Abstract
Autism spectrum disorder (ASD) is associated with significant social, communication, and behavioral challenges. The insufficient number of trained clinicians coupled with limited accessibility to quick and accurate diagnostic tools resulted in overlooking early symptoms of ASD in children around the world. Several studies have utilized behavioral data in developing and evaluating the performance of machine learning (ML) models toward quick and intelligent ASD assessment systems. However, despite the good evaluation metrics achieved by the ML models, there is not enough evidence on the readiness of the models for clinical use. Specifically, none of the existing studies reported the real-life application of the ML-based models. This might be related to numerous challenges associated with the data-centric techniques utilized and their misalignment with the conceptual basis upon which professionals diagnose ASD. The present work systematically reviewed recent articles on the application of ML in the behavioral assessment of ASD, and highlighted common challenges in the studies, and proposed vital considerations for real-life implementation of ML-based ASD screening and diagnostic systems. This review will serve as a guide for researchers, neuropsychiatrists, psychologists, and relevant stakeholders on the advances in ASD screening and diagnosis using ML.
Highlights
IntroductionAccording to the fifth edition of the diagnostic and statistical manual of mental disorders (DSM-5), the primary indicators for diagnosing Autism spectrum disorder (ASD) are deficits in social communication and the manifestation of repetitive and restricted patterns of activities, behavior, or interests [1]
From 2012 to 2018, not so many studies cared about the application of Machine Learning (ML) in Autism spectrum disorder (ASD) assessment
Utilized inputs include the items of screening tools, such as ADI-R and ADOS-G
Summary
According to the fifth edition of the diagnostic and statistical manual of mental disorders (DSM-5), the primary indicators for diagnosing ASD are deficits in social communication and the manifestation of repetitive and restricted patterns of activities, behavior, or interests [1]. Apart from the cost-ineffectiveness of the current diagnostic instruments, studies have indicated the delay of the clinical processes of diagnosing ASD [7,8,9,10]. Addressing these challenges lead to several suggestions, including the so-called quick and accurate Machine Learning (ML)-enabled ASD assessment systems [11,12,13,14]. The promising results realized with ML algorithms across various research fields motivated these suggestions and made it a vital step toward quick and cost-effective assessment of ASD symptoms
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have