AI-Based Gait Analysis System for Rehabilitation: Usability Evaluation of Human-Technology Interaction.
Seojin Hong, Hyun Choi, Hyosun Kweon
PMID 41411645WHAT IT FOUND
Five experienced physical therapists tested a prototype AI gait analysis system.
They valued the objective data but rated usability below average due to cumbersome setup, manual calibration, and poor hardware design. The system needs refinement before clinical use.
Key findings
01Participants appreciated the system's ability to provide quantitative assessments of gait parameters that are difficult to measure visually, such as symmetry.
02The mean System Usability Scale score was 57, which corresponds to a grade of D and indicates below-average usability.
03Key usability barriers included complex setup procedures, the need for manual calibration that introduces human error, and hardware issues like an obscured power button.
STILL TO COME
How it was doneWhat they foundWhat it means for PTs
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 included only five participants, which limits the generalizability of the findings. The sample was predominantly male (4 out of 5), which may introduce bias. This was a formative evaluation of a prototype, so it did not measure long-term usability or clinical efficacy outcomes. The evaluation was conducted in a controlled clinical environment, which may not reflect real-world variability.
Declared interests
The authors declared no conflicts of interest. The study was conducted at the National Rehabilitation Center in Seoul, Republic of Korea. The system was commissioned by the manufacturer for formative evaluation, and the authors noted that the manufacturer implemented changes based on these findings.
The easy way to misread this
Do not interpret this study as evidence that AI gait analysis improves patient outcomes or clinical decision-making. The study evaluated the usability of a prototype system with only five therapists and found below-average usability; it did not test the system's effectiveness in treating patients.
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 →