Abstract
Autism spectrum disorder (ASD) is a neuropsychiatric disorder associated with significant social, communication, and behavioral challenges. Neither the cause nor the cure of ASD is clearly understood. Several studies suggested machine-learning (ML) for quick and accurate identification and diagnosis of ASD. Despite limited evidence on the real-life implementation of the ML-based models, studies have demonstrated ML-based assessment of ASD using functional magnetic resonance imaging, eye tracking, genetic, behavioral data, and among others. However, there are numerous challenges identified in the previous studies. Particularly, despite the promising results reported on ML models for behavioral assessment of ASD, there is little evidence of real-life implementation of the ML models. Accordingly, challenges related to the misalignments of the data-centric techniques employed in the previous studies and the concepts upon which professionals assess ASD limit real-life implementation of the resulting models. This chapter guides toward the development of ML-based ASD screening and diagnostic systems that will leverage the potential of ML and preserve the clinical relevance of the assessment instrument. This chapter will also serve as a guide to researchers, neuropsychiatrists, and relevant stakeholders on the advances in ASD assessment with ML.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Neural Engineering Techniques for Autism Spectrum Disorder, Volume 2
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.