Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings

Cristina Perez; Alba Martin-Yebra; Jari Viik; Juan Pablo Martinez; Esther Pueyo; Pablo Laguna

doi:10.1109/IEEECONF53345.2021.9723261

Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings

Cristina Perez, Alba Martin-Yebra, Jari Viik, Juan Pablo Martinez, Esther Pueyo, Pablo Laguna

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

The electrocardiogram signal (ECG) represents the electrical activity of the heart measured at the body surface. Characteristic waves and their delineation marks are studied to define cardiac markers without using invasive procedures. Among them, slower adaptation of the QT interval, the time needed for ventricular depolarization plus repolarization, to sudden abrupt changes in heart rate (HR) has been identified as a marker of arrhythmic risk. Such abrupt HR changes are difficult to induce, leading here to explore estimation of this delay from the ramp-like HR variations observed in exercise stress test. However, stress test ECG signals are often corrupted by muscular activity and electrode motion, limiting the robustness of the information that can be extracted from them, as the identification of the T-wave end. The aim of this study is to find proper methods to emphasize the T-wave in order to improve delineation accuracy. Stress test ECG recordings from 447 subjects were analyzed. The first spatially-transformed lead based on two different lead-space reduction (LSR) techniques, and different learning versions, was used to delineate and obtain the QT series. Assuming that QT delineation errors will lead to a high variability in the QT interval series, the power of the high-pass filtered QT interval series was used as performance marker (the lower the power, the most stable the delineation). Periodic component analysis technique showed the lowest power, with no significant differences between its different learning versions.

Original language	English
Title of host publication	55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Subtitle of host publication	October 31 - November 3, 2021 Pacific Grove, California
Editors	Michael B. Matthews
Publisher	IEEE
Pages	261-264
Number of pages	4
ISBN (Electronic)	9781665458283
DOIs	https://doi.org/10.1109/IEEECONF53345.2021.9723261
Publication status	Published - 2022
Publication type	A4 Article in conference proceedings
Event	Asilomar Conference on Signals, Systems and Computers - Virtual, Pacific Grove, United States Duration: 31 Oct 2021 → 3 Nov 2021

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2021-October
ISSN (Print)	1058-6393

Conference

Conference	Asilomar Conference on Signals, Systems and Computers
Country/Territory	United States
City	Virtual, Pacific Grove
Period	31/10/21 → 3/11/21

Funding

This work was funded by project PID2019-104881RB-I00, and PID2019-105674RB-I00 funded by Spanish Ministry of Science and Innovation (MICINN) and FEDER, by Gobierno de Aragón (Reference Group Biomedical Signal Interpretation and Computational Simulation (BSICoS) T39-20R) cofunded by FEDER 2014-2020 “Building Europe from Aragón”, and by European Research Council (ERC) through project ERC-StG 638284. The computation was performed at the High

Keywords

biomedical marker
Periodic component analysis
QT interval

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/IEEECONF53345.2021.9723261

Cite this

Perez, C., Martin-Yebra, A., Viik, J., Martinez, J. P., Pueyo, E., & Laguna, P. (2022). Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings. In M. B. Matthews (Ed.), 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021: October 31 - November 3, 2021 Pacific Grove, California (pp. 261-264). (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2021-October). IEEE. https://doi.org/10.1109/IEEECONF53345.2021.9723261

Perez, Cristina ; Martin-Yebra, Alba ; Viik, Jari et al. / Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings. 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021: October 31 - November 3, 2021 Pacific Grove, California. editor / Michael B. Matthews. IEEE, 2022. pp. 261-264 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{cc36c72a7fee45e9a6829688e73f0815,

title = "Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings",

abstract = "The electrocardiogram signal (ECG) represents the electrical activity of the heart measured at the body surface. Characteristic waves and their delineation marks are studied to define cardiac markers without using invasive procedures. Among them, slower adaptation of the QT interval, the time needed for ventricular depolarization plus repolarization, to sudden abrupt changes in heart rate (HR) has been identified as a marker of arrhythmic risk. Such abrupt HR changes are difficult to induce, leading here to explore estimation of this delay from the ramp-like HR variations observed in exercise stress test. However, stress test ECG signals are often corrupted by muscular activity and electrode motion, limiting the robustness of the information that can be extracted from them, as the identification of the T-wave end. The aim of this study is to find proper methods to emphasize the T-wave in order to improve delineation accuracy. Stress test ECG recordings from 447 subjects were analyzed. The first spatially-transformed lead based on two different lead-space reduction (LSR) techniques, and different learning versions, was used to delineate and obtain the QT series. Assuming that QT delineation errors will lead to a high variability in the QT interval series, the power of the high-pass filtered QT interval series was used as performance marker (the lower the power, the most stable the delineation). Periodic component analysis technique showed the lowest power, with no significant differences between its different learning versions. ",

keywords = "biomedical marker, Periodic component analysis, QT interval",

author = "Cristina Perez and Alba Martin-Yebra and Jari Viik and Martinez, {Juan Pablo} and Esther Pueyo and Pablo Laguna",

note = "JUFOID=51931 Funding Information: This work was funded by project PID2019-104881RB-I00, and PID2019-105674RB-I00 funded by Spanish Ministry of Science and Innovation (MICINN) and FEDER, by Gobierno de Arag{\'o}n (Reference Group Biomedical Signal Interpretation and Computational Simulation (BSICoS) T39-20R) cofunded by FEDER 2014-2020 “Building Europe from Arag{\'o}n”, and by European Research Council (ERC) through project ERC-StG 638284. The computation was performed at the High Publisher Copyright: {\textcopyright} 2021 IEEE.; Asilomar Conference on Signals, Systems and Computers ; Conference date: 31-10-2021 Through 03-11-2021",

year = "2022",

doi = "10.1109/IEEECONF53345.2021.9723261",

language = "English",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE",

pages = "261--264",

editor = "Matthews, {Michael B.}",

booktitle = "55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021",

address = "United States",

}

Perez, C, Martin-Yebra, A, Viik, J, Martinez, JP, Pueyo, E & Laguna, P 2022, Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings. in MB Matthews (ed.), 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021: October 31 - November 3, 2021 Pacific Grove, California. Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2021-October, IEEE, pp. 261-264, Asilomar Conference on Signals, Systems and Computers, Virtual, Pacific Grove, United States, 31/10/21. https://doi.org/10.1109/IEEECONF53345.2021.9723261

Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings. / Perez, Cristina; Martin-Yebra, Alba; Viik, Jari et al.
55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021: October 31 - November 3, 2021 Pacific Grove, California. ed. / Michael B. Matthews. IEEE, 2022. p. 261-264 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2021-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings

AU - Perez, Cristina

AU - Martin-Yebra, Alba

AU - Viik, Jari

AU - Martinez, Juan Pablo

AU - Pueyo, Esther

AU - Laguna, Pablo

N1 - JUFOID=51931 Funding Information: This work was funded by project PID2019-104881RB-I00, and PID2019-105674RB-I00 funded by Spanish Ministry of Science and Innovation (MICINN) and FEDER, by Gobierno de Aragón (Reference Group Biomedical Signal Interpretation and Computational Simulation (BSICoS) T39-20R) cofunded by FEDER 2014-2020 “Building Europe from Aragón”, and by European Research Council (ERC) through project ERC-StG 638284. The computation was performed at the High Publisher Copyright: © 2021 IEEE.

PY - 2022

Y1 - 2022

N2 - The electrocardiogram signal (ECG) represents the electrical activity of the heart measured at the body surface. Characteristic waves and their delineation marks are studied to define cardiac markers without using invasive procedures. Among them, slower adaptation of the QT interval, the time needed for ventricular depolarization plus repolarization, to sudden abrupt changes in heart rate (HR) has been identified as a marker of arrhythmic risk. Such abrupt HR changes are difficult to induce, leading here to explore estimation of this delay from the ramp-like HR variations observed in exercise stress test. However, stress test ECG signals are often corrupted by muscular activity and electrode motion, limiting the robustness of the information that can be extracted from them, as the identification of the T-wave end. The aim of this study is to find proper methods to emphasize the T-wave in order to improve delineation accuracy. Stress test ECG recordings from 447 subjects were analyzed. The first spatially-transformed lead based on two different lead-space reduction (LSR) techniques, and different learning versions, was used to delineate and obtain the QT series. Assuming that QT delineation errors will lead to a high variability in the QT interval series, the power of the high-pass filtered QT interval series was used as performance marker (the lower the power, the most stable the delineation). Periodic component analysis technique showed the lowest power, with no significant differences between its different learning versions.

AB - The electrocardiogram signal (ECG) represents the electrical activity of the heart measured at the body surface. Characteristic waves and their delineation marks are studied to define cardiac markers without using invasive procedures. Among them, slower adaptation of the QT interval, the time needed for ventricular depolarization plus repolarization, to sudden abrupt changes in heart rate (HR) has been identified as a marker of arrhythmic risk. Such abrupt HR changes are difficult to induce, leading here to explore estimation of this delay from the ramp-like HR variations observed in exercise stress test. However, stress test ECG signals are often corrupted by muscular activity and electrode motion, limiting the robustness of the information that can be extracted from them, as the identification of the T-wave end. The aim of this study is to find proper methods to emphasize the T-wave in order to improve delineation accuracy. Stress test ECG recordings from 447 subjects were analyzed. The first spatially-transformed lead based on two different lead-space reduction (LSR) techniques, and different learning versions, was used to delineate and obtain the QT series. Assuming that QT delineation errors will lead to a high variability in the QT interval series, the power of the high-pass filtered QT interval series was used as performance marker (the lower the power, the most stable the delineation). Periodic component analysis technique showed the lowest power, with no significant differences between its different learning versions.

KW - biomedical marker

KW - Periodic component analysis

KW - QT interval

U2 - 10.1109/IEEECONF53345.2021.9723261

DO - 10.1109/IEEECONF53345.2021.9723261

M3 - Conference contribution

AN - SCOPUS:85127040636

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 261

EP - 264

BT - 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021

A2 - Matthews, Michael B.

PB - IEEE

T2 - Asilomar Conference on Signals, Systems and Computers

Y2 - 31 October 2021 through 3 November 2021

ER -

Perez C, Martin-Yebra A, Viik J, Martinez JP, Pueyo E, Laguna P. Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings. In Matthews MB, editor, 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021: October 31 - November 3, 2021 Pacific Grove, California. IEEE. 2022. p. 261-264. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/IEEECONF53345.2021.9723261

Eigenvector-based spatial ECG filtering improves QT delineation in stress test recordings

Abstract

Publication series

Conference

Funding

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this