JMIR Publications

ABSTRACT

Background:

Lack of access to mental health care could be addressed, in part, through the development of automated screening technologies to detect the most common mental health disorders without the direct involvement of clinicians. Objective smartphone-collected data may contain enough information about individuals’ behaviors to infer their mental state and therefore screen for anxiety disorders and depression.

Objective:

The goal of this study is to compare and contrast how a single set of recognized and novel features, extracted from smartphone-collected data, can be used to predict generalized anxiety disorder, social anxiety disorder, and depression.

Methods:

An Android app was designed, together with a centralized server system, to collect periodic measurements of objective smartphone data. The types of data include samples of ambient audio, GPS location, screen state, and light sensor data. Subjects were recruited into a 2-week observational study where the app was run on their personal smartphone. Subjects also completed self-report severity measures of social anxiety disorder, generalized anxiety disorder, and depression. Participants were 112 Canadian adults from a non-clinical population. High-level features were extracted from the data of 84 participants, and predictive models of social anxiety disorder, generalized anxiety disorder, and depression were built and evaluated.

Results:

Models of social anxiety disorder and depression achieved screening accuracy significantly greater than uninformative models (mean AUROC of 0.64 and 0.72, respectively), while models of generalized anxiety disorder failed to be predictive. Investigation of the model coefficients revealed key features that were predictive of social anxiety disorder and depression.

Conclusions:

We demonstrate the ability of a common feature set to act as capable predictors in models of both social anxiety disorder and depression. This suggests that the types of behaviors which can be inferred from smartphone-collected data are broad indicators of mental health which can be used to study, assess, and track psychopathology simultaneously across multiple disorders and diagnostic boundaries.