Capturing and Operationalizing Participation in Pediatric Re/Habilitation Research Using Artificial Intelligence: A Scoping Review

Abstract

BackgroundThere is increased interest in using artificial intelligence (AI) to provide participation-focused pediatric re/habilitation. Existing reviews on the use of AI in participation-focused pediatric re/habilitation focus on interventions and do not screen articles based on their definition of participation. AI-based assessments may help reduce provider burden and can support operationalization of the construct under investigation. To extend knowledge of the landscape on AI use in participation-focused pediatric re/habilitation, a scoping review on AI-based participation-focused assessments is needed.ObjectiveTo understand how the construct of participation is captured and operationalized in pediatric re/habilitation using AI.MethodsWe conducted a scoping review of literature published in Pubmed, PsycInfo, ERIC, CINAHL, IEEE Xplore, ACM Digital Library, ProQuest Dissertation and Theses, ACL Anthology, AAAI Digital Library, and Google Scholar. Documents were screened by 2–3 independent researchers following a systematic procedure and using the following inclusion criteria: (1) focuses on capturing participation using AI; (2) includes data on children and/or youth with a congenital or acquired disability; and (3) published in English. Data from included studies were extracted [e.g., demographics, type(s) of AI used], summarized, and sorted into categories of participation-related constructs.ResultsTwenty one out of 3,406 documents were included. Included assessment approaches mainly captured participation through annotated observations (n = 20; 95%), were administered in person (n = 17; 81%), and applied machine learning (n = 20; 95%) and computer vision (n = 13; 62%). None integrated the child or youth perspective and only one included the caregiver perspective. All assessment approaches captured behavioral involvement, and none captured emotional or cognitive involvement or attendance. Additionally, 24% (n = 5) of the assessment approaches captured participation-related constructs like activity competencies and 57% (n = 12) captured aspects not included in contemporary frameworks of participation.ConclusionsMain gaps for future research include lack of: (1) research reporting on common demographic factors and including samples representing the population of children and youth with a congenital or acquired disability; (2) AI-based participation assessment approaches integrating the child or youth perspective; (3) remotely administered AI-based assessment approaches capturing both child or youth attendance and involvement; and (4) AI-based assessment approaches aligning with contemporary definitions of participation.

Natural Language Processing to Classify Caregiver Strategies Supporting Participation Among Children and Youth with Craniofacial Microsomia and Other Childhood-Onset Disabilities

“…The use of AI might be one way to further customize participation-focused pediatric rehabilitation interventions such as PEM + to individual needs of children, youth and their families [ 13 – 15 ]. To our knowledge, this is one of the first studies to apply NLP and use of the UMLS for customizing participation-focused pediatric rehabilitation services [ 15 , 16 ]. We conducted a series of classification tasks with increased complexity to identify best performing predictive models to classify caregiver strategies to key predictors of participation.…”

“…Despite rapid increase in the use of artificial intelligence in pediatric rehabilitation, classification of caregiver strategies has been limited [ 15 , 16 ]. NLP research on classifying functional outcomes such as activity competence or participation may be most closely related to the classification of caregiver strategies to support child and youth participation.…”

“…Technology might support rehabilitation practitioners to feasibly customize participation-focused interventions by automating and simplifying steps and, thus, support to deliver family-centered interventions to service eligible children, youth and families [ 13 , 14 ]. However, two scoping reviews on the use of AI in participation-focused pediatric re/habilitation indicated a lack of AI-based tools that are customized to individual needs [ 15 , 16 ]. The Participation and Environment Measure Plus (PEM+) is being designed to pair with a Participation and Environment Measures (PEM) and is a promising technology-based and remotely delivered intervention for engaging families in decisions about service design [ 17 – 19 ].…”

Diversified caregiver input to upgrade the Young Children’s Participation and Environment Measure for equitable pediatric re/habilitation practice

“…As YC-PEM has been primarily shaped by the perspectives of BIPOC identifying caregivers situated in the U.S., the coexistence of individualistic and collectivist parent belief systems may have shaped their expectations for interdependence when describing their young child’s involvement in activities [ 57 , 58 ]. This focus on interdependence distinguishes participation from its intrinsic concepts (i.e., activity competence, preferences, sense of self) and differentiates it from more established approaches to measuring participation [ 59 , 60 ].…”

Engagement of Preschool-Aged Children in Daily Routines

“…The two subdomains of participation, involvement and engagement, are regarded as key priority outcomes of inclusive practices in early childhood education. As stated in the literature, involvement refers to an internal state of interest towards an activity itself, while engagement refers to the specific behavior, emotions, and thoughts [ 2 ]. With regard to early childhood education, engagement is expressed through the time the child spends engaged in activities, as well as the level of interaction with the social and physical environments and timeframe in which they are achieved in a developmentally and contextually appropriate manner.…”