Methodological considerations in calculating heart rate variability based on wearable device heart rate samples

Hung Kai Chen, Yu Feng Hu, Shien-Fong Lin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Heart rate variability (HRV) analysis has recently been incorporated into wearable device application. The data source of HRV is the time series of heart beat intervals extracted from electrocardiogram or photoplethysmogram. These intervals are non-uniformly sampled signals and not suitable for spectral HRV analysis, which usually uses uniformly resampled heart beat intervals before calculating the spectral domain parameters. Such a practice is not applicable to heart rate data obtained from wearable devices that usually display and export the beat per minute (BPM) time series data at 1 Hz. The preferred resampling rate to calculate spectral domain parameters is 4 Hz. We compare the spectral HRV results with the 1 Hz and 4 Hz resampling rates in order to validate the use of 1 Hz resampled-RRI data to represent wearable devices BPM time series data for HRV analysis. Our results show that, using a specific combination of signal processing techniques, the lowest mean relative error in spectral domain parameters of normalized low-frequency power (LFnu), normalized high-frequency power (HFnu) and the ratio of normalized low-frequency power to normalized high-frequency power (LFnu/HFnu) between 1 Hz and 4 Hz are 3.7%, 15.3% and 16.4%, respectively. We conclude that using the heart rate data sampled at 1 Hz produces a reasonable estimation of sympathetic activity but a poor estimation of parasympathetic activity.

Original languageEnglish (US)
JournalComputers in Biology and Medicine
DOIs
StateAccepted/In press - Jan 1 2018
Externally publishedYes

Fingerprint

Heart Rate
Equipment and Supplies
Time series
Information Storage and Retrieval
Electrocardiography
Signal processing

Keywords

  • Heart rate variability
  • Resampling rate
  • Spectral analysis
  • Wearable device

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

@article{7c844111113c4fc1b60e01df120a7002,
title = "Methodological considerations in calculating heart rate variability based on wearable device heart rate samples",
abstract = "Heart rate variability (HRV) analysis has recently been incorporated into wearable device application. The data source of HRV is the time series of heart beat intervals extracted from electrocardiogram or photoplethysmogram. These intervals are non-uniformly sampled signals and not suitable for spectral HRV analysis, which usually uses uniformly resampled heart beat intervals before calculating the spectral domain parameters. Such a practice is not applicable to heart rate data obtained from wearable devices that usually display and export the beat per minute (BPM) time series data at 1 Hz. The preferred resampling rate to calculate spectral domain parameters is 4 Hz. We compare the spectral HRV results with the 1 Hz and 4 Hz resampling rates in order to validate the use of 1 Hz resampled-RRI data to represent wearable devices BPM time series data for HRV analysis. Our results show that, using a specific combination of signal processing techniques, the lowest mean relative error in spectral domain parameters of normalized low-frequency power (LFnu), normalized high-frequency power (HFnu) and the ratio of normalized low-frequency power to normalized high-frequency power (LFnu/HFnu) between 1 Hz and 4 Hz are 3.7{\%}, 15.3{\%} and 16.4{\%}, respectively. We conclude that using the heart rate data sampled at 1 Hz produces a reasonable estimation of sympathetic activity but a poor estimation of parasympathetic activity.",
keywords = "Heart rate variability, Resampling rate, Spectral analysis, Wearable device",
author = "Chen, {Hung Kai} and Hu, {Yu Feng} and Shien-Fong Lin",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.compbiomed.2018.08.023",
language = "English (US)",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Methodological considerations in calculating heart rate variability based on wearable device heart rate samples

AU - Chen, Hung Kai

AU - Hu, Yu Feng

AU - Lin, Shien-Fong

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Heart rate variability (HRV) analysis has recently been incorporated into wearable device application. The data source of HRV is the time series of heart beat intervals extracted from electrocardiogram or photoplethysmogram. These intervals are non-uniformly sampled signals and not suitable for spectral HRV analysis, which usually uses uniformly resampled heart beat intervals before calculating the spectral domain parameters. Such a practice is not applicable to heart rate data obtained from wearable devices that usually display and export the beat per minute (BPM) time series data at 1 Hz. The preferred resampling rate to calculate spectral domain parameters is 4 Hz. We compare the spectral HRV results with the 1 Hz and 4 Hz resampling rates in order to validate the use of 1 Hz resampled-RRI data to represent wearable devices BPM time series data for HRV analysis. Our results show that, using a specific combination of signal processing techniques, the lowest mean relative error in spectral domain parameters of normalized low-frequency power (LFnu), normalized high-frequency power (HFnu) and the ratio of normalized low-frequency power to normalized high-frequency power (LFnu/HFnu) between 1 Hz and 4 Hz are 3.7%, 15.3% and 16.4%, respectively. We conclude that using the heart rate data sampled at 1 Hz produces a reasonable estimation of sympathetic activity but a poor estimation of parasympathetic activity.

AB - Heart rate variability (HRV) analysis has recently been incorporated into wearable device application. The data source of HRV is the time series of heart beat intervals extracted from electrocardiogram or photoplethysmogram. These intervals are non-uniformly sampled signals and not suitable for spectral HRV analysis, which usually uses uniformly resampled heart beat intervals before calculating the spectral domain parameters. Such a practice is not applicable to heart rate data obtained from wearable devices that usually display and export the beat per minute (BPM) time series data at 1 Hz. The preferred resampling rate to calculate spectral domain parameters is 4 Hz. We compare the spectral HRV results with the 1 Hz and 4 Hz resampling rates in order to validate the use of 1 Hz resampled-RRI data to represent wearable devices BPM time series data for HRV analysis. Our results show that, using a specific combination of signal processing techniques, the lowest mean relative error in spectral domain parameters of normalized low-frequency power (LFnu), normalized high-frequency power (HFnu) and the ratio of normalized low-frequency power to normalized high-frequency power (LFnu/HFnu) between 1 Hz and 4 Hz are 3.7%, 15.3% and 16.4%, respectively. We conclude that using the heart rate data sampled at 1 Hz produces a reasonable estimation of sympathetic activity but a poor estimation of parasympathetic activity.

KW - Heart rate variability

KW - Resampling rate

KW - Spectral analysis

KW - Wearable device

UR - http://www.scopus.com/inward/record.url?scp=85052747432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052747432&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2018.08.023

DO - 10.1016/j.compbiomed.2018.08.023

M3 - Article

C2 - 30177403

AN - SCOPUS:85052747432

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -