Abstract

Since the U.S. Centers for Disease Control and Prevention began tracking the prevalence of autism spectrum disorder (ASD) over twenty years ago, rates have tripled, with an estimated one in 44 children now receiving a diagnosis [1]. Early ASD diagnosis and intervention during the critical neurodevelopmental window is recommended to enhance long-term outcomes [2-4]; yet many families experience diagnostic delays and challenges accessing services. Diagnostic barriers include long waits for specialist assessment, lengthy and fragmented evaluation processes, and limited primary care diagnostic capacity. Race, ethnicity, gender, geography, and socioeconomic status contribute to further delays for some populations [5-8]. Even after an ASD diagnosis is received, health services may struggle to fund and deliver targeted and timely interventions to the rapidly growing number of children requiring treatment. Data driven approaches to scale, streamline and enhance the quality of diagnostic and therapeutic ASD care available to families are urgently required. This narrative literature review considers the practice change potential of one such approach: Artificial Intelligence (AI) applied to the field of ASD. After providing a brief overview of AI in healthcare, we review a number of ASD specific AI-based approaches and consider their potential to augment current ASD diagnostic or treatment pathways. Key challenges associated with integrating AIbased technologies into clinical practice are also considered.