 The study aimed to compare the predictive accuracy of a set of recognized and novel features extracted from smartphone-collected data for detecting generalized anxiety disorder, GAD, social anxiety disorder, SAD, and depression in a non-clinical population of 112 Canadian adults. The results showed that models of SAD and depression achieved significantly greater screening accuracy than uninformative models, while models of GAD failed to be predictive. The study suggests that smartphone-collected data can act as broad indicators of mental health and can be used to study, assess, and track psychopathology across multiple disorders and diagnostic boundaries. This article was authored by Daniel D. Mateo, Catherine Fotinos, Sikinthia Locuge, and others.