JMIR Publications

ABSTRACT

Background:

Artificial intelligence (AI) and game-based approaches are already widely integrated in healthcare. However, the combination of both could provide further benefits, especially in the management of chronic diseases.

Objective:

This systematic review seeks to generate an overview over the currently existing literature on the connection of artificial intelligence and game-based approaches in health care. Primary objectives were to cluster studies by diseases/health topic addressed, by levels of care and by AI/games technology.

Methods:

The PRISMA-P method (Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols) was used for the systematic review. The databases PubMed, Scopus, IEEExplore, Cochrane Library and Pubpsych were searched. Screening was performed independently by two authors using the Rayyan software.

Results:

A total of 16 papers met all inclusion criteria. Most studies were conducted in disease rehabilitation, tackling motion and cognitive impairment. Machine learning was the main AI technology applied, serious games the main game-based approach used. However, direct interaction between the technologies occurred only in three studies. The included studies all show very limited evidence quality, with most presenting either a rather technical proof-of-concept or usability testing with small sample sizes. From the patients and healthy subjects' perspective, generally high usability, motivation, and satisfaction was found.

Conclusions:

Our review shows limited evidence in the combination of artificial intelligence and games in healthcare. However, first results present a broad scope of possible applications, and positive perceptions by patients. In future, the development of adaptive game designs with direct interaction between AI and games seems promising and should be topic of further reviews.