Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study.

autism autism spectrum disorder behavior challenging behaviors disorder efficacy engagement impact machine learning retrospective subtypes treatment treatment response unsupervised machine learning

Journal

JMIR medical informatics
ISSN: 2291-9694
Titre abrégé: JMIR Med Inform
Pays: Canada
ID NLM: 101645109

Informations de publication

Date de publication:
02 Jun 2021
Historique:
received: 06 02 2021
accepted: 29 04 2021
revised: 23 04 2021
entrez: 2 6 2021
pubmed: 3 6 2021
medline: 3 6 2021
Statut: epublish

Résumé

Challenging behaviors are prevalent among individuals with autism spectrum disorder; however, research exploring the impact of challenging behaviors on treatment response is lacking. The purpose of this study was to identify types of autism spectrum disorder based on engagement in different challenging behaviors and evaluate differences in treatment response between groups. Retrospective data on challenging behaviors and treatment progress for 854 children with autism spectrum disorder were analyzed. Participants were clustered based on 8 observed challenging behaviors using k means, and multiple linear regression was performed to test interactions between skill mastery and treatment hours, cluster assignment, and gender. Seven clusters were identified, which demonstrated a single dominant challenging behavior. For some clusters, significant differences in treatment response were found. Specifically, a cluster characterized by low levels of stereotypy was found to have significantly higher levels of skill mastery than clusters characterized by self-injurious behavior and aggression (P<.003). These findings have implications on the treatment of individuals with autism spectrum disorder. Self-injurious behavior and aggression were prevalent among participants with the worst treatment response, thus interventions targeting these challenging behaviors may be worth prioritizing. Furthermore, the use of unsupervised machine learning models to identify types of autism spectrum disorder shows promise.

Sections du résumé

BACKGROUND BACKGROUND
Challenging behaviors are prevalent among individuals with autism spectrum disorder; however, research exploring the impact of challenging behaviors on treatment response is lacking.
OBJECTIVE OBJECTIVE
The purpose of this study was to identify types of autism spectrum disorder based on engagement in different challenging behaviors and evaluate differences in treatment response between groups.
METHODS METHODS
Retrospective data on challenging behaviors and treatment progress for 854 children with autism spectrum disorder were analyzed. Participants were clustered based on 8 observed challenging behaviors using k means, and multiple linear regression was performed to test interactions between skill mastery and treatment hours, cluster assignment, and gender.
RESULTS RESULTS
Seven clusters were identified, which demonstrated a single dominant challenging behavior. For some clusters, significant differences in treatment response were found. Specifically, a cluster characterized by low levels of stereotypy was found to have significantly higher levels of skill mastery than clusters characterized by self-injurious behavior and aggression (P<.003).
CONCLUSIONS CONCLUSIONS
These findings have implications on the treatment of individuals with autism spectrum disorder. Self-injurious behavior and aggression were prevalent among participants with the worst treatment response, thus interventions targeting these challenging behaviors may be worth prioritizing. Furthermore, the use of unsupervised machine learning models to identify types of autism spectrum disorder shows promise.

Identifiants

pubmed: 34076577
pii: v9i6e27793
doi: 10.2196/27793
pmc: PMC8209527
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e27793

Informations de copyright

©Julie Gardner-Hoag, Marlena Novack, Chelsea Parlett-Pelleriti, Elizabeth Stevens, Dennis Dixon, Erik Linstead. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 02.06.2021.

Références

Transl Psychiatry. 2017 Sep 19;7(9):e1234
pubmed: 28925999
JAMA. 2015 Apr 21;313(15):1524-33
pubmed: 25898050
Am J Ment Retard. 2007 Nov;112(6):418-38
pubmed: 17963434
Int J Med Inform. 2019 Sep;129:29-36
pubmed: 31445269
Behav Modif. 2007 May;31(3):264-78
pubmed: 17438342
J Intellect Disabil Res. 2003 Nov;47(Pt 8):622-7
pubmed: 14641810
Ann Clin Psychiatry. 2009 Jul-Sep;21(3):162-73
pubmed: 19758537
Autism. 2009 Nov;13(6):613-33
pubmed: 19933766
J Clin Child Adolesc Psychol. 2009 May;38(3):439-50
pubmed: 19437303
Pediatrics. 2016 Feb;137 Suppl 2:S167-75
pubmed: 26908472
J Intellect Disabil Res. 2006 Mar;50(Pt 3):172-83
pubmed: 16430729
Clin Psychol Rev. 2010 Jun;30(4):387-99
pubmed: 20223569
Res Dev Disabil. 2014 Oct;35(10):2463-76
pubmed: 24992447
Res Dev Disabil. 2003 Mar-Apr;24(2):120-38
pubmed: 12623082
J Autism Dev Disord. 2012 Apr;42(4):512-20
pubmed: 21404083
J Am Acad Child Adolesc Psychiatry. 2009 Dec;48(12):1143-54
pubmed: 19858761
Behav Modif. 2017 Mar;41(2):229-252
pubmed: 27651097
Am J Ment Retard. 2006 Jul;111(4):290-8
pubmed: 16792430
Am J Med Genet C Semin Med Genet. 2015 Jun;169(2):198-208
pubmed: 25959391
N Am J Med Sci (Boston). 2013;6(3):
pubmed: 24363828
J Intellect Disabil Res. 2008 Oct;52(10):819-29
pubmed: 18444989
J Am Acad Child Adolesc Psychiatry. 2000 Mar;39(3):346-52
pubmed: 10714055
J Child Psychol Psychiatry. 2014 Dec;55(12):1354-62
pubmed: 24889883
J Clin Child Adolesc Psychol. 2015;44(6):897-922
pubmed: 26430947
Child Neuropsychol. 2006 Aug;12(4-5):247-67
pubmed: 16911971
J Autism Dev Disord. 2012 Feb;42(2):210-20
pubmed: 21472360
J Child Psychol Psychiatry. 2007 Aug;48(8):803-12
pubmed: 17683452
Behav Modif. 2002 Jan;26(1):49-68
pubmed: 11799654
Res Dev Disabil. 2007 Nov-Dec;28(6):567-79
pubmed: 16973329
Genes Brain Behav. 2014 Mar;13(3):276-85
pubmed: 24373520
Am J Intellect Dev Disabil. 2010 Sep;115(5):381-405
pubmed: 20687823
Res Dev Disabil. 2007 May-Jun;28(3):287-303
pubmed: 16730944
J Clin Child Adolesc Psychol. 2008 Jan;37(1):8-38
pubmed: 18444052
PLoS One. 2010 May 28;5(5):e10887
pubmed: 20526357
Am J Intellect Dev Disabil. 2009 Jan;114(1):23-41
pubmed: 19143460
J Autism Dev Disord. 2001 Aug;31(4):411-22
pubmed: 11569587

Auteurs

Julie Gardner-Hoag (J)

Schmid College of Science and Technology, Chapman University, Orange, CA, United States.

Marlena Novack (M)

Center for Autism and Related Disorders, Woodland Hills, CA, United States.

Chelsea Parlett-Pelleriti (C)

Fowler School of Engineering, Chapman University, Orange, CA, United States.

Elizabeth Stevens (E)

Fowler School of Engineering, Chapman University, Orange, CA, United States.

Dennis Dixon (D)

Center for Autism and Related Disorders, Woodland Hills, CA, United States.

Erik Linstead (E)

Fowler School of Engineering, Chapman University, Orange, CA, United States.

Classifications MeSH