A personal sensing technology enabled service versus a digital psychoeducation control for primary care patients with depression and anxiety: a pilot randomized controlled trial.

Background: Technology-enabled services (TES; clinical services that include both technology-driven [e.g., personal sensing technologies] and person-powered support elements) may address gaps in depression and anxiety treatments in healthcare settings. The current study: (1) developed a TES tailored for Primary Care patients with depression and/or anxiety, and (2) conducted a pilot randomized controlled trial to assess the efficacy of the TES compared to a digital psychoeducation control app.

Methods: Participants were randomized to either: (1) TES: the "Vira" smartphone app (Ksana Health Inc.), informed by behavioral activation and using passive sensing technology to provide behavioral "insights" and target behaviors associated with mental health symptoms, alongside lay-provider coaching, or (2) Control: the Mood Education mobile app (ME), containing static psychoeducational resources designed to target mental health symptoms. Both apps collected usage data. Participants completed assessments on depression (PHQ-9), anxiety (GAD-7), health-related quality of life (PedsQL), and engagement (TWEETs) at baseline, mid-treatment (week 4), end-of-treatment (week 8), and post-treatment (week 12).

Results: Participants (N = 130) were randomized to receive either the TES (Vira; M_age= 30) or ME (M_age= 33). Linear mixed-effects models determined significant improvements in PHQ-9 and GAD-7 scores for participants across both conditions (ps < 0.001). There was no interactive effect of intervention and time for the PHQ-9 (p = .90) nor the GAD-7 (p = .49). Adjusting for baseline differences and randomization strata, TES participants reported a greater change in a quality of life rating of Physical Functioning (PedsQL) across time (p = .018). TES participants also reported higher levels of engagement and demonstrated higher app usage. However, adjusting for baseline symptom severity, neither app usage nor coach interaction frequency moderated outcomes (ps ≥ 0.2).

Conclusions: While the TES demonstrated superior engagement, improvements in depressive and anxious symptoms for both conditions speak to the potential benefit of both TES and low-intensity psychoeducation treatments in care settings. Future research is needed to better understand which patients might differentially benefit from TESs and broader personal sensing technologies over low-intensity treatments.

Trial registration: ClinicalTrials.gov NCT05406791.