A Mobile Sensing App to Monitor Youth Mental Health: Observational Pilot Study

Abstract

Background Internalizing disorders are the most common psychiatric problems observed among youth in Canada. 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, which creates a barrier to the accurate assessment of these symptoms in youth. Therefore, novel assessment tools that use objective data need to be developed to meet the highest standards of reliability, feasibility, scalability, and affordability. Mobile sensing technologies, which unobtrusively record aspects of youth 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 This study aims to explore whether passively collected smartphone sensor data can be used to predict internalizing symptoms among youth in Canada. Methods In this study, the youth participants (N=122) completed self-report assessments of symptoms of anxiety, depression, and attention-deficit hyperactivity disorder. Next, the participants installed an app, which passively collected data about their mobility, screen time, sleep, and social interactions over 2 weeks. Then, we tested whether these passive sensor data could be used to predict internalizing symptoms among these youth participants. 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=.02), and fewer outgoing calls (r=−0.244; P=.03). In contrast, more severe anxiety symptoms correlated with less time spent stationary (r=−0.249; P=.01) and greater mobility (r=0.234; P=.02). In addition, youths with higher anxiety scores spent more time on the screen (r=0.203; P=.049). Finally, adding passively collected smartphone sensor data to the prediction models of internalizing symptoms significantly improved their fit. Conclusions Passively collected smartphone sensor data provide a useful way to monitor internalizing symptoms among youth. Although 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 via mobile technology to reduce the burden of internalizing symptoms early on.

Opportunities for Smartphone Sensing in E-Health Research: A Narrative Review

“…The majority of articles (59%) used smartphone sensing to infer mental health conditions. While six articles examined overall mental health [ 13 , 24 , 25 , 26 , 27 , 68 ], other studies examined specific factors such as mood [ 15 , 16 , 17 , 18 , 19 , 20 , 21 , 69 , 70 , 71 , 72 , 73 , 74 , 75 ] and stress [ 76 , 77 , 78 ]. Additionally, studies also examined specific mental health conditions such as depression [ 7 , 8 , 67 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 ], schizophrenia [ 90 , 91 , 92 , 93 ], and bipolar disorder [ 94 , 95 ].…”

“…Several studies have utilized smartphones to remotely collect data from users and gain health insights from these data. Studies have explored how smartphone-based sensing can be used to infer mood [ 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ], physical activity [ 3 , 11 , 22 , 23 ], and mental health [ 13 , 24 , 25 , 26 , 27 ], and also to track the effects of chronic health conditions [ 28 , 29 , 30 , 31 ]. Moreover, software frameworks have also been developed to help researchers use smartphone sensing to conduct their own studies, such as AWARE [ 32 ], Beiwe [ 33 ], and EARS [ 34 ] to name a few.…”

What Are We Measuring When We Evaluate Digital Interventions for Improving Lifestyle? A Scoping Meta-Review

“…Moreover, smartphone-based episodic audio recordings allow analyses of voice and speech features that may be potential vocal markers of stress (118,119). Phone usage and the number of calls, texts, and interactions in online social media can be used as proxies of social contact or interaction (116,(120)(121)(122), while global positioning system (GPS)-based mobility and conversations captured by smartphone microphones were used to estimate social activity and loneliness in individuals with schizophrenia (123). Social support, however, is more complex than social contacts.…”

Predicting Depression in Adolescents Using Mobile and Wearable Sensors: Multimodal Machine Learning–Based Exploratory Study

“…Self-reports of anxiety, depression, and attention-deficit hyperactivity disorder collected; N=122 for 2 weeks of passively sensed data; CES-DC d and SCARED e anxiety assessments were used Explored whether passively collected smartphone sensor data can be used to predict internalizing symptoms among youths in Canada; participants aged between 10 and 21 years MacLeod et al [44] a PHQ-9: Patient Health Questionnaire-9.…”