This workshop is in the field of affective health computing, focusing on detection and intervention techniques for mental health and well-being, pain and distress. We invite contributions from researchers with multidisciplinary expertise (computer science, engineering, psychology and medicine), both in academia and industry, in the following domains:

Distress - e.g. pain, panic, confusion, itching - in patients with restricted communicative verbal abilities such as neonates and children, somnolent patients and patients with dementia is difficult to diagnose. For example, the subjectively experienced pain may be partly or even completely unrelated to the somatic pathology of tissue damage and other disorders. Therefore, the clinically used methods of distress assessment do not allow for objective and robust measurement, and physicians must rely on the patient’s report regarding the quality and intensity of the distress. Common tools are verbal scales, which are restricted to patients with normal mental abilities. However, there are procedures for distress assessment available for people with verbal and/or cognitive impairments and scales for pain assessment in people who are sedated and require ventilation. Overall, these diagnostic methods have limited reliability, validity or are very time consuming. If valid measurement of distress is not possible, treating the negative affect may lead to cardiac stress in risk patients and over- or under-usage of medical treatment. There are several efforts to create an automatic system for recognizing distress through different kind of modalities and machine learning techniques.

Mental health and wellbeing, which are one of the most challenging issues of the modern society. For instance, depression is growing worldwide: by 2020 one suicide will happen every 20 seconds, and by 2030 it will be the #1 disease burden. Other typical causes of poor mental health and wellbeing are high levels of stress and anxiety, sleep deprivation, and loneliness due to impoverished social communication. Also, chronic mental illnesses such as schizophrenia, and neurodevelopmental disorders such as autism, if not monitored and treated timely, can lead to further degradation of the person’s mental health and wellbeing. Most existing methods and algorithms for monitoring and providing feedback to individual’s mental health and wellbeing have been built/evaluate using (limited) data captured in highly constrained settings (e.g., labs). This can limit the applicability and reliability of such tools and algorithms when applied in every-day situations. The goals of this part of the workshop are (i) to explore practical research challenges and opportunities for designing new methods, algorithms and applications for affect/mood measurement/prediction in every-day life or clinical settings, and (ii) to introduce novel target tools and algorithms and discuss the directions on how the design of these should be tackled in the future.