A scoping review of inclusive and adaptive human–AI interaction design for neurodivergent users
Zhan Xu, Eric Zhi Feng Liu, Guobin Xia, Yixiang Duan, Luwen Yu
Abstract
PURPOSE: This review explored the design and application of Artificial Intelligence (AI) technologies supporting neurodiverse users, including individuals with Autism Spectrum Disorder (ASD), ADHD, and dyslexia. It examined system types, application domains, inclusive and adaptive design strategies, user participation, and related ethical challenges. MATERIALS AND METHODS: A systematic search across Web of Science, PubMed, ACM Digital Library, IEEE Xplore, and Google Scholar identified studies published between 2019 and 2025. After applying the inclusion criteria and conducting cross-validation, 117 peer-reviewed papers were analysed across five themes: technical features, design strategies, user engagement, effectiveness, and ethical considerations. RESULTS: Findings reveal a growing diversity of AI applications in education, healthcare, rehabilitation, and workplace contexts. Multimodal interaction, adaptive feedback, and embodied interfaces enhance engagement and usability; however, research remains fragmented and often lacks long-term perspectives. Most studies lack neurodivergent user participation and fail to adequately address sensory and cognitive heterogeneity, accessibility barriers, and gender bias in their datasets. CONCLUSIONS: AI-driven interaction design shows strong potential to enhance inclusivity and personalisation for neurodiverse users. Sustained progress requires interdisciplinary collaboration, participatory co-design, and longitudinal evaluation. Ethical principles, particularly fairness, transparency, and accessibility, should guide the development of future AI systems to ensure equitable, evidence-based support.