Artificial Intelligence in the Detection of Autism Spectrum Disorders (ASD): a Systematic Review

The growth and optimization of different algorithms applied within Artificial Intelligence (AI) has allowed the creation of several fields of research, one of the most revolutionary being artificial vision techniques and neural networks related to autism spectrum disorder (ASD). This systematic review focused on identifying key approaches in autism research in children using these technologies. After applying the PRISMA protocol, 28 studies were selected from the Web of Science and Scopus databases (2018–2023). The results highlight the relevance of AI for diagnosis and support in ASD, addressing from early detection based on nonverbal, verbal and brain cues, to the assessment of socioemotional development and the creation of tools to study ASD in children. Future directions focused on early detection and social-emotional development of children with ASD using AI applications are explored.