Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals.
Gabriel Ng, Jan Andrysek
PMID 40355892WHAT IT FOUND
A new sensor algorithm tracked gait quality in prosthetic users, correlating moderately with the clinical gold standard.
It distinguished users with limb shortening from others, but did not match their self-reported walking ability. This is a validation study, not proof the tool changes patient care.
Key findings
01The new algorithm (HMM-SM) showed a moderate correlation with the Gait Profile Score when sensors were placed on the lower legs, indicating it tracks similar deviations as the standard measure.
02The algorithm successfully identified differences in gait quality for users with limb shortening compared to other prosthetic groups, particularly when using pelvic sensors.
03Scores from the new algorithm did not correlate with patients' self-reported mobility or functional capabilities, meaning the tool measures mechanical gait deviation rather than perceived ability.
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 had a small sample size (26 prosthetic users), which limits the reliability of subgroup comparisons, especially for the limb shortening group (n=3). The 'gold standard' GPS was calculated using inertial sensor kinematics rather than optical motion capture, which may introduce measurement bias. Data was collected in a single session, so the repeatability and long-term reliability of the HMM-SM were not tested. The new algorithm showed inconsistent performance depending on sensor placement, raising concerns about its robustness in real-world settings where sensor position may vary. The study did not find correlations between gait quality scores and functional questionnaires, leaving unclear how these mechanical metrics relate to daily life performance.
Declared interests
The research was funded by the Canadian Institutes of Health Research, the Natural Sciences and Engineering Research Council of Canada, the Kimel Family Scholarship, and the Loo Geok Eng Foundation.
The easy way to misread this
Do not interpret the moderate correlation with the Gait Profile Score as evidence that this tool improves patient outcomes or predicts functional ability. The study explicitly found no relationship between the sensor scores and patients' self-reported mobility, and the method's performance varied significantly based on sensor location.