The effect of gamified robot-enhanced training on motor performance in chronic stroke survivors.

Task-specific training constitutes a core element for evidence-based rehabilitation strategies targeted at improving upper extremity activity after stroke. Its combination with additional treatment strategies and neurotechnology-based solutions could further improve patients' outcomes. Here, we studied the effect of gamified robot-assisted upper limb motor training on motor performance, skill learning, and transfer with respect to a non-gamified control condition with a group of chronic stroke survivors. The results suggest that a gamified training strategy results in more controlled motor performance during the training phase, which is characterized by a higher accuracy (lower deviance), higher smoothness (lower jerk), but slower speed. The responder analyses indicated that mildly impaired patients benefited most from the gamification approach. In conclusion, gamified robot-assisted motor training, which is personalized to the individual capabilities of a patient, constitutes a promising investigational strategy for further improving motor performance after a stroke.

Predictive Analysis of Errors During Robot-Mediated Gamified Training.

This paper presents our approach to predicting future error-related events in a robot-mediated gamified physical training activity for stroke patients. The ability to predict future error under such conditions suggests the existence of distinguishable features and separated class characteristics between the casual gameplay state and error prune state in the data. Identifying such features provides valuable insight to creating individually tailored, adaptive games as well as possible ways to increase rehabilitation success by patients. Considering the time-series nature of sensory data created by motor actions of patients we employed a predictive analysis strategy on carefully engineered features of sequenced data. We split the data into fixed time windows and explored logistic regression models, decision trees, and recurrent neural networks to predict the likelihood of a patient making an error based on the features from the time window before the error. We achieved an 84.4% F1-score with a 0.76 ROC value in our best model for predicting motion accuracy related errors. Moreover, we computed the permutation importance of the features to explain which ones are more indicative of future errors.

Towards an Adaptive Upper Limb Rehabilitation Game with Tangible Robots.

A key feature of a successful game is its ability to provide the player with an adequate level of challenge. However, the objective of difficulty adaptation in serious games is not only to maintain the player's motivation by challenging, but also to ensure the completion of training objectives.This paper describes our proposed upper-limb rehabilitation game with tangible robots and investigates the effect of game elements and gameplay on the amount of the performed motion in several planes and percentage of failure by using the data from 33 unimpaired subjects who played 53 games within two consecutive days. In order to provide a more generic adaptation strategy in the future, we discretize the game area to circular zones. We then show the effect of changing these zones during gameplay on the activation of different muscles through EMG data in a pilot study.The study shows that it is possible to increase the challenge level by adding more active agents chasing the player and increasing the speed of these agents. However, only the increase in number of agents significantly increases the users' motion on both planes. Analysis of player behaviors leads us to suggest that by adapting the behaviour of these active agents in specific zones, it is possible to change the trajectory of the user, and to provide a focus on the activation of specific muscles.

Designing Configurable Arm Rehabilitation Games: How Do Different Game Elements Affect User Motion Trajectories?

For successful rehabilitation of a patient after a stroke or traumatic brain injury, it is crucial that rehabilitation activities are motivating, provide feedback and have a high rate of repetitions. Advancements in recent technologies provide solutions to address these aspects where needed. Additionally, through the use of gamification, we are able to increase the motivation for participants. However, many of these systems require complex set-ups, which can be a big challenge when conducting rehabilitation in a home-based setting. To address the lack of simple rehabilitation tools for arm function for a home-based application, we previously developed a system, Cellulo for rehabilitation, that is comprised of paper-supported tangible robots that are orchestrated by applications deployed on consumer tablets. These components enable different features that allow for gamification, easy setup, portability, and scalability. To support the configuration of game elements to patients' level of motor skills and strategies, their motor trajectories need to be classified. In this paper, we investigate the classification of different motor trajectories and how game elements impact these in unimpaired, healthy participants. We show that the manipulation of certain game elements do have an impact on motor trajectories, which might indicate that it is possible to adapt the arm remediation of patients by configuring game elements. These results provide a first step towards providing adaptive rehabilitation based upon patients' measured trajectories.