Affective computing in serious games for physical rehabilitation: Scoping review (Preprint)

BACKGROUND Serious games have become an alternative support for traditional physical therapy. However, many of these games do not address the emotional needs of patients. People with disabilities often experience emotions such as sadness, frustration, and even anger, which can create a barrier to their rehabilitation treatment. OBJECTIVE This review aims to identify technologies and methods of affective computing applied in serious games for physical rehabilitation, establish a foundation for future research, and identify areas of opportunity for further exploration. METHODS A scoping review was conducted following PRISMA guidelines, using the databases PubMed, ScienceDirect, IEEE Xplore, ACM Digital Library, PEDro, Springer, and Google Scholar. RESULTS The initial search yielded 5,293 records, of which 9 articles met the inclusion criteria. Data were systematically extracted from these articles based on predefined research questions. Notably, engagement, tiredness, and pain were the most identified emotions, reported in 50% of the studies. Only three studies applied theoretical frameworks for emotion classification. Facial expression analysis and gesture recognition were the most frequently employed affective computing techniques, yet only two studies implemented adaptive gameplay based on emotional feedback. CONCLUSIONS This scoping review revealed that none of the studies validate the benefits of affective computing in the rehabilitation process, suggesting that future work should adopt more rigorous methodological designs.