Abstract The application of Artificial Intelligence (AI) in assisting individuals with autism spectrum disorder (ASD) has gained significant attention in recent years. However, existing studies exhibit notable differences in their objectives, targeted populations, and methodological approaches. This systematic literature review (SLR) followed the widely recognized guidelines of Kitchenham and Charters and the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement, resulting in a final selection of 21 studies. The review aims to provide a comprehensive analysis of AI-driven solutions designed to support individuals with ASD. The review examines key aspects such as the age and severity level of the target population, the specific objectives of AI-based solutions, the employed technologies, the methods used to assess their effectiveness, and the challenges faced in their implementation. A comparative analysis of existing SLRs highlights gaps in current research, including the lack of standardized evaluation metrics and the limited focus on personalized, real-world applications. Findings indicate that most AI-based interventions prioritize improving social and communication skills, especially in children, whereas significantly fewer solutions focus on assisting with daily tasks to enhance independence, particularly in adults. While AI technologies such as machine learning, natural language processing, and virtual agents offer promising avenues for assistance, ethical considerations, accessibility constraints, and adaptation to individual needs remain critical challenges. This review provides a structured synthesis of the state-of-the-art in AI-assisted interventions for ASD, offering insights into future research directions aimed at developing more inclusive and effective support systems.
Heras et al. (Wed,) studied this question.