Title : Artificial Intelligence, equity, and pediatric neurodevelopmental disorders: A scoping review of clinical practice applications
Abstract:
Artificial intelligence (AI) is increasingly used in healthcare and has the potential to improve the diagnosis, treatment, monitoring, and management of neurodevelopmental disorders (NDDs) in children. Early identification and personalized care are often constrained by subjective assessments and inequitable access. AI tools may enhance diagnostic accuracy and care delivery, but the maturity, clinical readiness, and equity implications of this evidence base remain unclear. This scoping review mapped peer-reviewed studies published in English since 2015 that described empirical or conceptual AI applications for diagnosis, monitoring, decision support, or treatment in pediatric NDD care, with particular attention to equity considerations. Searches included major databases and grey literature sources. Data were charted on study characteristics, AI function, target condition, outcomes, implementation maturity, and equity considerations. From 1,027 records, 13 studies met the inclusion criteria. Most focused on attention deficit/hyperactivity disorder, ADHD, (n=7), or autism spectrum disorder, ASD, (n=4), with diagnostic tools predominating. Reported accuracies ranged from 76–100% for ADHD and 88–95% for ASD. Most studies were preliminary or in early implementation, with only one externally validated. Equity considerations were limited, with overrepresentation of White males and little attention to socioeconomic or cultural factors. AI shows promise for pediatric NDD care, but equitable clinical adoption will require inclusive research, external validation, and equity-focused implementation.
