PTOTSLPSystematic ReviewJournal of neuroengineering and rehabilitation2026

Use of artificial intelligence for outcome assessment in pediatric rehabilitation: a scoping review.

Neda Naghdi, Adam Farhat, Michael Amara and 2 others

PMID 41787455

WHAT IT FOUND

Most AI tools for pediatric outcome assessment are still experimental, focused on gait in children with cerebral palsy.

High accuracy reported in these studies reflects technical testing, not clinical readiness for routine use.

Key findings

01The majority of included studies used cross-sectional designs, with most focusing on feasibility and early validation rather than large-scale clinical implementation.

02Children with cerebral palsy were the most frequently studied population, particularly for gait analysis outcomes.

03Most studies remained in early or preclinical phases, with very few progressing to routine clinical use.

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.

Already have one?

What it does not show

No formal risk-of-bias or methodological quality appraisal was conducted, consistent with scoping review methodology. High accuracy values reported in studies may be inflated due to internal validation using limited datasets. Substantial heterogeneity in outcome measures, assessment tools, and data sources limits comparability across studies. Ethical considerations, consent procedures, and data governance frameworks were underreported in the included studies. Most studies focused on children with cerebral palsy, restricting generalizability to other pediatric rehabilitation populations.

Declared interests

The review was funded by the 2025 Shriners Children’s Helen Lemieux Research Internship award and Fonds de recherche du Québec. No other conflicts of interest were declared.

The easy way to misread this

Do not interpret high accuracy values reported in these studies as evidence that AI tools are ready for clinical use. Most studies were exploratory and conducted at early or preclinical stages, with performance metrics derived from internal validation on limited datasets.

Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →