Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep

Andrew McDowell, Mark Donnelly, Chris Nugent, Michael McGrath

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Sleep problems can have a major impact on cognitive function, particularly in older adults who are also more likely to have a clinically diagnosed cognitive impairment. While several approved methods for sleep disturbance exist, most are not suitable for use within the abovementioned population. Often the reason for this is due to the symptoms associated with cognitive impairment or for the invasiveness of some sleep profiling methods. Developed from current sleep actigraphy techniques, this paper presents a non-contact alternative method for sleep profiling that is deemed to be more suitable for long term monitoring in the older population than current clinically approved techniques. This first evaluation has been conducted with a young control group in order to validate the approach. The results have demonstrated that based on the approach a random forest classifier using features calculated from optimally placed static accelerometers can produce a sleep/wake classification accuracy of 92%.
LanguageEnglish
Title of host publicationImpact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science
Place of PublicationArtimino, Italy
Pages157-164
Volume7251
DOIs
Publication statusPublished - 2012

Fingerprint

Monitoring
Accelerometers
Sleep
Classifiers

Cite this

McDowell, A., Donnelly, M., Nugent, C., & McGrath, M. (2012). Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep. In Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science (Vol. 7251, pp. 157-164). Artimino, Italy. https://doi.org/10.1007/978-3-642-30779-9_20
McDowell, Andrew ; Donnelly, Mark ; Nugent, Chris ; McGrath, Michael. / Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep. Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science. Vol. 7251 Artimino, Italy, 2012. pp. 157-164
@inbook{3a980c1b3a53422abe1ef1d1c7b5c6be,
title = "Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep",
abstract = "Sleep problems can have a major impact on cognitive function, particularly in older adults who are also more likely to have a clinically diagnosed cognitive impairment. While several approved methods for sleep disturbance exist, most are not suitable for use within the abovementioned population. Often the reason for this is due to the symptoms associated with cognitive impairment or for the invasiveness of some sleep profiling methods. Developed from current sleep actigraphy techniques, this paper presents a non-contact alternative method for sleep profiling that is deemed to be more suitable for long term monitoring in the older population than current clinically approved techniques. This first evaluation has been conducted with a young control group in order to validate the approach. The results have demonstrated that based on the approach a random forest classifier using features calculated from optimally placed static accelerometers can produce a sleep/wake classification accuracy of 92{\%}.",
author = "Andrew McDowell and Mark Donnelly and Chris Nugent and Michael McGrath",
year = "2012",
doi = "10.1007/978-3-642-30779-9_20",
language = "English",
isbn = "978-3-642-30778-2",
volume = "7251",
pages = "157--164",
booktitle = "Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science",

}

McDowell, A, Donnelly, M, Nugent, C & McGrath, M 2012, Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep. in Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science. vol. 7251, Artimino, Italy, pp. 157-164. https://doi.org/10.1007/978-3-642-30779-9_20

Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep. / McDowell, Andrew; Donnelly, Mark; Nugent, Chris; McGrath, Michael.

Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science. Vol. 7251 Artimino, Italy, 2012. p. 157-164.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep

AU - McDowell, Andrew

AU - Donnelly, Mark

AU - Nugent, Chris

AU - McGrath, Michael

PY - 2012

Y1 - 2012

N2 - Sleep problems can have a major impact on cognitive function, particularly in older adults who are also more likely to have a clinically diagnosed cognitive impairment. While several approved methods for sleep disturbance exist, most are not suitable for use within the abovementioned population. Often the reason for this is due to the symptoms associated with cognitive impairment or for the invasiveness of some sleep profiling methods. Developed from current sleep actigraphy techniques, this paper presents a non-contact alternative method for sleep profiling that is deemed to be more suitable for long term monitoring in the older population than current clinically approved techniques. This first evaluation has been conducted with a young control group in order to validate the approach. The results have demonstrated that based on the approach a random forest classifier using features calculated from optimally placed static accelerometers can produce a sleep/wake classification accuracy of 92%.

AB - Sleep problems can have a major impact on cognitive function, particularly in older adults who are also more likely to have a clinically diagnosed cognitive impairment. While several approved methods for sleep disturbance exist, most are not suitable for use within the abovementioned population. Often the reason for this is due to the symptoms associated with cognitive impairment or for the invasiveness of some sleep profiling methods. Developed from current sleep actigraphy techniques, this paper presents a non-contact alternative method for sleep profiling that is deemed to be more suitable for long term monitoring in the older population than current clinically approved techniques. This first evaluation has been conducted with a young control group in order to validate the approach. The results have demonstrated that based on the approach a random forest classifier using features calculated from optimally placed static accelerometers can produce a sleep/wake classification accuracy of 92%.

U2 - 10.1007/978-3-642-30779-9_20

DO - 10.1007/978-3-642-30779-9_20

M3 - Chapter

SN - 978-3-642-30778-2

VL - 7251

SP - 157

EP - 164

BT - Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science

CY - Artimino, Italy

ER -

McDowell A, Donnelly M, Nugent C, McGrath M. Passive Sleep Actigraphy: Evaluating a Non-contact Method of Monitoring Sleep. In Impact Analysis of Solutions for Chronic Disease Prevention and Management, Lecture Notes in Computer Science. Vol. 7251. Artimino, Italy. 2012. p. 157-164 https://doi.org/10.1007/978-3-642-30779-9_20