JMIR Publications

ABSTRACT

Background:

The quality of user interaction with therapeutic tools has been positively associated with treatment response; however, no studies have investigated these relationships for voice-based digital tools.

Objective:

This study evaluated the relationships of objective and subjective user interaction measures as well as treatment response on Lumen, a novel virtual voice-based coach, delivering Problem-solving Treatment (PST) to patients with mild-to-moderate depression and/or anxiety.

Methods:

In a pilot trial, 42 adults with clinically significant depression (PHQ9) and/or anxiety (GAD7) symptoms received Lumen, a virtual coach delivering 8 problem-solving treatment (PST) sessions. Objective (number of conversational breakdowns) and subjective user interaction measures (task-related workload, user experience, treatment alliance) were obtained for each session. Changes in PHQ9 and GAD7 scores at each ensuing session after session 1 measured treatment response.

Results:

Participants were 38.9 (SD=12.9) years, 67% women, 19% Black, 29% Latino, 12% Asian. Means (SDs) across sessions showed: breakdowns (2.3-6.5 [1.8-4.9]) decreasing over sessions; favorable task-related workload (14.5-17.6 [4.1-6.4]) decreasing over sessions, neutral-to-positive user experience (0.5-1.1 [0.9-1.5]), and high treatment alliance (5.0-5.3 [0.9-1.4]). PHQ9 (Ptrend=0.001) and GAD7 scores (Ptrend=0.01) improved significantly over sessions. Treatment alliance correlated with improvements in PHQ9 (Pearson’s r=-0.02 to -0.46) and GAD7 (r=0.03 to -0.57) across sessions, whereas breakdowns and task-related workload did not. Mixed models showed that participants with higher individual mean treatment alliance had greater improvements in PHQ9 (β=-1.13, 95% CI=-2.16, -0.10) and GAD7 (β=-1.17, 95% CI=-2.13, -0.20).

Conclusions:

Participants had declined conversational breakdowns and largely favorable user interactions with Lumen across sessions. Conversational breakdowns were not associated with subjective user interaction measures or treatment response, highlighting how participants adapted and effectively used Lumen. Individuals experiencing higher treatment alliance had greater improvements in depression and anxiety. Clinical Trial: The study was registered on ClinicalTrials.gov (NCT# 04524104).