AI-Based Diagnostic Techniques for Children with Autism Spectrum Disorder: Current Practices and Emerging Trends

Abstract

This research investigated the application of AI-based diagnostic tools for children with autism spectrum disorder (ASD), with a primary focus on existing methods advantages challenges, and recent developments. A quantitative descriptive survey design was chosen, and a total of 350 professionals after special education teachers, psychologists, speech therapists, pediatricians, and therapists working in autism-related fields were surveyed for data collection. A structured questionnaire with demographic variables and 40 research items was prepared by the researcher. Data analysis was done through descriptive and inferential statistics like frequency percentage, independent samples t-test, one-way ANOVA, and reliability analysis. The results revealed that overall, the respondents' perceptions of AI-based diagnostic methods were very positive, especially regarding their role in facilitating early detection, enhancing efficiency, and aiding decision-making in ASD diagnosis. Significant variations were noted among the groups of selected demographic characteristics and training-related aspects. This paper argues that AI-based diagnostic methods may be considered as helpful adjuncts, under the guidance of a professional, in the diagnosis of ASD in children.