Computer Vision-Based Approach for Quantifying Occupational Therapists' Qualitative Evaluations of Postural Control.
Hiromichi Hagihara, Naoto Ienaga, Daiki Enomoto and 5 others
PMID 32410925WHAT IT FOUND
Computer vision scores matched therapists' qualitative judgments of postural control better than duration time alone.
The visual method also worked well with only 20 seconds of video, suggesting assessments could be shorter and less tiring for children.
Key findings
01Computer vision-based static postural balance scores showed a significant positive correlation with therapists' qualitative clinical evaluations.
02A model combining computer vision scores with duration time reflected therapists' evaluations more strongly than duration time alone.
03When the test time was reduced to 20 seconds, the computer vision score still correlated more strongly with therapist evaluations than the conventional duration time measure.
STILL TO COME
How it was doneWhat they foundWhat 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
The study was conducted only on typically developing preschoolers, so it does not show if this method works for children with developmental disorders or motor impairments. The sample size was small (34 children). The computer vision tool used (OpenPose) is not yet a validated clinical device, and the study did not test its reliability across different cameras or settings. The authors note that the antigravity score had a weaker correlation with therapist judgments, possibly because therapists prioritize other factors when scoring.
Declared interests
The study was conducted by a collaboration of occupational therapists and computer vision engineers. No specific funding sources or conflicts of interest declarations are provided in the text.
The easy way to misread this
Do not assume this technology is ready for clinical use. The study tested a specific computer vision algorithm on typically developing children in a controlled setting. It has not been validated for children with developmental coordination disorder or other conditions, nor has it been tested as a standalone clinical tool.