Capturing and Operationalizing Participation in Pediatric Re/Habilitation Research Using Artificial Intelligence: A Scoping Review.
Vera C Kaelin, Mina Valizadeh, Zurisadai Salgado and 5 others
PMID 35919375WHAT IT FOUND
Artificial intelligence tools currently measure only observable behavior, failing to capture how children actually feel or think during therapy activities.
These tools also rely on data from autistic boys, meaning they cannot yet assess the full experience of participation for all patients.
Key findings
01No AI-based assessment included in the review captured attendance, emotional involvement, or cognitive involvement, with all approaches limited to behavioral involvement.
02The majority of studies focused on children with autism spectrum disorder and male participants, while none reported on family socio-economic status or child ethnicity.
03Most AI approaches used machine learning to predict participation based on annotated observations by professionals or researchers, rather than self-reports from the child.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The review did not assess the quality of the included studies, which is standard for scoping reviews but limits conclusions about the validity of the AI tools. The search may have missed relevant studies if 'artificial intelligence' was not mentioned in the title or abstract. The included studies had very small sample sizes (2 to 35 participants), which limits the generalizability of the findings about AI performance. The samples were heavily skewed toward boys with autism, so the results may not apply to girls or children with other disabilities.
Declared interests
The work was supported by the University of Illinois at Chicago and a grant from the National Institute on Disability, Independent Living, and Rehabilitation Research (NIDILRR). The authors declared no commercial or financial conflicts of interest.
The easy way to misread this
Do not interpret the term 'engagement' in these AI studies as equivalent to 'participation' as defined in rehabilitation frameworks. The review found that these tools measured observable behavior but failed to capture the internal experience of involvement, such as a child's feelings or thoughts during an activity.