Detail publikace

Wavelet Transform Based Detection of the First-degree Atrioventricular Block

SMÍŠEK, R. VIŠČOR, I. IVORA, A. BULKOVÁ, V. MARŠÁNOVÁ, L. NEJEDLÝ, P. KOŠČOVÁ, Z. HALÁMEK, J. JURÁK, P. PLEŠINGER, F.

Originální název

Wavelet Transform Based Detection of the First-degree Atrioventricular Block

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Introduction: First-degree atrioventricular block (AVB I) is a pathology defined on ECG by a PR interval greater than 200 msec. This paper aims to automatically detect AVB I by measuring the length of the PR interval. Method: Our method consists of the following steps: a) Records with atrial fibrillation or atrial flutter were excluded. b) QRS complexes were detected. c) QRS onset and T offset was detected for each ECG cycle. The median distance between QRS onset and the end of the previous T- wave is calculated (marked as X). d) QRSs were aligned and clustered according to morphological similarity. QRSs of the most frequent morphology were averaged. e) QRS onset and offset were detected for the averaged QRS. The signal between QRS onset and offset was replaced by a line intersected by the QRS onset and offset points. This signal was transformed by a wavelet transform. f) The P wave was detected in the transformed signal. The P onset was detected in the section from QRS onset minus X to the P wave position. g) AVB I was detected when the PR interval was longer than 200 msec. Results: The algorithm was set up and validated on private data and tested on publicly available databases. The algorithm achieves sensitivity 0.81, 0.81, 0.82, 0.84 and specificity 0.91, 0.90, 0.86, 0.93 for CPSC, CPSC- Extra, PTB-XL and Georgia database, respectively.

Klíčová slova

Body-surface UHF-ECG, Ultra-high-frequency electrocardiography, VDI Vision

Autoři

SMÍŠEK, R.; VIŠČOR, I.; IVORA, A.; BULKOVÁ, V.; MARŠÁNOVÁ, L.; NEJEDLÝ, P.; KOŠČOVÁ, Z.; HALÁMEK, J.; JURÁK, P.; PLEŠINGER, F.

Vydáno

10. 1. 2022

Nakladatel

IEEE

Místo

Brno, Czech republic

ISSN

2325-887X

Periodikum

Computing in Cardiology

Ročník

48

Číslo

1

Stát

Spojené státy americké

Strany od

1

Strany do

4

Strany počet

4

URL

https://www.cinc.org/2021/Program/accepted/168_Preprint.pdf

BibTex

@inproceedings{BUT174123,
  author="Radovan {Smíšek} and Ivo {Viščor} and Adam {Ivora} and Veronika {Bulková} and Lucie {Šaclová} and Petr {Nejedlý} and Zuzana {Koščová} and Josef {Halámek} and Pavel {Jurák} and Filip {Plešinger}",
  title="Wavelet Transform Based Detection of the First-degree Atrioventricular Block",
  booktitle="Computing in Cardiology 2021",
  year="2022",
  journal="Computing in Cardiology",
  volume="48",
  number="1",
  pages="1--4",
  publisher="IEEE",
  address="Brno, Czech republic",
  doi="10.23919/CinC53138.2021.9662877",
  issn="2325-887X",
  url="https://www.cinc.org/2021/Program/accepted/168_Preprint.pdf"
}