Development, validation and use of artificial-intelligence-related technologies to assess basic motor skills in children: a scoping review

Abstract

Background: In basic motor skills evaluation, two observersers can eventually mark the same child’s performance differently. When systematic, this brings serious noise to the assessment. New motion sensing and tracking technologies offer more precise measures of these children’s capabilities. We aimed to review current development, validation and use of artificial intelligence-related technologies that assess basic motor skills in children aged 3 to 6 years old. Methods: We performed a scoping review in Medline, EBSCO, IEEE and Web of Science databases. PRISMA Extension recommendations for scoping reviews were applied for the full review, whereas the COSMIN criteria for diagnostic instruments helped to evaluate the validation of the artificial intelligence (AI)-related measurements. Results: We found 672 studies, from which 12 were finally selected, 7 related to development and validation and 5 related to use. From the 7 studies, we tracked 10 other publications updating and/or using these technologies. Engineering work and technological features have been prioritised in studies about AI-related technologies. The validation of these algorithms was strictly based on engineering criteria; it means, no substantive knowledge of the medical or psychological aspects of motor skills was integrated into the validation process. Technical features typically evaluated in psychometric instruments designed for assessing motor skills in children were also ignored (e.g., COSMIN criteria). The use of these AI-related technologies in scientific research is still limited. Conclusion: Clinical measurement standards have not been integrated into the development of AI-related technologies for measuring basic motor skills in children. This compromises the validity, reliability and practical utility of these tools, so future improvement in this type of research is needed.