Chatbot-Delivered Cognitive Behavioral Therapy in Adolescents With Depression and Anxiety During the COVID-19 Pandemic: Feasibility and Acceptability Study

Abstract

Background Symptoms of depression and anxiety, suicidal ideation, and self-harm have escalated among adolescents to crisis levels during the COVID-19 pandemic. As a result, primary care providers (PCPs) are often called on to provide first-line care for these youth. Digital health interventions can extend mental health specialty care, but few are evidence based. We evaluated the feasibility of delivering an evidence-based mobile health (mHealth) app with an embedded conversational agent to deliver cognitive behavioral therapy (CBT) to symptomatic adolescents presenting in primary care settings during the pandemic. Objective In this 12-week pilot study, we evaluated the feasibility of delivering the app-based intervention to adolescents aged 13 to 17 years with moderate depressive symptoms who were treated in a practice-based research network (PBRN) of academically affiliated primary care clinics. We also obtained preliminary estimates of app acceptability, effectiveness, and usability. Methods This small, pilot randomized controlled trial (RCT) evaluated depressive symptom severity in adolescents randomized to the app or to a wait list control condition. The primary end point was depression severity at 4-weeks, measured by the 9-item Patient Health Questionnaire (PHQ-9). Data on acceptability, feasibility, and usability were collected from adolescents and their parent or legal guardian. Qualitative interviews were conducted with 13 PCPs from 11 PBRN clinics to identify facilitators and barriers to incorporating mental health apps in treatment planning for adolescents with depression and anxiety. Results The pilot randomized 18 participants to the app (n=10, 56%) or to a wait list control condition (n=8, 44%); 17 participants were included in the analysis, and 1 became ineligible upon chart review due to lack of eligibility based on documented diagnosis. The overall sample was predominantly female (15/17, 88%), White (15/17, 88%), and privately insured (15/17, 88%). Mean PHQ-9 scores at 4 weeks decreased by 3.3 points in the active treatment group (representing a shift in mean depression score from moderate to mild symptom severity categories) and 2 points in the wait list control group (no shift in symptom severity category). Teen- and parent-reported usability, feasibility, and acceptability of the app was high. PCPs reported preference for introducing mHealth interventions like the one in this study early in the course of care for individuals presenting with mild or moderate symptoms. Conclusions In this small study, we demonstrated the feasibility, acceptability, usability, and safety of using a CBT-based chatbot for adolescents presenting with moderate depressive symptoms in a network of PBRN-based primary care clinics. This pilot study could not establish effectiveness, but our results suggest that further study in a larger pediatric population is warranted. Future study inclusive of rural, socioeconomically disadvantaged, and underrepresented communities is needed to establish generalizability of effectiveness and identify implementation-related adaptations needed to promote broader uptake in pediatric primary care. Trial Registration ClinicalTrials.gov NCT04603053; https://clinicaltrials.gov/ct2/show/NCT04603053

Use of automated conversational agents in improving young population mental health: a scoping review

“…Of the 25 studies, 19 were recently published (between 2020 and 2023) 8 – 10 , 12 , 26 – 40 . Studies were conducted predominantly in the US ( n = 12) 11 , 12 , 27 , 28 , 33 , 34 , 38 , 41 – 45 , followed by Europe ( n = 5) 10 , 26 , 29 , 32 , 35 , Asia ( n = 4) 9 , 31 , 36 , 39 , New Zealand ( n = 2) 37 , 40 , and Australia ( n = 1) 30 .…”

“…In total, there were 21 different agents described in the included studies. Only 3 of the CA were the focus of more than one study – Paro 11 , 41 , 45 , Nao 8 , 38 , and Woebot 12 , 42 . These automated CAs were predominantly disembodied chatbots ( n = 15) 10 , 26 , 28 – 32 , 35 – 37 , 40 , 42 – 44 , followed by robots ( n = 7) 8 , 9 , 33 , 34 , 38 , 41 , 45 .…”

“…In an educational context, they have been employed as a tool to reduce problems such as general distress or performance anxiety 10 , 11 . Automated CAs have also been used to prevent or to treat depression and anxiety in the general or psychiatric population 12 .…”

A Relational Agent Intervention for Adolescents Seeking Mental Health Treatment: Protocol for a Randomized Controlled Trial

“…Therapeutic alliance, a construct familiar in psychotherapeutic treatment outcomes research, refers to the therapeutic relationship and affective bond between provider and patient and is associated with the efficacy of psychotherapy [26,27]. A randomized controlled pilot among adolescents aged 13-17 years (n=17) demonstrated W-GenZD's preliminary feasibility and utility in an outpatient primary care pediatric setting [28], but further evaluation of its feasibility and acceptability as well as clinical efficacy is warranted.…”

Digital technology and mental health during the COVID-19 pandemic: a narrative review with a focus on depression, anxiety, stress, and trauma

“…A 12 weeks randomized controlled trial during the pandemic evaluated the feasibility and efficacy of using a natural language and machine learning chat-based app (W-GenZ) for mood tracking and for facilitating tailored intervention in 13 to 17 years-olds with moderate symptoms of depression (58). The outcome of the study revealed that use of the app was feasible and acceptable to both the teenagers and their parents, and depressive symptoms in the young participants showed a shift from the moderate to mild category by 4 weeks in the treatment arm compared to the control group, as determined using Patient Health Questionnaire (PHQ-9) scores.…”