Mobile App to Streamline the Development of Wearable Sensor-Based Exercise Biofeedback Systems: System Development and Evaluation.
Martin O'Reilly, Joe Duffin, Tomas Ward and 1 others
PMID 28827210WHAT IT FOUND
A tablet app built personalized exercise feedback systems using a sensor on the thigh for healthy people.
Accuracy was highest for single-leg squats and lowest for lunges. It is not yet evidence for patient rehabilitation.
Key findings
01The personalized classifiers were least accurate for lunges (84.14%) and most accurate for single-leg squats (97.26%).
02The system was more accurate for the experienced group (98.59%) than the beginners group (88.00%) for the deadlift exercise, but was otherwise more accurate for the beginners.
03For squats, there was a 13% chance that an acceptable repetition may be classified as aberrant and a 17% chance that an aberrant repetition may be classified as acceptable.
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 accuracy evaluation included 15 participants, and they were not people currently undergoing rehabilitation. The participants were a convenience sample and were not balanced by experience or gender. Accuracy varied widely between people for lunges and squats. Only a single exercise professional labeled the data, and the labels were not compared with other professionals. The sensor settings may be insufficient for faster exercises such as jumping or plyometric exercises. The tool still requires an exercise professional to record and label data. The authors state that it is not yet understood how the tool will be incorporated into clinical practice.
The easy way to misread this
Do not read the accuracy figures as evidence that this app improves patient exercise technique or rehabilitation outcomes. It was evaluated in healthy volunteers, not people in rehabilitation, and the authors state that it is not yet understood how it will be incorporated into clinical practice.