QRS detection in single-lead, telehealth electrocardiogram signals: Benchmarking open-source algorithms.


Journal

PLOS digital health
ISSN: 2767-3170
Titre abrégé: PLOS Digit Health
Pays: United States
ID NLM: 9918335064206676

Informations de publication

Date de publication:
Aug 2024
Historique:
received: 16 01 2024
accepted: 27 05 2024
medline: 13 8 2024
pubmed: 13 8 2024
entrez: 13 8 2024
Statut: epublish

Résumé

A key step in electrocardiogram (ECG) analysis is the detection of QRS complexes, particularly for arrhythmia detection. Telehealth ECGs present a new challenge for automated analysis as they are noisier than traditional clinical ECGs. The aim of this study was to identify the best-performing open-source QRS detector for use with telehealth ECGs. The performance of 18 open-source QRS detectors was assessed on six datasets. These included four datasets of ECGs collected under supervision, and two datasets of telehealth ECGs collected without clinical supervision. The telehealth ECGs, consisting of single-lead ECGs recorded between the hands, included a novel dataset of 479 ECGs collected in the SAFER study of screening for atrial fibrillation (AF). Performance was assessed against manual annotations. A total of 12 QRS detectors performed well on ECGs collected under clinical supervision (F1 score ≥0.96). However, fewer performed well on telehealth ECGs: five performed well on the TELE ECG Database; six performed well on high-quality SAFER data; and performance was poorer on low-quality SAFER data (three QRS detectors achieved F1 of 0.78-0.84). The presence of AF had little impact on performance. The Neurokit and University of New South Wales QRS detectors performed best in this study. These performed sufficiently well on high-quality telehealth ECGs, but not on low-quality ECGs. This demonstrates the need to handle low-quality ECGs appropriately to ensure only ECGs which can be accurately analysed are used for clinical decision making.

Sections du résumé

BACKGROUND AND OBJECTIVES OBJECTIVE
A key step in electrocardiogram (ECG) analysis is the detection of QRS complexes, particularly for arrhythmia detection. Telehealth ECGs present a new challenge for automated analysis as they are noisier than traditional clinical ECGs. The aim of this study was to identify the best-performing open-source QRS detector for use with telehealth ECGs.
METHODS METHODS
The performance of 18 open-source QRS detectors was assessed on six datasets. These included four datasets of ECGs collected under supervision, and two datasets of telehealth ECGs collected without clinical supervision. The telehealth ECGs, consisting of single-lead ECGs recorded between the hands, included a novel dataset of 479 ECGs collected in the SAFER study of screening for atrial fibrillation (AF). Performance was assessed against manual annotations.
RESULTS RESULTS
A total of 12 QRS detectors performed well on ECGs collected under clinical supervision (F1 score ≥0.96). However, fewer performed well on telehealth ECGs: five performed well on the TELE ECG Database; six performed well on high-quality SAFER data; and performance was poorer on low-quality SAFER data (three QRS detectors achieved F1 of 0.78-0.84). The presence of AF had little impact on performance.
CONCLUSIONS CONCLUSIONS
The Neurokit and University of New South Wales QRS detectors performed best in this study. These performed sufficiently well on high-quality telehealth ECGs, but not on low-quality ECGs. This demonstrates the need to handle low-quality ECGs appropriately to ensure only ECGs which can be accurately analysed are used for clinical decision making.

Identifiants

pubmed: 39137171
doi: 10.1371/journal.pdig.0000538
pii: PDIG-D-24-00016
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e0000538

Informations de copyright

Copyright: © 2024 Kristof et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Déclaration de conflit d'intérêts

MRC is employed by Astrazeneca PLC. HCL is employed by Zenicor Medical Systems AB.

Auteurs

Florian Kristof (F)

TUM School of Computation, Information, and Technology, Technical University of Munich, Garching bei München, Germany.

Maximilian Kapsecker (M)

TUM School of Computation, Information, and Technology, Technical University of Munich, Garching bei München, Germany.
Institute for Digital Medicine, University Hospital Bonn, Bonn, Germany.

Leon Nissen (L)

Institute for Digital Medicine, University Hospital Bonn, Bonn, Germany.

James Brimicombe (J)

Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.

Martin R Cowie (MR)

School of Cardiovascular Medicine & Sciences, Faculty of Lifesciences & Medicine, King's College London, London, United Kingdom.

Zixuan Ding (Z)

Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.

Andrew Dymond (A)

Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.

Stephan M Jonas (SM)

Institute for Digital Medicine, University Hospital Bonn, Bonn, Germany.

Hannah Clair Lindén (HC)

Zenicor Medical Systems AB, Stockholm, Sweden.

Gregory Y H Lip (GYH)

Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool, United Kingdom.
Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Aalborg, Denmark.

Kate Williams (K)

Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.

Jonathan Mant (J)

Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.

Peter H Charlton (PH)

Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.

Classifications MeSH