Evaluation of Foetal ECG extraction Methods in the Presence of Non-Stationary Abdominal Mixtures

Fernando Andreotti; Joachim Behar; G. D. Clifford

Evaluation of Foetal ECG extraction Methods in the Presence of Non-Stationary Abdominal Mixtures

Fernando Andreotti, Joachim Behar, G. D. Clifford

Research output: Contribution to conference › Paper › peer-review

Abstract

The non-invasive foetal electrocardiogram obtained from abdominal electrodes is an alternative for assessing the foetal health state. This study evaluates the behavior of two well-known methods (Independent Component Analysis and Template Subtraction). These techniques are often referred to in literature for extracting the FECG from the abdominal mixture. Our analysis quantifies the extraction results in terms of accuracy of foetal peak detection using the F1 measure. 1750 five-minute-long simulations considering the absence and presence of non-stationarity mixtures served as dataset for this study. In terms of the F1 measure, on average ICA (97.3 ± 0.1 %) was found to outperform TS (88.1 ± 0.2 %). Moreover, we have shown that the presence of non-stationarities can degrade the performance of both methods considerably, indicating a beat-by-beat adaptive approach may be preferable.

Original language	American English
Pages	1585-1588
Number of pages	4
State	Published - 2014
Externally published	Yes
Event	XXIV CBEB - Brazilian Coingress on Biomedical Engineering - Uberlândia, Brazil Duration: 13 Oct 2014 → 17 Oct 2014 Conference number: 24 https://www.canal6.com.br/cbeb/2014/index.html

Conference

Conference	XXIV CBEB - Brazilian Coingress on Biomedical Engineering
Abbreviated title	CBEB 2014
Country/Territory	Brazil
City	Uberlândia
Period	13/10/14 → 17/10/14
Internet address	https://www.canal6.com.br/cbeb/2014/index.html

Keywords

Electrocardiogram (ECG)
Fetal Monitoring
Artificial Intelligence

Access to Document

https://www.canal6.com.br/cbeb/2014/index.html

Cite this

@conference{facdf23688c447b981b81d698c0217db,

title = "Evaluation of Foetal ECG extraction Methods in the Presence of Non-Stationary Abdominal Mixtures",

abstract = "The non-invasive foetal electrocardiogram obtained from abdominal electrodes is an alternative for assessing the foetal health state. This study evaluates the behavior of two well-known methods (Independent Component Analysis and Template Subtraction). These techniques are often referred to in literature for extracting the FECG from the abdominal mixture. Our analysis quantifies the extraction results in terms of accuracy of foetal peak detection using the F1 measure. 1750 five-minute-long simulations considering the absence and presence of non-stationarity mixtures served as dataset for this study. In terms of the F1 measure, on average ICA (97.3 ± 0.1 %) was found to outperform TS (88.1 ± 0.2 %). Moreover, we have shown that the presence of non-stationarities can degrade the performance of both methods considerably, indicating a beat-by-beat adaptive approach may be preferable.",

keywords = "Electrocardiogram (ECG), Fetal Monitoring, Artificial Intelligence",

author = "Fernando Andreotti and Joachim Behar and Clifford, {G. D.}",

year = "2014",

language = "American English",

pages = "1585--1588",

note = "XXIV CBEB - Brazilian Coingress on Biomedical Engineering, CBEB 2014 ; Conference date: 13-10-2014 Through 17-10-2014",

url = "https://www.canal6.com.br/cbeb/2014/index.html",

}

TY - CONF

T1 - Evaluation of Foetal ECG extraction Methods in the Presence of Non-Stationary Abdominal Mixtures

AU - Andreotti, Fernando

AU - Behar, Joachim

AU - Clifford, G. D.

N1 - Conference code: 24

PY - 2014

Y1 - 2014

N2 - The non-invasive foetal electrocardiogram obtained from abdominal electrodes is an alternative for assessing the foetal health state. This study evaluates the behavior of two well-known methods (Independent Component Analysis and Template Subtraction). These techniques are often referred to in literature for extracting the FECG from the abdominal mixture. Our analysis quantifies the extraction results in terms of accuracy of foetal peak detection using the F1 measure. 1750 five-minute-long simulations considering the absence and presence of non-stationarity mixtures served as dataset for this study. In terms of the F1 measure, on average ICA (97.3 ± 0.1 %) was found to outperform TS (88.1 ± 0.2 %). Moreover, we have shown that the presence of non-stationarities can degrade the performance of both methods considerably, indicating a beat-by-beat adaptive approach may be preferable.

AB - The non-invasive foetal electrocardiogram obtained from abdominal electrodes is an alternative for assessing the foetal health state. This study evaluates the behavior of two well-known methods (Independent Component Analysis and Template Subtraction). These techniques are often referred to in literature for extracting the FECG from the abdominal mixture. Our analysis quantifies the extraction results in terms of accuracy of foetal peak detection using the F1 measure. 1750 five-minute-long simulations considering the absence and presence of non-stationarity mixtures served as dataset for this study. In terms of the F1 measure, on average ICA (97.3 ± 0.1 %) was found to outperform TS (88.1 ± 0.2 %). Moreover, we have shown that the presence of non-stationarities can degrade the performance of both methods considerably, indicating a beat-by-beat adaptive approach may be preferable.

KW - Electrocardiogram (ECG)

KW - Fetal Monitoring

KW - Artificial Intelligence

M3 - Paper

SP - 1585

EP - 1588

T2 - XXIV CBEB - Brazilian Coingress on Biomedical Engineering

Y2 - 13 October 2014 through 17 October 2014

ER -

Evaluation of Foetal ECG extraction Methods in the Presence of Non-Stationary Abdominal Mixtures

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this