Serious games for rehabilitation: Gestural interaction in personalized gamified exercises through a recommender system

[Display omitted] •We designed a recommender system of exergames for rehabilitation.•We created a personalized game mode based in a gestural interaction platform.•We studied the effectiveness, efficacy, learnability and satisfaction of gestural interaction.•We presented different methods for testing the recommender system. One of the principal problems of rehabilitation is that therapy sessions can be boring due the repetition of exercises. Serious games, and in particular exergames in rehabilitation, can motivate, engage and increase patients’ adherence to their treatment. Also, the automatic personalization of exercises to each patient can help therapists. Thus, the main objective of this work is to build an intelligent exergame-based rehabilitation system consisting of a platform with an exergame player and a designer tool. The intelligent platform includes a recommender system which analyzes user interactions, along with the user’s history, to select new gamified exercises for the user. The main contributions of this paper focus, first, on defining a recommender system based on different difficulty levels and user skills. The recommender system offers the ability to provide the user with a personalized game mode based on his own history and preferences. The results of a triple validation with experts, users and rehabilitation center professionals reveal a positive impact on gestural interaction and rehabilitation uses. Also, different methods are presented for testing the rehabilitation recommender system.