Machine learning (ML) for the diagnosis of autism spectrum disorder (ASD) using brain imaging


Creative Commons License

NOĞAY H. S. , Adeli H.

REVIEWS IN THE NEUROSCIENCES, vol.31, no.8, pp.825-841, 2020 (Journal Indexed in SCI) identifier identifier identifier

  • Publication Type: Article / Review
  • Volume: 31 Issue: 8
  • Publication Date: 2020
  • Doi Number: 10.1515/revneuro-2020-0043
  • Title of Journal : REVIEWS IN THE NEUROSCIENCES
  • Page Numbers: pp.825-841
  • Keywords: autism spectrum disorder, classification, feature extraction, machine learning, MRI, ATTENTION-DEFICIT/HYPERACTIVITY DISORDER, FUNCTIONAL CONNECTIVITY, NEURAL-NETWORK, DIGITOPALMAR COMPLEX, SYMPTOM SEVERITY, CRACK DETECTION, CLASSIFICATION, CHILDREN, PREDICTION, MRI

Abstract

Autism spectrum disorder (ASD) is a neuro-developmental incurable disorder with a long diagnostic period encountered in the early years of life. If diagnosed early, the negative effects of this disease can be reduced by starting special education early. Machine learning (ML), an increasingly ubiquitous technology, can be applied for the early diagnosis of ASD. The aim of this study is to examine and provide a comprehensive state-ofthe-art review of ML research for the diagnosis of ASD based on (a) structural magnetic resonance image (MRI), (b) functional MRI and (c) hybrid imaging techniques over the past decade. The accuracy of the studies with a large number of participants is in general lower than those with fewer participants leading to the conclusion that further large-scale studies are needed. An examination of the age of the participants shows that the accuracy of the automated diagnosis of ASD is higher at a younger age range. ML technology is expected to contribute significantly to the early and rapid diagnosis of ASD in the coming years and become available to clinicians in the near future. This review is aimed to facilitate that.