This is the authors' abstract. We don't add key points for this paper.
Artificial intelligence and data-driven systems are increasingly embedded in support structures for neurodivergent children; however, approaches often prioritize measurable signals over contextual understanding, creating a disconnect between data-driven representations and the realities of everyday life. This study presents a narrative review of AI-supportive systems using a PRISMA-informed screening process to identify 67 studies published between 2021 and 2026. Findings show that the evidence base is dominated by autism-focused prototype development evaluated under controlled conditions. Support needs are more often involved in validating completed prototypes than in shaping systems during the design process. Research demonstrates technical feasibility more reliably than meaningful benefit in real-world use. In response, this article proposes a Function-Context-Participation framework, arguing that AI-supportive systems should be organized around cross-diagnostic functional needs, evaluated across home, school, and clinical settings, and developed through co-design processes that involve neurodivergent children and their support networks from the earliest stages of design.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: