF patients who underwent DC cardioversion at Royal Victoria Hospital, Belfast. The efficacy of the R-peak detection algorithm for both normal sinus rhythm and atrial fibrillation beats was assessed using three performance parameters: Sensitivity, Positive Predictivity and Accuracy. The preliminary results acquired using the proposed R(peak) detection approach provided results of 99.61%, 99.88% and 99.50% respectively, indicating that the utilization of DWT to assist peak detection is a viable method. The second phase of the study assessed how effectively the algorithm could discriminate between segments presenting normal sinus rhythm and those presenting atrial fibrillation based on RR interval data derived from the R-peak detection method. Fifty segments of normal sinus rhythm and AF-ECG were tested, and 100% successful classification was achieved. This highlights that the DWT R-peak detection method can be utilized in a practical application to differentiate between patients in normal sinus rhythm and those in AF.

KW - Atrial fibrillation ECG denoising

KW - discrete wavelet transform

KW - mains interference filtering

KW - digital filters

KW - electrocardiography.

M3 - Conference contribution

VL - 43

BT - Unknown Host Publication

A2 - Murray, Alan

ER -

Goodfellow J, Escalona OJ, Kodoth V, Manoharan G, Bosnjak A. Denoising and Automated R-peak Detection in the ECG using Discrete Wavelet Transform. In Murray A, editor, Unknown Host Publication. Vol. 43. 2017