Self-adaptive games for rehabilitation at home

Abstract

Computer games are a promising tool to support rehabilitation at home. It is widely recognized that rehabilitation games should (i) be nicely integrated in general-purpose rehabilitation stations, (ii) adhere to the constraints posed by the clinical protocols, (iii) involve movements that are functional to reach the rehabilitation goal, and (iv) adapt to the patients' current status and progress. However, the vast majority of existing rehabilitation games are stand-alone applications (not integrated in a patient station), that rarely adapt to the patients' condition. In this paper, we present the first prototype of the patient rehabilitation station we developed that integrates video games for rehabilitation with methods of computational intelligence both for on-line monitoring the movements' execution during the games and for adapting the gameplay to the patients' status. The station employs a fuzzy system to monitor the exercises execution, on-line, according to the clinical constraints defined by the therapist at configuration time, and to provide direct feedback to the patients. At the same time, it applies real-time adaptation (using the Quest Bayesian adaptive approach) to modify the gameplay according both (i) to the patient current performance and progress and (ii) to the exercise plan specified by the therapist. Finally, we present one of the games available in our patient stations (designed in tight cooperation with therapists) that integrates monitoring functionalities with in-game self-adaptation to provide the best support possible to patients during their routine.