Diagnostic Tools for Detecting Autism Spectrum Disorder: A Review

The autism spectrum disorder (ASD) is a developmental disability caused by abnormalities in the brain. Different methods have been used to diagnose ASD in the past, each with its own advantages and disadvantages. Prior research has focused mainly on algorithms and processing methods, rather than identification tools, to improve the automated diagnosis of ASD. This article identifies and describes diagnostic tools in the ASD literature, including facial features, EEG recordings, speech signals, and neuroimaging, in order to assist researchers interested in developing statistical, computational, and sound clinical approaches to ASD data mining. Accordingly, based on the responses obtained, this review study intends to assess several aspects of the key automatic diagnostic tools for autism spectrum disorders, including diagnostic accuracy, privacy protection, uncertainty, cost, efficiency, absence of methodological interference, and prospective clinical and therapeutic conditions.