Emotional recognition technologies applied to health: Review and challenges.

Abstract

Emotions affect health and health affects emotions. Emotions can help in the prevention, diagnosis, and treatment of many diseases when properly recognized and interpreted. Affective computing emerges to detect one or more signals associated with human emotions. Research into the use of emotion recognition in healthcare is scarce, therefore it is crucial to explore the reasons behind this phenomenon and identify neglected methods with potential for human health. We review methods and technologies used in emotion recognition and their applications in healthcare, highlighting methods not discussed in previous reviews of the field, including electroencephalogram and electrocardiogram, thermal camera, bracelet, skin conductance, and audio. A metric based on reproducibility and population was established to assess the review articles' quality. We surveyed and analyzed studies with tools of affective computing applied to health, based on the metrics established, to qualify and identify the challenges of the area. Our study reveal that there are challenges to be overcome in detecting and recognising human emotions, related to sample size and low quality reproducibility. We list and discuss the main current challenges, perspectives and solutions to overcome the challenges, focusing on investigating the application of affective technologies in healthcare and establishing a gold standard.