JMIR Publications

ABSTRACT

Background:

Adolescent mental health needs remain largely unmet, particularly among youth in geographically underserved communities. Digital peer support is a promising approach to expanding mental health support, yet real-world evidence on engagement patterns and clinical outcomes remains limited.

Objective:

This study aimed to: 1) describe the demographic and clinical characteristics of enrolled adolescents and young adults and patterns of platform engagement; 2) identify demographic and clinical predictors of engagement intensity; and 3) describe within-measure pre-post changes in depressive symptoms, anxiety symptoms, and well-being among adolescents and young adults with paired assessments.

Methods:

This retrospective observational study analyzed secondary data from 5,673 adolescents and young adults enrolled in Somethings from January 29, 2023, through June 3, 2026. Engagement was operationalized as communication days per month. Standardized clinical outcome measures (Patient Health Questionnaire-9 [PHQ-9], Generalized Anxiety Disorder-7 [GAD-7], World Health Organization-5 Well-Being Index [WHO-5]) were administered as part of routine measurement-based care. Ordinary least squares regression was used to examine predictors of engagement, and pre-post change scores were evaluated across four assessment windows.

Results:

The sample was predominantly female (81.1%, n = 4,600) with a mean age of 16.4 years and moderate-to-severe symptom burden at baseline (PHQ-9 M = 12.6; GAD-7 M = 10.7; WHO-5 M = 44.8). Of enrolled adolescents and young adults, 98.1% (n = 5,565) had at least one recorded engagement with the platform, with a mean of 4.56 communication days per month. Female sex was a significant positive predictor of engagement intensity (β = 0.64, p = .004). Hispanic and Latino adolescents and young adults also engaged significantly more frequently than White non-Hispanic adolescents and young adults (β = 0.61, p = .019). HPSA shortage score was significantly and positively associated with engagement intensity (β = 0.08, p < .001). Baseline symptom severity was not associated with engagement intensity (β = 0.04, p = .914). Within-measure paired scores improved significantly from baseline to follow-up across the PHQ-9, GAD-7, and WHO-5. At last assessment, 31.9% (n = 237/742), 36.6% (n = 222/606), and 38.0% (n = 167/442) of adolescents and young adults met clinically meaningful improvement thresholds on the PHQ-9, GAD-7, and WHO-5, respectively.

Conclusions:

Text-based peer support shows promise as a scalable approach to expanding mental health access for underserved adolescents. Prospective, controlled studies are needed to establish causal efficacy.