Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities

Alessandro Crippa, Christian Salvatore, Paolo Perego, Sara Forti, Maria Nobile, Massimo Molteni, Isabella Castiglioni

Research output: Contribution to journalArticle

Abstract

In the present work, we have undertaken a proof-of-concept study to determine whether a simple upper-limb movement could be useful to accurately classify low-functioning children with autism spectrum disorder (ASD) aged 2–4. To answer this question, we developed a supervised machine-learning method to correctly discriminate 15 preschool children with ASD from 15 typically developing children by means of kinematic analysis of a simple reach-to-drop task. Our method reached a maximum classification accuracy of 96.7 % with seven features related to the goal-oriented part of the movement. These preliminary findings offer insight into a possible motor signature of ASD that may be potentially useful in identifying a well-defined subset of patients, reducing the clinical heterogeneity within the broad behavioral phenotype.

Original languageEnglish
Pages (from-to)2146-2156
Number of pages11
JournalJournal of Autism and Developmental Disorders
Volume45
Issue number7
DOIs
Publication statusPublished - Jul 19 2015

Keywords

  • Autism spectrum disorder
  • Classification
  • Kinematics
  • Machine learning
  • Support vector machines

ASJC Scopus subject areas

  • Developmental and Educational Psychology
  • Medicine(all)

Fingerprint Dive into the research topics of 'Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities'. Together they form a unique fingerprint.

  • Cite this