Tracking and Predicting Depressive Symptoms of Adolescents Using Smartphone-Based Self-Reports, Parental Evaluations, and Passive Phone Sensor Data: Development and Usability Study

Abstract

Background: Depression carries significant financial, medical, and emotional burden on modern society. Various proof-of-concept studies have highlighted how apps can link dynamic mental health status changes to fluctuations in smartphone usage in adult patients with major depressive disorder (MDD). However, the use of such apps to monitor adolescents remains a challenge.

Objective: This study aimed to investigate whether smartphone apps are useful in evaluating and monitoring depression symptoms in a clinically depressed adolescent population compared with the following gold-standard clinical psychometric instruments: Patient Health Questionnaire (PHQ-9), Hamilton Rating Scale for Depression (HAM-D), and Hamilton Anxiety Rating Scale (HAM-A).

Methods: We recruited 13 families with adolescent patients diagnosed with MDD with or without comorbid anxiety disorder. Over an 8-week period, daily self-reported moods and smartphone sensor data were collected by using the Smartphone- and OnLine usage-based eValuation for Depression (SOLVD) app. The evaluations from teens' parents were also collected. Baseline depression and anxiety symptoms were measured biweekly using PHQ-9, HAM-D, and HAM-A.

Results: We observed a significant correlation between the self-evaluated mood averaged over a 2-week period and the biweekly psychometric scores from PHQ-9, HAM-D, and HAM-A (0.45≤|r|≤0.63; P=.009, P=.01, and P=.003, respectively). The daily steps taken, SMS frequency, and average call duration were also highly correlated with clinical scores (0.44≤|r|≤0.72; all P<.05). By combining self-evaluations and smartphone sensor data of the teens, we could predict the PHQ-9 score with an accuracy of 88% (23.77/27). When adding the evaluations from the teens' parents, the prediction accuracy was further increased to 90% (24.35/27).

Conclusions: Smartphone apps such as SOLVD represent a useful way to monitor depressive symptoms in clinically depressed adolescents, and these apps correlate well with current gold-standard psychometric instruments. This is a first study of its kind that was conducted on the adolescent population, and it included inputs from both teens and their parents as observers. The results are preliminary because of the small sample size, and we plan to expand the study to a larger population.

Keywords: SOLVD-Teen and SOLVD-Parent App; adolescent depression; parental input; self-evaluation; sensory data; smartphone monitoring.

Figure 1

Screenshots of the Smartphone- and OnLine usage–based eValuation for Depression (SOLVD)-Teen (left) and SOLVD-Parent (right) apps. The user input is converted to a numerical score between 0 and 100. The frontend of the SOLVD-Parent app is modified to capture both the parents’ self-evaluations and their perceived well-being of their kids.

Figure 2

Study design, data collection protocol, and study timeline for the Smartphone- and OnLine usage–based eValuation for Depression (SOLVD)-Teen trial. Both SOLVD-Teen and SOLVD-Parent apps have a user-facing module and a background mobile logger. Each subject enrolled in the study for 8 weeks.

Figure 3

Definition and equations of location variance and normalized entropy.

Figure 4

Pearson correlation coefficients between self-reports, parental inputs, and psychometric scores for the adolescent patients. On the basis of the significance level, *P<.1, **P<.05, and ***P<.01. HAM-A: Hamilton Anxiety Rating Scale; HAM-D: Hamilton Rating Scale for Depression; PHQ-9: Patient Health Questionnaire-9.

Figure 5

Pearson correlation coefficients between mobility and psychometric scores for the adolescent patients. On the basis of the significance level, *P<.1, **P<.05, and ***P<.01. HAM-A: Hamilton Anxiety Rating Scale; HAM-D: Hamilton Rating Scale for Depression; PHQ-9: Patient Health Questionnaire-9.

Figure 6

Pearson correlation coefficients between social interactions, living context, and psychometric scores for the adolescent patients. On the basis of the significance level, *P<.1, **P<.05, and ***P<.01. HAM-A: Hamilton Anxiety Rating Scale; HAM-D: Hamilton Rating Scale for Depression; PHQ-9: Patient Health Questionnaire-9.