JMIR Publications

ABSTRACT

Background:

Internalizing disorders are the most common psychiatric problems in Canadian youth. Sadly, youth with internalizing disorders often avoid seeking clinical help and rarely receive adequate treatment. Current methods of assessing internalizing disorders usually rely on subjective symptom ratings, but internalizing symptoms are frequently underreported, creating a barrier to the accurate assessment of these symptoms in youth. Therefore, novel assessment tools need to be developed meeting the highest standards of reliability, feasibility, scalability, and affordability using objective data. Mobile sensing technologies, which unobtrusively record aspects of youth’s behaviors in their daily-lives with the potential to make inferences about their mental health states, offer a possible method of addressing this assessment barrier.

Objective:

The objective of the study was to explore if passively collected smartphone sensor data can be used to predict internalizing symptoms of youth.

Methods:

In the current study, youth (n=122) completed self-report assessments of symptoms of anxiety, depression, and attention-deficit/hyperactivity disorder. Next youth installed an app, which passively collected data about their mobility, screen time, sleep and social interactions over 2 weeks. Afterwards, we tested whether these passive sensor data can be used to predict youth’s internalizing symptoms.

Results:

More severe depressive symptoms correlated with more time spent stationary (r= 0.293; P = .003), less mobility (r = 0.271; P = .006), higher light intensity during the night (r= -0.227; P = .022), and fewer outgoing calls (r = -0.244; P = .026). In contrast, more severe anxiety symptoms correlated with less time spent stationary (r = -0.249; P = .013) and more mobility (r = 0.234; P = .018). In addition, youth with higher anxiety scores spent also more time on screen (r = 0.203; P = .049). Finally, adding passively collected smartphone sensor data to prediction models of internalizing symptoms significantly improved their fits.

Conclusions:

Passively collected smartphone sensor data represents a useful way to monitor internalizing symptoms in youth. While the results replicated findings from adult populations, to ensure clinical utility they still need to be replicated in larger samples of youth. The work also highlights intervention opportunities through mobile technology to reduce the burden of internalizing symptoms early-on.