Acceptability and effectiveness of a chatbot for delivering Cognitive Behavioral Therapy (CBT) to adolescents with depression and anxiety during the COVID-19 pandemic (Preprint)

Abstract

BACKGROUND Depression, anxiety and related suicidal ideation and self-harm are common among adolescents, and have increased in prevalence and severity during the pandemic to crisis levels, exacerbated by the long-standing workforce shortage of child mental health professionals. As a result, primary care providers are often called on to provide first-line care for these youth. Digital health interventions extend mental health specialty care to youth with moderately severe symptoms, but few are evidence-based. Here, we describe the feasibility of delivering an evidence-based intervention that utilizes a relational conversational agent embedded in a smartphone application (app) to deliver cognitive behavioral therapy (CBT) to adolescents presenting to their PCP for treatment of moderately severe depression and/or anxiety. OBJECTIVE In this 12-week pilot randomized controlled study, we evaluated the feasibility of the app-based intervention to adolescents ages 13-17 years with moderate depressive symptoms presenting in ambulatory pediatric primary care clinics. METHODS We evaluated change in depressive symptom severity as measured by the 9-item Patient Health Questionnaire (PHQ-9), anxiety symptoms via the 7-item Generalized Anxiety Disorder Questionnaire (GAD-7) and self-efficacy for mental health via the Mental Health Self-efficacy Scale (MHSES) at 4 and 12 weeks. Data on acceptability, feasibility and usability were collected from participants, and qualitative interviews were conducted with referring primary care providers (PCPs). RESULTS The pilot randomized 18 participants to treatment plus usual care (n=10) or usual care alone (n=8). There were no difference between groups on baseline characteristics, and all randomized participants completed the program. Although participants in the active treatment group experienced a greater reduction in depressive symptoms than the usual care group, mental health outcomes between groups was not statistically significant. Teen- and parent-reported usability, feasibility and acceptability of the app was high; PCPs reported preference for introducing the app early in the course of care for individuals presenting with mild or moderate symptoms. CONCLUSIONS In this small randomized study, we demonstrated the feasibility, acceptability, usability and safety of using a CBT-based chatbot for adolescents presenting with moderate depressive symptoms in real-world primary care settings. Further study is needed to fully determine effectiveness of both the intervention and implementation in primary care settings. CLINICALTRIAL NCT04603053 (https://clinicaltrials.gov/ct2/show/NCT04603053)

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 2 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.