Skip to Main content Skip to Navigation
Journal articles

From pattern classification to stratification: towards conceptualizing the heterogeneity of Autism Spectrum Disorder

Thomas Wolfers 1, 2, * Dorothea Floris 1, 2 Richard Dinga 3 Daan van Rooij 1, 2 Christina Isakoglou 1, 2 Seyed Mostafa Kia 1, 2 Mariam Zabihi 2, 1 Alberto Llera 2, 1 Rajanikanth Chowdanayaka 4 Vinod Kumar 5 Han Peng 6, 1 Charles Laidi 7 Dafnis Batalle 8 Ralica Dimitrova 8 Tony Charman 8 Eva Loth 8 Meng-Chuan Lai 9, 10, 11 Emily Jones 12 Sarah Baumeister 13, 14 Carolin Moessnang 13, 14 Tobias Banaschewski 14, 13 Christine Ecker 8, 15 Guillaume Dumas 16 Jonathan O'Muircheartaigh 8, 17 Declan Murphy 8, 17 Jan Buitelaar 1, 2 Andre Marquand 2, 1 Christian Beckmann 2, 1, 6
* Corresponding author
1 Donders Institute for Brain, Cognition and Behaviour
2 Radboud University Medical Center [Nijmegen]
3 AMC - Academic Medical Center - Academisch Medisch Centrum [Amsterdam]
4 University of Mysore
5 Max Planck Institute for Biological Cybernetics
6 FMRIB - Oxford Centre for Functional Magnetic Resonance Imaging of the Brain
7 IMRB - Institut Mondor de Recherche Biomédicale
8 Institute of Psychiatry, Psychology & Neuroscience, King's College London
9 University of Toronto
10 CAM - University of Cambridge [UK]
11 NTU - National Taiwan University [Taiwan]
12 Centre for Brain and Cognitive Development [Birkbeck College]
13 Universität Heidelberg [Heidelberg]
14 Medizinische Fakultät Mannheim
15 Goethe-University Frankfurt am Main
16 GHFC (UMR_3571 / U-Pasteur_1) - Génétique humaine et fonctions cognitives - Human Genetics and Cognitive Functions
17 King‘s College London
Abstract : Pattern classification and stratification approaches have increasingly been used in research on Autism Spectrum Disorder (ASD) over the last ten years with the goal of translation towards clinical applicability. Here, we present an extensive scoping literature review on those two approaches. We screened a total of 635 studies, of which 57 pattern classification and 19 stratification studies were included. We observed large variance across pattern classification studies in terms of predictive performance from about 60% to 98% accuracy, which is among other factors likely linked to sampling bias, different validation procedures across studies, the heterogeneity of ASD and differences in data quality. Stratification studies were less prevalent with only two studies reporting replications and just a few showing external validation. While some identified strata based on cognition and intelligence reappear across studies, biology as a stratification marker is clearly underexplored. In summary, mapping biological differences at the level of the individual with ASD is a major challenge for the field now. Conceptualizing those mappings and individual trajectories that lead to the diagnosis of ASD, will become a major challenge in the near future.
Keywords : Autism spectrum disorder Biotypes Classification Clustering Machine learning Pattern recognition Precision medicine Stratification
Document type :
Journal articles
Complete list of metadata
https://hal-pasteur.archives-ouvertes.fr/pasteur-02398512
Contributor : Guillaume Dumas Connect in order to contact the contributor
Submitted on : Saturday, December 7, 2019 - 4:07:35 PM
Last modification on : Tuesday, October 19, 2021 - 10:28:20 PM

Links full text

openaccess

Identifiers

Collections

PASTEUR | IMRB | UPEC-UPEM | UPEC | INSERM | UNIV-PARIS7 | USPC | CNRS | UNIV-PARIS | UP-SCIENCES

Citation

Thomas Wolfers, Dorothea Floris, Richard Dinga, Daan van Rooij, Christina Isakoglou, et al.. From pattern classification to stratification: towards conceptualizing the heterogeneity of Autism Spectrum Disorder. Neuroscience and Biobehavioral Reviews, Elsevier, 2019, 104, pp.240-254. ⟨10.1016/j.neubiorev.2019.07.010⟩. ⟨pasteur-02398512⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Les métriques sont temporairement indisponibles