Emerging methods for measuring physical activity using accelerometry in children and adolescents with neuromotor disorders: a narrative review.
Bailey A Petersen, Kirk I Erickson, Brad G Kurowski and 2 others
PMID 38419099WHAT IT FOUND
Standard step-counters and cut-point analyses often misclassify activity in children with cerebral palsy or brain injury.
Combining participation questionnaires with raw accelerometer data, ideally using machine learning tailored to the child's mobility level, provides a more accurate picture of their real-world activity than commercial devices alone.
Key findings
01Commercial devices and standard cut-points are unreliable for this population because algorithms are trained on able-bodied adults and structured lab tasks do not match free-living play.
02Machine learning models outperform standard cut-points, with accuracy exceeding 80%, particularly for children with lower mobility levels where cut-points frequently miscategorize intensity.
03Optimal sensor placement varies by method; while hip sensors are standard for cut-points, machine learning classification improves significantly with multiple sensors (e.g., wrist and hip).
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTs
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
This is a narrative review, not a systematic review, so the selection of studies may be biased toward the authors' interests. Most cited studies involve ambulatory children (GMFCS I-III); there is very little data on non-ambulatory children or those with severe impairments. Few studies have validated machine learning models in true free-living (home/community) settings; most are lab-based simulations. There is no consensus on the best method, making direct comparison between different clinics difficult.
Declared interests
The authors declare no conflicts of interest. The work was supported by the National Institutes of Health (Extramural).
The easy way to misread this
Do not assume that buying a commercial smartwatch for a patient will provide valid physical activity data. These devices are calibrated for able-bodied adults and often misinterpret the atypical movements of children with neuromotor disorders.