Background Sustained engagement is essential for the success of telerehabilitation programs. However, patients’ lack of motivation and adherence could undermine these goals. To overcome this challenge, physical exercises have often been gamified. Building on the advantages of serious games, we propose a citizen science–based approach in which patients perform scientific tasks by using interactive interfaces and help advance scientific causes of their choice. This approach capitalizes on human intellect and benevolence while promoting learning. To further enhance engagement, we propose performing citizen science activities in immersive media, such as virtual reality (VR). Objective This study aims to present a novel methodology to facilitate the remote identification and classification of human movements for the automatic assessment of motor performance in telerehabilitation. The data-driven approach is presented in the context of a citizen science software dedicated to bimanual training in VR. Specifically, users interact with the interface and make contributions to an environmental citizen science project while moving both arms in concert. Methods In all, 9 healthy individuals interacted with the citizen science software by using a commercial VR gaming device. The software included a calibration phase to evaluate the users’ range of motion along the 3 anatomical planes of motion and to adapt the sensitivity of the software’s response to their movements. During calibration, the time series of the users’ movements were recorded by the sensors embedded in the device. We performed principal component analysis to identify salient features of movements and then applied a bagged trees ensemble classifier to classify the movements. Results The classification achieved high performance, reaching 99.9% accuracy. Among the movements, elbow flexion was the most accurately classified movement (99.2%), and horizontal shoulder abduction to the right side of the body was the most misclassified movement (98.8%). Conclusions Coordinated bimanual movements in VR can be classified with high accuracy. Our findings lay the foundation for the development of motion analysis algorithms in VR-mediated telerehabilitation.

BACKGROUND Human interaction with machines is essential for the success of telerehabilitation programs. Telerehabilitation devices are designed for use by individuals whose behavior is atypical due to motor impairment. In order to implement optimal control strategies for human-machine interactions that are intuitive and safe, the machine must “gain an understanding” of the user's actions. OBJECTIVE This study seeks to demonstrate the possibility of classifying bimanual movements in telerehabilitation using machine learning, toward automatic assessment of motor performance. METHODS Nine healthy individuals interacted with a commercial virtual reality gaming system within an engaging citizen science project. Time series of their movement were recorded by the sensors embedded in the device as they performed scientific tasks. We performed principal component analysis to identify salient features of movements, and then applied a bagged trees ensemble classifier to classify the movements. RESULTS Classification achieved exceptionally high performance, reaching 99.9% accuracy. Among the movements, elbow flexion was most accurately classified (99.2%) and horizontal shoulder abduction to the right side of the body was most misclassified (98.8%). CONCLUSIONS Coordinated bimanual movements in virtual reality can be classified with extraordinary high accuracy. Our findings lay the foundation for the development of motion analysis algorithms in virtual reality-mediated telerehabilitation.