JMIR Publications

ABSTRACT

Background:

Unaddressed early stage mental health including stress, anxiety and mild depression can become burdens for individuals in the long term. Identifying milder symptoms of mental health issues before they become clinical issues is important and has motivated the use of digital phenotyping for that purpose. Digital phenotyping involves capturing continuous behavioural data via digital devices to monitor human behaviour and identify any abnormalities.

Objective:

This systematic literature review focuses on the effectiveness of using digital phenotyping to identify stress, anxiety, and mild depression. We review data collected via smartphones to systematically identify which sensor data detects and predicts behavioural patterns associated to stress, anxiety and mild depression.

Methods:

We used the PRISMA process to identify 28 articles to assess the key smartphone sensors that are highly correlated with anxiety, stress and mild depression.

Results:

Location (GPS), audio, accelerometer, light and keyboard were found to be significantly correlated to self-reported stress, anxiety and mild depression.

Conclusions:

The focus was to understand whether smartphone sensors could be effectively used to detect behavioural patterns associated to stress and anxiety in non-clinical participants. The reviewed studies provide evidence that smartphone sensors are effective in identifying behavioural patterns associated to anxiety, stress and mild depression.