Immersive simulation interventions for children and adolescents with autism spectrum disorder: technologies, cognitive and socio-emotional development, and AI-driven emotion estimation: a systematic review

Abstract

Virtual Reality (VR) and related immersive technologies are increasingly being explored as innovative intervention tools for children and adolescents with autism spectrum disorder (ASD), offering controlled, repeatable, and engaging environments for skill development. This systematic review synthesizes evidence from 141 studies (2015 –2025) examining the use of immersive technologies, Virtual Reality (VR), Augmented Reality (AR), Mixed Reality (MR), and Extended Reality (XR) for interventions targeting children and adolescents with ASD. The review addresses key research questions regarding participant characteristics, technology types, AI-enabled features, comparator conditions, therapeutic outcomes, and methodological quality. Findings indicate that immersive interventions are predominantly VR-based, with growing integration of AI-driven emotion recognition, adaptive feedback, and multimodal sensing (e.g., eye-tracking, motion capture). Studies report improvements in social-emotional skills, cognitive abilities, daily living skills, motor coordination, and adaptive behaviors, with quantitative gains frequently evidenced by large effect sizes (e.g., d > 0.5) and machine-learning models achieving up to 97% accuracy in emotion recognition, though evidence is often limited by small sample sizes, non-randomized designs, and inconsistent outcome reporting. Geographically, research is concentrated in North America, Europe, and parts of Asia, highlighting global disparities in access and implementation. The review identifies significant methodological gaps, including a lack of long-term and generalization studies, underrepresentation of females and lower-functioning individuals, and limited use of rigorous comparative designs. Future research should prioritize larger, more diverse samples, standardized outcome measures, longitudinal designs, and ethically informed AI integration to advance the field toward evidence-based, scalable, and inclusive immersive interventions for ASD. https://www.crd.york.ac.uk/PROSPERO/view/CRD420251147405 , identifier CRD4202341147405.