Introduction / Rationale: Artificial intelligence (AI) and machine learning (ML) are increasingly integrated into rehabilitation to enhance outcome measurement accuracy. However, the extent to which AI/ML contributes to assessing and interpreting functional outcomes in pediatric rehabilitation remains unclear. A scoping review is needed to map current evidence in this emerging field.
Objectives: This scoping review aims to identify and synthesize studies that utilize AI/ML to develop, analyze, or interpret outcome measures in children with physical disabilities undergoing rehabilitation.
Methods / Approach: Following the Arksey & O’Malley framework and PRISMA-ScR guidelines, we will systematically search electronic databases (e.g., Medline, IEEE Xplore, CINAHL, Scopus) for studies published from 2015-2025. Inclusion criteria will focus on AI/ML applications in pediatric rehabilitation for children 0-18 years with physical disabilities that support outcome assessment. Two reviewers will independently screen studies, extract data, and conduct a qualitative synthesis of the included studies.
Results / Practice Implications: Preliminary findings suggest AI/ML is employed in gait analysis, motor function assessment, and cognitive outcome tracking. The review will highlight key methodologies, AI models used, and gaps in current research, informing future clinical applications.
Conclusion / Contribution to the occupational therapy profession: By summarizing AI/ML’s role in outcome measurement, this scoping review provides insights into how these technologies can enhance assessment precision, guide intervention planning, and optimize patient outcomes in pediatric rehabilitation. Findings will support occupational therapists in integrating AI-driven assessment tools into practice.