Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms

Szymon Siecinski; Pawel S. Kostka; Ewaryst J. Tkacz

doi:10.1109/EMBC.2019.8857452

Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms

Szymon Siecinski^*, Pawel S. Kostka, Ewaryst J. Tkacz

^*Corresponding author for this work

Institute of Medical Informatics

Silesian University of Technology

Abstract

Heart rate variability (HRV) is a physiological variation of time interval between consecutive heart beats caused by the activity of autonomic nervous system. Seismocardiography (SCG) is a non-invasive method of analyzing cardiac vibrations and can be used to obtain inter-beat intervals required to perform HRV analysis. Heart beats on SCG signals are detected as the occurrences of aortic valve opening (AO) waves. Morphological variations between subjects complicate developing annotation algorithms. To overcome this obstacle we propose the empirical mode decomposition (EMD) to improve the signal quality. We used two algorithms to determine the influence of EMD on HRV indices: the first algorithm uses a band-pass filter and the second algorithm uses EMD as the first step. Higher beat detection performance was achieved for algorithm with EMD (Se=0.926, PPV=0.926 for all analyzed beats) than the algorithm with a band-pass filter (Se=0.859, PPV=0.855). The influence of analyzed algorithms on HRV indices is low despite the differences of heart beat detection performance between analyzed algorithms.

Original language	English
Title of host publication	2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 24-27 July 2019
Publication date	07.10.2019
Pages	4913-4916
ISBN (Electronic)	978-1-5386-1311-5
DOIs	https://doi.org/10.1109/EMBC.2019.8857452
Publication status	Published - 07.10.2019

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/EMBC.2019.8857452

Cite this

Siecinski, S., Kostka, P. S., & Tkacz, E. J. (2019). Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 24-27 July 2019 (pp. 4913-4916) https://doi.org/10.1109/EMBC.2019.8857452

@inproceedings{41c90bd6c0bf45d594c96c38f812999c,

title = "Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms",

abstract = "Heart rate variability (HRV) is a physiological variation of time interval between consecutive heart beats caused by the activity of autonomic nervous system. Seismocardiography (SCG) is a non-invasive method of analyzing cardiac vibrations and can be used to obtain inter-beat intervals required to perform HRV analysis. Heart beats on SCG signals are detected as the occurrences of aortic valve opening (AO) waves. Morphological variations between subjects complicate developing annotation algorithms. To overcome this obstacle we propose the empirical mode decomposition (EMD) to improve the signal quality. We used two algorithms to determine the influence of EMD on HRV indices: the first algorithm uses a band-pass filter and the second algorithm uses EMD as the first step. Higher beat detection performance was achieved for algorithm with EMD (Se=0.926, PPV=0.926 for all analyzed beats) than the algorithm with a band-pass filter (Se=0.859, PPV=0.855). The influence of analyzed algorithms on HRV indices is low despite the differences of heart beat detection performance between analyzed algorithms.",

author = "Szymon Siecinski and Kostka, {Pawel S.} and Tkacz, {Ewaryst J.}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.",

year = "2019",

month = oct,

day = "7",

doi = "10.1109/EMBC.2019.8857452",

language = "English",

pages = "4913--4916",

booktitle = "2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 24-27 July 2019",

}

Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms. / Siecinski, Szymon; Kostka, Pawel S.; Tkacz, Ewaryst J.
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 24-27 July 2019. 2019. p. 4913-4916.

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms

AU - Siecinski, Szymon

AU - Kostka, Pawel S.

AU - Tkacz, Ewaryst J.

PY - 2019/10/7

Y1 - 2019/10/7

N2 - Heart rate variability (HRV) is a physiological variation of time interval between consecutive heart beats caused by the activity of autonomic nervous system. Seismocardiography (SCG) is a non-invasive method of analyzing cardiac vibrations and can be used to obtain inter-beat intervals required to perform HRV analysis. Heart beats on SCG signals are detected as the occurrences of aortic valve opening (AO) waves. Morphological variations between subjects complicate developing annotation algorithms. To overcome this obstacle we propose the empirical mode decomposition (EMD) to improve the signal quality. We used two algorithms to determine the influence of EMD on HRV indices: the first algorithm uses a band-pass filter and the second algorithm uses EMD as the first step. Higher beat detection performance was achieved for algorithm with EMD (Se=0.926, PPV=0.926 for all analyzed beats) than the algorithm with a band-pass filter (Se=0.859, PPV=0.855). The influence of analyzed algorithms on HRV indices is low despite the differences of heart beat detection performance between analyzed algorithms.

AB - Heart rate variability (HRV) is a physiological variation of time interval between consecutive heart beats caused by the activity of autonomic nervous system. Seismocardiography (SCG) is a non-invasive method of analyzing cardiac vibrations and can be used to obtain inter-beat intervals required to perform HRV analysis. Heart beats on SCG signals are detected as the occurrences of aortic valve opening (AO) waves. Morphological variations between subjects complicate developing annotation algorithms. To overcome this obstacle we propose the empirical mode decomposition (EMD) to improve the signal quality. We used two algorithms to determine the influence of EMD on HRV indices: the first algorithm uses a band-pass filter and the second algorithm uses EMD as the first step. Higher beat detection performance was achieved for algorithm with EMD (Se=0.926, PPV=0.926 for all analyzed beats) than the algorithm with a band-pass filter (Se=0.859, PPV=0.855). The influence of analyzed algorithms on HRV indices is low despite the differences of heart beat detection performance between analyzed algorithms.

U2 - 10.1109/EMBC.2019.8857452

DO - 10.1109/EMBC.2019.8857452

M3 - Conference contribution

SP - 4913

EP - 4916

BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 24-27 July 2019

ER -

Influence of Empirical Mode Decomposition on Heart Rate Variability Indices Obtained from Smartphone Seismocardiograms

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this