AbstractStroke is a major cause of adult-onset disability worldwide, and approximately 40% of stroke survivors have residual impairment in upper-extremity function. Prior studies suggest that increased participation in rehabilitation exercises improves motor function post-stroke,1 however further clarification of optimal exercise dose and timing has been limited by the technical challenge of quantifying exercise activities over multiple days. In this exploratory study, we assessed the feasibility of using body-worn sensors to track rehabilitation exercises in the inpatient setting, and investigated which recording parameters and data analysis strategies are sufficient for accurately identifying and counting exercise repetitions. MC10 BioStampRC® sensors were used to measure accelerometry and gyroscopy from arms of healthy controls (n=11) and patients with arm weakness due to recent stroke (n=13) while the subjects performed three pre-selected upper extremity exercises. Sensor data was then labeled by exercise type, and this labeled data set was used to train a machine learning classification algorithm for identifying exercise type. The machine-learning algorithm and a peak-finding algorithm was used to count exercise repetitions in non-labeled data sets. We achieved a repetition counting accuracy of 95.6 ± 2.4 % overall, and 95.0 ± 2.3 % in patients with arm weakness due to stroke. Accuracy was decreased when using fewer sensors or using accelerometry alone. Our exploratory study suggests that body-worn sensor systems are technically feasible, well-tolerated in subjects with recent stroke, and may ultimately be useful for developing a system to measure total exercise “dose” in post-stroke patients during clinical rehabilitation or clinical trials.
Automatic Identification of Upper Extremity Rehabilitation Exercise Type and Dose Using Body-Worn Sensors and Machine Learning: A Pilot Study
