Wearable sensors to predict improvement following an exercise intervention in patients with knee osteoarthritis.
Dylan Kobsar, Sean T Osis, Jeffrey E Boyd and 2 others
PMID 28899433WHAT IT FOUND
Thigh accelerometers plus patient-reported scores predicted hip-strengthening response in knee OA with 74.4% accuracy.
A back and thigh sensor pair matched the three-sensor array at 80.0%. These preliminary findings support a simple wearable system for identifying who will improve, pending clinical validation.
Key findings
01The thigh sensor was the best single location for predicting response, achieving 74.4% classification accuracy when combined with patient-reported outcome measures.
02A two-sensor array (back and thigh) achieved 80.0% accuracy, which was not significantly different from the best three-sensor array (back, thigh, shank) at 81.7%.
03Baseline gait speed, age, and BMI did not significantly differ between responders and non-responders, suggesting subjective or standard demographic measures alone may not predict treatment response.
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 was retrospective and used a small sample of 39 completers, requiring further validation before clinical use. The findings apply only to hip strengthening interventions and should not be generalized to other exercise types or treatments. High-frequency acceleration data was filtered out, potentially removing useful gait information. The classification accuracy (74.4-81.7%) is not perfect, meaning the system would misclassify some patients.
Declared interests
The study was funded by the Canadian Institutes of Health Research and Alberta Innovates - Health Solutions. The authors did not declare any other conflicts of interest.
The easy way to misread this
Do not implement this as a diagnostic tool yet. The accuracy rates are from a small, retrospective analysis that requires prospective validation. Additionally, the model predicts response specifically to hip strengthening exercises; it does not identify which patients will respond to other interventions like manual therapy or aerobic exercise.