Computerized Assessment of Motor Imitation as a Scalable Method for Distinguishing Children With Autism.
Autism
Imitation
Intervention
Machine learning
Motor learning
Social behavior
Journal
Biological psychiatry. Cognitive neuroscience and neuroimaging
ISSN: 2451-9030
Titre abrégé: Biol Psychiatry Cogn Neurosci Neuroimaging
Pays: United States
ID NLM: 101671285
Informations de publication
Date de publication:
03 2021
03 2021
Historique:
received:
18
06
2020
revised:
02
09
2020
accepted:
02
09
2020
pubmed:
25
11
2020
medline:
4
6
2021
entrez:
24
11
2020
Statut:
ppublish
Résumé
Imitation deficits are prevalent in autism spectrum conditions (ASCs) and are associated with core autistic traits. Imitating others' actions is central to the development of social skills in typically developing populations, as it facilitates social learning and bond formation. We present a Computerized Assessment of Motor Imitation (CAMI) using a brief (1-min), highly engaging video game task. Using Kinect Xbox motion tracking technology, we recorded 48 children (27 with ASCs, 21 typically developing) as they imitated a model's dance movements. We implemented an algorithm based on metric learning and dynamic time warping that automatically detects and evaluates the important joints and returns a score considering spatial position and timing differences between the child and the model. To establish construct validity and reliability, we compared imitation performance measured by the CAMI method to the more traditional human observation coding (HOC) method across repeated trials and two different movement sequences. Results revealed poorer imitation in children with ASCs than in typically developing children (ps < .005), with poorer imitation being associated with increased core autism symptoms. While strong correlations between the CAMI and HOC methods (rs = .69-.87) confirmed the CAMI's construct validity, CAMI scores classified the children into diagnostic groups better than the HOC scores (accuracy Findings support the CAMI as an objective, highly scalable, directly interpretable method for assessing motor imitation differences, providing a promising biomarker for defining biologically meaningful ASC subtypes and guiding intervention.
Sections du résumé
BACKGROUND
Imitation deficits are prevalent in autism spectrum conditions (ASCs) and are associated with core autistic traits. Imitating others' actions is central to the development of social skills in typically developing populations, as it facilitates social learning and bond formation. We present a Computerized Assessment of Motor Imitation (CAMI) using a brief (1-min), highly engaging video game task.
METHODS
Using Kinect Xbox motion tracking technology, we recorded 48 children (27 with ASCs, 21 typically developing) as they imitated a model's dance movements. We implemented an algorithm based on metric learning and dynamic time warping that automatically detects and evaluates the important joints and returns a score considering spatial position and timing differences between the child and the model. To establish construct validity and reliability, we compared imitation performance measured by the CAMI method to the more traditional human observation coding (HOC) method across repeated trials and two different movement sequences.
RESULTS
Results revealed poorer imitation in children with ASCs than in typically developing children (ps < .005), with poorer imitation being associated with increased core autism symptoms. While strong correlations between the CAMI and HOC methods (rs = .69-.87) confirmed the CAMI's construct validity, CAMI scores classified the children into diagnostic groups better than the HOC scores (accuracy
CONCLUSIONS
Findings support the CAMI as an objective, highly scalable, directly interpretable method for assessing motor imitation differences, providing a promising biomarker for defining biologically meaningful ASC subtypes and guiding intervention.
Identifiants
pubmed: 33229247
pii: S2451-9022(20)30252-4
doi: 10.1016/j.bpsc.2020.09.001
pmc: PMC7943651
mid: NIHMS1627863
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
321-328Subventions
Organisme : NICHD NIH HHS
ID : R01 HD087133
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH106564
Pays : United States
Informations de copyright
Copyright © 2020 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.
Références
Autism Res. 2017 Apr;10(4):648-652
pubmed: 27653620
J Exp Child Psychol. 2008 Nov;101(3):170-85
pubmed: 18572186
Curr Biol. 2013 Apr 8;23(7):R266-8
pubmed: 23578869
Biol Psychiatry. 2016 Apr 15;79(8):633-41
pubmed: 26543004
Autism. 2001 Sep;5(3):317-23
pubmed: 11708590
Front Psychol. 2016 May 13;7:726
pubmed: 27242632
IEEE Trans Neural Syst Rehabil Eng. 2016 Jun;24(6):682-91
pubmed: 26353376
Autism Res. 2014 Jun;7(3):363-80
pubmed: 24863681
Dev Sci. 2009 Jul;12(4):510-20
pubmed: 19635079
Autism Res. 2010 Dec;3(6):311-22
pubmed: 21182208
J Autism Dev Disord. 2015 Jul;45(7):2146-56
pubmed: 25652603
J Exp Child Psychol. 2008 Nov;101(3):186-205
pubmed: 18582895
Front Integr Neurosci. 2012 Dec 13;6:117
pubmed: 23248591
IEEE Trans Affect Comput. 2018 Jan-Mar;9(1):14-20
pubmed: 29963280
IEEE Trans Pattern Anal Mach Intell. 2010 Mar;32(3):569-75
pubmed: 20075479
Child Dev. 2013 Sep-Oct;84(5):1511-8
pubmed: 23488734
PLoS One. 2017 Aug 16;12(8):e0182652
pubmed: 28813454
Br J Psychol. 2010 May;101(Pt 2):311-23
pubmed: 19646328
Neuropsychology. 2012 Mar;26(2):165-71
pubmed: 22288405
Infant Behav Dev. 2012 Dec;35(4):689-96
pubmed: 22986177
Front Integr Neurosci. 2013 Feb 18;7:4
pubmed: 23423608
Dev Sci. 2006 May;9(3):295-302
pubmed: 16669800