Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults

P. Fonseca, Tim Weysen, M.S. Goelema, Els Møst, M. Radha, C.F.W. Lunsingh Scheurleer, Leonie van den Heuvel, R.M. Aarts

Research output: Contribution to journalArticleAcademicpeer-review

12 Citations (Scopus)

Abstract

Study Objectives:
To compare the accuracy of automatic sleep staging based on heart rate variability measured from photoplethysmography (PPG) combined with body movements measured with an accelerometer, with polysomnography (PSG) and actigraphy.


Methods:
Using wrist-worn PPG to analyze heart rate variability and an accelerometer to measure body movements, sleep stages and sleep statistics were automatically computed from overnight recordings. Sleep–wake, 4-class (wake/N1 + N2/N3/REM) and 3-class (wake/NREM/REM) classifiers were trained on 135 simultaneously recorded PSG and PPG recordings of 101 healthy participants and validated on 80 recordings of 51 healthy middle-aged adults. Epoch-by-epoch agreement and sleep statistics were compared with actigraphy for a subset of the validation set.

Results:
The sleep–wake classifier obtained an epoch-by-epoch Cohen’s κ between PPG and PSG sleep stages of 0.55 ± 0.14, sensitivity to wake of 58.2 ± 17.3%, and accuracy of 91.5 ± 5.1%. κ and sensitivity were significantly higher than with actigraphy (0.40 ± 0.15 and 45.5 ± 19.3%, respectively). The 3-class classifier achieved a κ of 0.46 ± 0.15 and accuracy of 72.9 ± 8.3%, and the 4-class classifier, a κ of 0.42 ± 0.12 and accuracy of 59.3 ± 8.5%.

Conclusions:
The moderate epoch-by-epoch agreement and, in particular, the good agreement in terms of sleep statistics suggest that this technique is promising for long-term sleep monitoring, although more evidence is needed to understand whether it can complement PSG in clinical practice. It also offers an improvement in sleep/wake detection over actigraphy for healthy individuals, although this must be confirmed on a larger, clinical population.

Keywords: Photoplethysmography, sleep tracker, actigraphy, computerized analysis, heart rate variability, scoring, statistics.

Topic: middle-aged adult,
photoplethysmography,
polysomnography,
sleep stages,
sleep,
epoch protocol,
actigraphy
LanguageEnglish
Article numberzsx097
JournalSleep
Volume40
Issue number7
DOIs
StatePublished - 1 Jul 2017

Fingerprint

Photoplethysmography
Polysomnography
Actigraphy
Sleep
Sleep Stages
Heart Rate
Body Weights and Measures
Wrist
Healthy Volunteers

Cite this

Fonseca, P. ; Weysen, Tim ; Goelema, M.S. ; Møst, Els ; Radha, M. ; Lunsingh Scheurleer, C.F.W. ; van den Heuvel, Leonie ; Aarts, R.M./ Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults. In: Sleep. 2017 ; Vol. 40, No. 7.
@article{5af11815d9b148deadd7ce88ef701a87,
title = "Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults",
abstract = "Study Objectives:To compare the accuracy of automatic sleep staging based on heart rate variability measured from photoplethysmography (PPG) combined with body movements measured with an accelerometer, with polysomnography (PSG) and actigraphy.Methods:Using wrist-worn PPG to analyze heart rate variability and an accelerometer to measure body movements, sleep stages and sleep statistics were automatically computed from overnight recordings. Sleep–wake, 4-class (wake/N1 + N2/N3/REM) and 3-class (wake/NREM/REM) classifiers were trained on 135 simultaneously recorded PSG and PPG recordings of 101 healthy participants and validated on 80 recordings of 51 healthy middle-aged adults. Epoch-by-epoch agreement and sleep statistics were compared with actigraphy for a subset of the validation set.Results:The sleep–wake classifier obtained an epoch-by-epoch Cohen’s κ between PPG and PSG sleep stages of 0.55 ± 0.14, sensitivity to wake of 58.2 ± 17.3{\%}, and accuracy of 91.5 ± 5.1{\%}. κ and sensitivity were significantly higher than with actigraphy (0.40 ± 0.15 and 45.5 ± 19.3{\%}, respectively). The 3-class classifier achieved a κ of 0.46 ± 0.15 and accuracy of 72.9 ± 8.3{\%}, and the 4-class classifier, a κ of 0.42 ± 0.12 and accuracy of 59.3 ± 8.5{\%}.Conclusions:The moderate epoch-by-epoch agreement and, in particular, the good agreement in terms of sleep statistics suggest that this technique is promising for long-term sleep monitoring, although more evidence is needed to understand whether it can complement PSG in clinical practice. It also offers an improvement in sleep/wake detection over actigraphy for healthy individuals, although this must be confirmed on a larger, clinical population.Keywords: Photoplethysmography, sleep tracker, actigraphy, computerized analysis, heart rate variability, scoring, statistics.Topic: middle-aged adult, photoplethysmography, polysomnography, sleep stages, sleep, epoch protocol, actigraphy",
author = "P. Fonseca and Tim Weysen and M.S. Goelema and Els M{\o}st and M. Radha and {Lunsingh Scheurleer}, C.F.W. and {van den Heuvel}, Leonie and R.M. Aarts",
year = "2017",
month = "7",
day = "1",
doi = "10.1093/sleep/zsx097",
language = "English",
volume = "40",
journal = "Sleep",
issn = "0161-8105",
publisher = "American Academy of Sleep Medicine",
number = "7",

}

Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults. / Fonseca, P.; Weysen, Tim; Goelema, M.S.; Møst, Els; Radha, M.; Lunsingh Scheurleer, C.F.W.; van den Heuvel, Leonie; Aarts, R.M.

In: Sleep, Vol. 40, No. 7, zsx097, 01.07.2017.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults

AU - Fonseca,P.

AU - Weysen,Tim

AU - Goelema,M.S.

AU - Møst,Els

AU - Radha,M.

AU - Lunsingh Scheurleer,C.F.W.

AU - van den Heuvel,Leonie

AU - Aarts,R.M.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Study Objectives:To compare the accuracy of automatic sleep staging based on heart rate variability measured from photoplethysmography (PPG) combined with body movements measured with an accelerometer, with polysomnography (PSG) and actigraphy.Methods:Using wrist-worn PPG to analyze heart rate variability and an accelerometer to measure body movements, sleep stages and sleep statistics were automatically computed from overnight recordings. Sleep–wake, 4-class (wake/N1 + N2/N3/REM) and 3-class (wake/NREM/REM) classifiers were trained on 135 simultaneously recorded PSG and PPG recordings of 101 healthy participants and validated on 80 recordings of 51 healthy middle-aged adults. Epoch-by-epoch agreement and sleep statistics were compared with actigraphy for a subset of the validation set.Results:The sleep–wake classifier obtained an epoch-by-epoch Cohen’s κ between PPG and PSG sleep stages of 0.55 ± 0.14, sensitivity to wake of 58.2 ± 17.3%, and accuracy of 91.5 ± 5.1%. κ and sensitivity were significantly higher than with actigraphy (0.40 ± 0.15 and 45.5 ± 19.3%, respectively). The 3-class classifier achieved a κ of 0.46 ± 0.15 and accuracy of 72.9 ± 8.3%, and the 4-class classifier, a κ of 0.42 ± 0.12 and accuracy of 59.3 ± 8.5%.Conclusions:The moderate epoch-by-epoch agreement and, in particular, the good agreement in terms of sleep statistics suggest that this technique is promising for long-term sleep monitoring, although more evidence is needed to understand whether it can complement PSG in clinical practice. It also offers an improvement in sleep/wake detection over actigraphy for healthy individuals, although this must be confirmed on a larger, clinical population.Keywords: Photoplethysmography, sleep tracker, actigraphy, computerized analysis, heart rate variability, scoring, statistics.Topic: middle-aged adult, photoplethysmography, polysomnography, sleep stages, sleep, epoch protocol, actigraphy

AB - Study Objectives:To compare the accuracy of automatic sleep staging based on heart rate variability measured from photoplethysmography (PPG) combined with body movements measured with an accelerometer, with polysomnography (PSG) and actigraphy.Methods:Using wrist-worn PPG to analyze heart rate variability and an accelerometer to measure body movements, sleep stages and sleep statistics were automatically computed from overnight recordings. Sleep–wake, 4-class (wake/N1 + N2/N3/REM) and 3-class (wake/NREM/REM) classifiers were trained on 135 simultaneously recorded PSG and PPG recordings of 101 healthy participants and validated on 80 recordings of 51 healthy middle-aged adults. Epoch-by-epoch agreement and sleep statistics were compared with actigraphy for a subset of the validation set.Results:The sleep–wake classifier obtained an epoch-by-epoch Cohen’s κ between PPG and PSG sleep stages of 0.55 ± 0.14, sensitivity to wake of 58.2 ± 17.3%, and accuracy of 91.5 ± 5.1%. κ and sensitivity were significantly higher than with actigraphy (0.40 ± 0.15 and 45.5 ± 19.3%, respectively). The 3-class classifier achieved a κ of 0.46 ± 0.15 and accuracy of 72.9 ± 8.3%, and the 4-class classifier, a κ of 0.42 ± 0.12 and accuracy of 59.3 ± 8.5%.Conclusions:The moderate epoch-by-epoch agreement and, in particular, the good agreement in terms of sleep statistics suggest that this technique is promising for long-term sleep monitoring, although more evidence is needed to understand whether it can complement PSG in clinical practice. It also offers an improvement in sleep/wake detection over actigraphy for healthy individuals, although this must be confirmed on a larger, clinical population.Keywords: Photoplethysmography, sleep tracker, actigraphy, computerized analysis, heart rate variability, scoring, statistics.Topic: middle-aged adult, photoplethysmography, polysomnography, sleep stages, sleep, epoch protocol, actigraphy

U2 - 10.1093/sleep/zsx097

DO - 10.1093/sleep/zsx097

M3 - Article

VL - 40

JO - Sleep

T2 - Sleep

JF - Sleep

SN - 0161-8105

IS - 7

M1 - zsx097

ER -