Affective Computing for Brain Health Disorders

Affective computing has immense potential to benefit the treatment and care of brain health disorders. Affective computing (also referred to as artificial emotion intelligence or emotion AI) is the study and development of systems and devices that can recognize, interpret, process, and simulate emotion or other affective phenomena. Health conditions across the lifespan - including neurodevelopmental, psychiatric, and neurodegenerative conditions - have benefited by different affective computing tools and technologies. Using the latest advances in computer vision, signal processing, and pattern recognition, facial indicators, head movements and pose, body movements, gaze, and vocal indicators have been found that identify depressed patients and monitor stage and severity of depression progression. Social media behavior analysis and keystroke analysis have also been found to be useful in detecting depression and suicidal ideations. For Parkinson’s disease, objectively assessing facial expression changes and vocal impairments has been found to be beneficial to detect and monitor Parkinson’s, identify subtypes, monitor treatment responses, and differentiate between commonly confused disorders. Fine motor control, vocal impairments, and eye movement have also been found to detect and monitor early Alzheimer’s disease. There is a myriad of other possible affective computing brain health applications. Efforts are needed to ensure ethical development of affective computing applications for brain health that account for algorithmic and human bias.