Social relationships are essential for humans; neglecting our social needs can reduce wellbeing or even lead to the development of more severe issues such as depression or substance dependency. Although essential, some individuals face major challenges in forming and maintaining social relationships due to the experience of social anxiety. The burden of social anxiety can be reduced through accessible assessment that leads to treatment. However, socially anxious individuals who seek help face many barriers stemming from geography, fear, or disparities in (...) access to systems of care. But recent research suggested digital behavioral markers as a way to deliver cheap and easily accessible digital assessment for social anxiety: As earlier work shows, players with social anxiety show similar behaviors in virtual worlds as in the physical world, including tending to walk farther around other avatars and standing farther away from other avatars. The characteristics of the movement behavior in-game can be harnessed for the development of digital behavioral markers for the assessment of social anxiety. In this paper, we investigate whether implicit as well as explicit digital behavioral markers, proposed by prior work, for social anxiety can be used for predicting the level of social anxiety. We show that both, explicit and implicit digital behavioral markers can be harnessed for the assessment. Our findings provide further insights about how game-based digital behavioral markers can be used for the assessment of social anxiety. (shrink)

We describe the design and evaluation of a sub-clinical digital assessment tool that integrates digital biomarkers of depression. Based on three standard cognitive tasks on which people with depression have been known to perform differently than a control group, we iteratively designed a digital assessment tool that could be deployed outside of laboratory contexts, in uncontrolled home environments on computer systems with widely varying system characteristics. We conducted two online studies, in which participants used the assessment tool in their own (...) homes, and completed subjective questionnaires including the Patient Health Questionnaire —a standard self-report tool for assessing depression in clinical contexts. In a first study, we demonstrate that each task can be used in isolation to significantly predict PHQ-9 scores. In a second study, we replicate these results and further demonstrate that when used in combination, behavioral metrics from the three tasks significantly predicted PHQ-9 scores, even when taking into account demographic factors known to influence depression such as age and gender. A multiple regression model explained 34.4% of variance in PHQ-9 scores with behavioral metrics from each task providing unique and significant contributions to the prediction. (shrink)