AI chatbot coaches teens through anxiety homework

Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.

INCLUSION CRITERIA (youth participants): 1. Has a clinical or subclinical anxiety or related disorder (e.g., panic disorder, social anxiety disorder, obsessive-compulsive disorder) for which exposure-based CBT is indicated. 2. Between the ages of 12 and 22 years at the time of enrollment. 3. Is either (a) currently receiving exposure-based CBT (or CBT in which exposure-based content is expected to be a core component) at a participating MGB outpatient program, or (b) on the waitlist for a participating program and expected to initiate exposure-based CBT in the near future. 4. Sufficient ability to communicate in English (study materials, measures, and the BraveBot interface are currently English-only). For minors, at least one parent/guardian must be sufficiently proficient in English to understand the consent information. 5. The youth and/or caregiver has access to a device that can receive SMS text reminders and open secure web links to complete exposure homework and brief post-exposure surveys. EXCLUSION CRITERIA (present at enrollment): 1. Symptoms of suicidal or homicidal ideation, psychosis, or a non-anxiety-related primary mental health concern (i.e., where treatment for a disorder other than anxiety is indicated prior to exposure treatment, or independent exposure homework is not clinically appropriate as determined by the treating clinician). Examples include: current substance use or dependence requiring specialized or higher-level care that must be addressed before or instead of anxiety-focused exposure-based CBT; and current eating disorder severe enough to require intensive/specialized treatment such that exposure-based CBT for anxiety/OCD is not the appropriate primary focus. 2. Youth is unable to complete homework independently. 3. Any other condition or circumstance for which treatment for another primary psychiatric condition is clearly indicated prior to anxiety-focused exposure-based CBT, or for which out-of-session exposure homework is considered unsafe or inappropriate. The investigators will also recruit up to 10 clinicians at participating programs who may use the BraveBot system with their patients (who have enrolled in the study independently) and complete brief baseline and end-of-study surveys.