JMIR Publications

ABSTRACT

Background:

Misuse of substances is common, can be serious and costly to society, and often goes untreated due to barriers accessing care. Digital health programs offer greater public health reach. Woebot is a mental health digital solution informed by Cognitive Behavioral Therapy and built upon an artificial intelligence (AI) driven platform to deliver tailored content to users. In a prior 2-week randomized controlled trial, Woebot alleviated depressive symptoms.

Objective:

We adapted Woebot for the treatment of substance use disorders (W-SUDs), adding elements from Dialectical Behavior Therapy and Motivational Interviewing. W-SUDs is an 8-week program with mood, craving, and pain tracking and modules (psychoeducational lessons and psychotherapeutic skills/tools). In a single-group pre/post design, we report on feasibility, acceptability, and preliminary efficacy of W-SUDs.

Methods:

Adults (ages 18-65 years) residing in the US who screened positive on the CAGE-AID (2+) without major health contraindications were enrolled March 27 - May 6, 2020. Enrollment (N=101) doubled the recruitment goal. The sample averaged 36.8 years of age (SD 10.0); 75.2% were female; 78.2% non-Hispanic White; and 72.3% employed. Most (68.3%) identified alcohol as their primary problematic substance, followed by cannabis (19.8%); 36.7% identified multiple problematic substances; and 72.3% reported a lifetime mental illness. Nearly all (98.0%) were sheltering-in-place with the COVID-19 pandemic.

Results:

Participants’ use of W-SUDs averaged 15.7 (SD 14.2) days, 12.1 (SD=8.3) modules, and 600.7 (SD 556.5) sent messages; 94.0% (562/598) of completed psychoeducational lessons were rated positively. From treatment start to end, in-app craving ratings were reduced by half (87/101 reporting; OR 0.48, 95% CI 0.32-0.73). Post-treatment assessment completion was 50% (n=51), with retention better among those who initially screened higher on the CAGE-AID. From pre- to post-treatment, confidence to resist urges to use significantly increased (mean 46.0, SD 19.3 to mean 62.8, SD 22.4) and past-month substance use occasions (mean 29.5, SD 14.0 to mean 20.1, SD 17.8), AUDIT-C (mean 5.3, SD 2.9 to mean 4.0, SD 3.2), DAST-10 (mean 2.9, SD 2.7 to mean 1.7, SD 2.4), PHQ-8 depression (mean 10.7, SD 5.3 to mean 8.6, SD 5.1), and GAD-7 anxiety (mean 10.1, SD 5.7 to mean 7.8, SD 5.3), and cravings (68.6% vs. 47.1% moderate-to-extreme) significantly decreased (all p-values<.05). Most would recommend W-SUDs to a friend (39/51, 76%) and received service they desired (41/51, 80%). Fewer felt W-SUDs met most/all of their needs (22/51, 43%). The one serious adverse event (hospitalization) was deemed unrelated to study participation.

Conclusions:

W-SUDs was feasible to deliver, engaging, and acceptable; and associated with significant improvements in substance use, confidence, cravings, depression, and anxiety. Study attrition was high. Future research will evaluate W-SUDs in a randomized controlled trial with a more diverse sample and with use of greater strategies for study retention. Clinical Trial: NCT04096001