Inertial sensor-based gait parameters reflect patient-reported fatigue in multiple sclerosis.
Alzhraa A Ibrahim, Arne Küderle, Heiko Gaßner and 3 others
PMID 33339530WHAT IT FOUND
In 49 people with MS, changes in gait measured by foot sensors during a six-minute walk predicted perceived fatigue within one Borg point.
This supports using wearable sensors to track fatigue in real-world walking, though the study did not test whether this helps patient care.
Key findings
01The model predicted Borg fatigue scores with a mean absolute error of 1.38, which is less than the two-point width of each exhaustion category on the scale.
02Normalized stride time, maximum toe clearance, heel strike angle, and stride length were the gait parameters most strongly associated with fatigue.
03The correlation between fatigue and EDSS was only moderate, meaning fatigue can occur at any disease stage and is not simply a result of higher disability scores.
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 49 patients, so the model may not generalize to the wider MS population. Fatigue was measured only by the Borg scale, which captures exertion during the walk but not other causes of fatigue such as sleep disorders, depression, or cognitive impairment. The study was cross-sectional and did not track patients over time, so it cannot show how fatigue changes with disease progression. Patients had to be able to walk at least 10 meters unassisted, so the findings do not apply to people with more severe disability. The prediction model was validated using cross-validation on the same dataset, not on an independent group of patients.
Declared interests
The authors declared no conflicts of interest. The work was funded by the Ministry of Higher Education, Egypt, and Projekt DEAL.
The easy way to misread this
Do not read the prediction accuracy as evidence that sensor-based gait analysis is ready for clinical use. The model was validated on the same 49 patients it was trained on, and the study never tested whether using these sensors actually improves patient outcomes or treatment decisions.