Diagnostic shifts in autism spectrum disorder can be linked to the fuzzy nature of the diagnostic boundary: a data-driven approach.
Autism spectrum disorders
diagnosis
infancy
machine learning
stability
Journal
Journal of child psychology and psychiatry, and allied disciplines
ISSN: 1469-7610
Titre abrégé: J Child Psychol Psychiatry
Pays: England
ID NLM: 0375361
Informations de publication
Date de publication:
10 2021
10 2021
Historique:
accepted:
06
01
2021
pubmed:
8
4
2021
medline:
27
10
2021
entrez:
7
4
2021
Statut:
ppublish
Résumé
Diagnostic shifts at early ages may provide invaluable insights into the nature of separation between autism spectrum disorder (ASD) and typical development. Recent conceptualizations of ASD suggest the condition is only fuzzily separated from non-ASD, with intermediate cases between the two. These intermediate cases may shift along a transition region over time, leading to apparent instability of diagnosis. We used a cohort of children with high ASD risk, by virtue of having an older sibling with ASD, assessed at 24 months (N = 212) and 36 months (N = 191). We applied machine learning to empirically characterize the classification boundary between ASD and non-ASD, using variables quantifying developmental and adaptive skills. We computed the distance of children to the classification boundary. Children who switched diagnostic labels from 24 to 36 months, in both directions, (dynamic group) had intermediate phenotypic profiles. They were closer to the classification boundary compared to children who had stable diagnoses, both at 24 months (Cohen's d = .52) and at 36 months (d = .75). The magnitude of change in distance between the two time points was similar for the dynamic and stable groups (Cohen's d = .06), and diagnostic shifts were not associated with a large change. At the individual level, a few children in the dynamic group showed substantial change. Our results suggested that a diagnostic shift was largely due to a slight movement within a transition region between ASD and non-ASD. This fact highlights the need for more vigilant surveillance and intervention strategies. Young children with intermediate phenotypes may have an increased susceptibility to gain or lose their diagnosis at later ages, calling attention to the inherently dynamic nature of early ASD diagnoses.
Sections du résumé
BACKGROUND
Diagnostic shifts at early ages may provide invaluable insights into the nature of separation between autism spectrum disorder (ASD) and typical development. Recent conceptualizations of ASD suggest the condition is only fuzzily separated from non-ASD, with intermediate cases between the two. These intermediate cases may shift along a transition region over time, leading to apparent instability of diagnosis.
METHODS
We used a cohort of children with high ASD risk, by virtue of having an older sibling with ASD, assessed at 24 months (N = 212) and 36 months (N = 191). We applied machine learning to empirically characterize the classification boundary between ASD and non-ASD, using variables quantifying developmental and adaptive skills. We computed the distance of children to the classification boundary.
RESULTS
Children who switched diagnostic labels from 24 to 36 months, in both directions, (dynamic group) had intermediate phenotypic profiles. They were closer to the classification boundary compared to children who had stable diagnoses, both at 24 months (Cohen's d = .52) and at 36 months (d = .75). The magnitude of change in distance between the two time points was similar for the dynamic and stable groups (Cohen's d = .06), and diagnostic shifts were not associated with a large change. At the individual level, a few children in the dynamic group showed substantial change.
CONCLUSIONS
Our results suggested that a diagnostic shift was largely due to a slight movement within a transition region between ASD and non-ASD. This fact highlights the need for more vigilant surveillance and intervention strategies. Young children with intermediate phenotypes may have an increased susceptibility to gain or lose their diagnosis at later ages, calling attention to the inherently dynamic nature of early ASD diagnoses.
Identifiants
pubmed: 33826159
doi: 10.1111/jcpp.13406
pmc: PMC8601115
mid: NIHMS1754658
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
1236-1245Subventions
Organisme : NIMH NIH HHS
ID : K01 MH122779
Pays : United States
Organisme : NICHD NIH HHS
ID : R01 HD088125
Pays : United States
Organisme : NICHD NIH HHS
ID : P50 HD105354
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH121462
Pays : United States
Organisme : NIH HHS
ID : S10 OD023495
Pays : United States
Organisme : NIEHS NIH HHS
ID : R01 ES026961
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH073084
Pays : United States
Organisme : NICHD NIH HHS
ID : R01 HD055741
Pays : United States
Organisme : NICHD NIH HHS
ID : U54 HD087011
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH116961
Pays : United States
Organisme : NICHD NIH HHS
ID : U54 HD086984
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH117807
Pays : United States
Organisme : NIMH NIH HHS
ID : R01 MH118362
Pays : United States
Informations de copyright
© 2021 Association for Child and Adolescent Mental Health.
Références
IEEE Trans Pattern Anal Mach Intell. 1979 Feb;1(2):224-7
pubmed: 21868852
J Neurodev Disord. 2015;7(1):24
pubmed: 26203305
J Am Acad Child Adolesc Psychiatry. 2018 Nov;57(11):849-857.e2
pubmed: 30392626
Neurosci Biobehav Rev. 2014 Feb;39:1-33
pubmed: 24361967
Mol Autism. 2016 Jan 21;7:10
pubmed: 26798446
Am J Psychiatry. 2012 Jun;169(6):601-8
pubmed: 22684595
J Am Acad Child Adolesc Psychiatry. 2014 Dec;53(12):1317-1327.e1
pubmed: 25457930
J Autism Dev Disord. 2009 May;39(5):693-705
pubmed: 19082876
Autism Res. 2008 Dec;1(6):320-8
pubmed: 19360687
J Am Acad Child Adolesc Psychiatry. 2018 Nov;57(11):837-848.e2
pubmed: 30392625
J Child Psychol Psychiatry. 2017 May;58(5):634-636
pubmed: 28414862
Nat Med. 2020 Sep;26(9):1375-1379
pubmed: 32778826
Autism Res. 2017 Jan;10(1):169-178
pubmed: 27417857
J Neurodev Disord. 2020 Feb 5;12(1):5
pubmed: 32024459
J Am Acad Child Adolesc Psychiatry. 2014 Apr;53(4):398-407.e2
pubmed: 24655649
J Am Acad Child Adolesc Psychiatry. 2018 Nov;57(11):822-823
pubmed: 30392621
J Child Psychol Psychiatry. 2015 Sep;56(9):988-98
pubmed: 25921776
J Appl Psychol. 2014 Mar;99(2):332-40
pubmed: 24188393
Neuroimage. 2016 Jan 1;124(Pt B):1188-1195
pubmed: 26364860
Pediatrics. 2012 May;129(5):e1112-20
pubmed: 22473372
Autism Res. 2016 Jul;9(7):790-800
pubmed: 26613202
JAMA Psychiatry. 2015 Mar;72(3):276-83
pubmed: 25629657
Autism Res. 2020 Mar;13(3):464-473
pubmed: 31868321
Pediatrics. 2009 May;123(5):1383-91
pubmed: 19403506
Front Psychiatry. 2020 Feb 19;11:60
pubmed: 32140115
JAMA Pediatr. 2019 Jun 1;173(6):578-587
pubmed: 31034004