Sleep patterns predictive of daytime challenging behavior in individuals with low-functioning autism

Simonne Cohen, Ben D. Fulcher, Shantha M. W. Rajaratnam, Russell Conduit, Jason P. Sullivan, Melissa A. St Hilaire, Andrew J. K. Phillips, Tobias Loddenkemper, Sanjeev V. Kothare, Kelly McConnell, Paula Braga-Kenyon, William Ahearn, Andrew Shlesinger, Jacqueline Potter, Frank Bird, Kim M. Cornish, Steven W. Lockley

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Increased severity of problematic daytime behavior has been associated with poorer sleep quality in individuals with autism spectrum disorder. In this work, we investigate whether this relationship holds in a real-time setting, such that an individual's prior sleep can be used to predict their subsequent daytime behavior. We analyzed an extensive real-world dataset containing over 20,000 nightly sleep observations matched to subsequent challenging daytime behaviors (aggression, self-injury, tantrums, property destruction and a challenging behavior index) across 67 individuals with low-functioning autism living in two U.S. residential facilities. Using support vector machine classifiers, a statistically significant predictive relationship was found in 81% of individuals studied (P < 0.05). For all five behaviors examined, prediction accuracy increased up to approximately eight nights of prior sleep used to make the prediction, indicating that the behavioral effects of sleep may manifest on extended timescales. Accurate prediction was most strongly driven by sleep variability measures, highlighting the importance of regular sleep patterns. Our findings constitute an initial step towards the development of a real-time monitoring tool to pre-empt behavioral episodes and guide prophylactic treatment for individuals with autism. Autism Res 2018, 11: 391–403.

Original languageEnglish
Pages (from-to)391-403
Number of pages13
JournalAutism Research
Volume11
Issue number2
DOIs
Publication statusPublished - 1 Feb 2018

Keywords

  • autism spectrum disorder
  • challenging behavior
  • intellectual disability
  • machine learning
  • sleep

Cite this

Cohen, Simonne ; Fulcher, Ben D. ; Rajaratnam, Shantha M. W. ; Conduit, Russell ; Sullivan, Jason P. ; St Hilaire, Melissa A. ; Phillips, Andrew J. K. ; Loddenkemper, Tobias ; Kothare, Sanjeev V. ; McConnell, Kelly ; Braga-Kenyon, Paula ; Ahearn, William ; Shlesinger, Andrew ; Potter, Jacqueline ; Bird, Frank ; Cornish, Kim M. ; Lockley, Steven W. / Sleep patterns predictive of daytime challenging behavior in individuals with low-functioning autism. In: Autism Research. 2018 ; Vol. 11, No. 2. pp. 391-403.
@article{5ff24bbaacc2493ca5b056a1be215f8f,
title = "Sleep patterns predictive of daytime challenging behavior in individuals with low-functioning autism",
abstract = "Increased severity of problematic daytime behavior has been associated with poorer sleep quality in individuals with autism spectrum disorder. In this work, we investigate whether this relationship holds in a real-time setting, such that an individual's prior sleep can be used to predict their subsequent daytime behavior. We analyzed an extensive real-world dataset containing over 20,000 nightly sleep observations matched to subsequent challenging daytime behaviors (aggression, self-injury, tantrums, property destruction and a challenging behavior index) across 67 individuals with low-functioning autism living in two U.S. residential facilities. Using support vector machine classifiers, a statistically significant predictive relationship was found in 81{\%} of individuals studied (P < 0.05). For all five behaviors examined, prediction accuracy increased up to approximately eight nights of prior sleep used to make the prediction, indicating that the behavioral effects of sleep may manifest on extended timescales. Accurate prediction was most strongly driven by sleep variability measures, highlighting the importance of regular sleep patterns. Our findings constitute an initial step towards the development of a real-time monitoring tool to pre-empt behavioral episodes and guide prophylactic treatment for individuals with autism. Autism Res 2018, 11: 391–403.",
keywords = "autism spectrum disorder, challenging behavior, intellectual disability, machine learning, sleep",
author = "Simonne Cohen and Fulcher, {Ben D.} and Rajaratnam, {Shantha M. W.} and Russell Conduit and Sullivan, {Jason P.} and {St Hilaire}, {Melissa A.} and Phillips, {Andrew J. K.} and Tobias Loddenkemper and Kothare, {Sanjeev V.} and Kelly McConnell and Paula Braga-Kenyon and William Ahearn and Andrew Shlesinger and Jacqueline Potter and Frank Bird and Cornish, {Kim M.} and Lockley, {Steven W.}",
year = "2018",
month = "2",
day = "1",
doi = "10.1002/aur.1899",
language = "English",
volume = "11",
pages = "391--403",
journal = "Autism Research",
issn = "1939-3792",
publisher = "Wiley-Blackwell",
number = "2",

}

Cohen, S, Fulcher, BD, Rajaratnam, SMW, Conduit, R, Sullivan, JP, St Hilaire, MA, Phillips, AJK, Loddenkemper, T, Kothare, SV, McConnell, K, Braga-Kenyon, P, Ahearn, W, Shlesinger, A, Potter, J, Bird, F, Cornish, KM & Lockley, SW 2018, 'Sleep patterns predictive of daytime challenging behavior in individuals with low-functioning autism' Autism Research, vol. 11, no. 2, pp. 391-403. https://doi.org/10.1002/aur.1899

Sleep patterns predictive of daytime challenging behavior in individuals with low-functioning autism. / Cohen, Simonne; Fulcher, Ben D.; Rajaratnam, Shantha M. W.; Conduit, Russell; Sullivan, Jason P.; St Hilaire, Melissa A.; Phillips, Andrew J. K.; Loddenkemper, Tobias; Kothare, Sanjeev V.; McConnell, Kelly; Braga-Kenyon, Paula; Ahearn, William; Shlesinger, Andrew; Potter, Jacqueline; Bird, Frank; Cornish, Kim M.; Lockley, Steven W.

In: Autism Research, Vol. 11, No. 2, 01.02.2018, p. 391-403.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Sleep patterns predictive of daytime challenging behavior in individuals with low-functioning autism

AU - Cohen, Simonne

AU - Fulcher, Ben D.

AU - Rajaratnam, Shantha M. W.

AU - Conduit, Russell

AU - Sullivan, Jason P.

AU - St Hilaire, Melissa A.

AU - Phillips, Andrew J. K.

AU - Loddenkemper, Tobias

AU - Kothare, Sanjeev V.

AU - McConnell, Kelly

AU - Braga-Kenyon, Paula

AU - Ahearn, William

AU - Shlesinger, Andrew

AU - Potter, Jacqueline

AU - Bird, Frank

AU - Cornish, Kim M.

AU - Lockley, Steven W.

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Increased severity of problematic daytime behavior has been associated with poorer sleep quality in individuals with autism spectrum disorder. In this work, we investigate whether this relationship holds in a real-time setting, such that an individual's prior sleep can be used to predict their subsequent daytime behavior. We analyzed an extensive real-world dataset containing over 20,000 nightly sleep observations matched to subsequent challenging daytime behaviors (aggression, self-injury, tantrums, property destruction and a challenging behavior index) across 67 individuals with low-functioning autism living in two U.S. residential facilities. Using support vector machine classifiers, a statistically significant predictive relationship was found in 81% of individuals studied (P < 0.05). For all five behaviors examined, prediction accuracy increased up to approximately eight nights of prior sleep used to make the prediction, indicating that the behavioral effects of sleep may manifest on extended timescales. Accurate prediction was most strongly driven by sleep variability measures, highlighting the importance of regular sleep patterns. Our findings constitute an initial step towards the development of a real-time monitoring tool to pre-empt behavioral episodes and guide prophylactic treatment for individuals with autism. Autism Res 2018, 11: 391–403.

AB - Increased severity of problematic daytime behavior has been associated with poorer sleep quality in individuals with autism spectrum disorder. In this work, we investigate whether this relationship holds in a real-time setting, such that an individual's prior sleep can be used to predict their subsequent daytime behavior. We analyzed an extensive real-world dataset containing over 20,000 nightly sleep observations matched to subsequent challenging daytime behaviors (aggression, self-injury, tantrums, property destruction and a challenging behavior index) across 67 individuals with low-functioning autism living in two U.S. residential facilities. Using support vector machine classifiers, a statistically significant predictive relationship was found in 81% of individuals studied (P < 0.05). For all five behaviors examined, prediction accuracy increased up to approximately eight nights of prior sleep used to make the prediction, indicating that the behavioral effects of sleep may manifest on extended timescales. Accurate prediction was most strongly driven by sleep variability measures, highlighting the importance of regular sleep patterns. Our findings constitute an initial step towards the development of a real-time monitoring tool to pre-empt behavioral episodes and guide prophylactic treatment for individuals with autism. Autism Res 2018, 11: 391–403.

KW - autism spectrum disorder

KW - challenging behavior

KW - intellectual disability

KW - machine learning

KW - sleep

UR - http://www.scopus.com/inward/record.url?scp=85036556141&partnerID=8YFLogxK

U2 - 10.1002/aur.1899

DO - 10.1002/aur.1899

M3 - Article

VL - 11

SP - 391

EP - 403

JO - Autism Research

JF - Autism Research

SN - 1939-3792

IS - 2

ER -