Effectiveness of a chatbot for eating disorders prevention: A randomized clinical trial.

OBJECTIVE: Prevention of eating disorders (EDs) is of high importance. However, digital programs with human moderation are unlikely to be disseminated widely. The aim of this study was to test whether a chatbot (i.e., computer program simulating human conversation) would significantly reduce ED risk factors (i.e., weight/shape concerns, thin-ideal internalization) in women at high risk for an ED, compared to waitlist control, as well as whether it would significantly reduce overall ED psychopathology, depression, and anxiety and prevent ED onset. METHOD: Women who screened as high risk for an ED were randomized (N = 700) to (1) chatbot based on the StudentBodies© program; or (2) waitlist control. Participants were followed for 6 months. RESULTS: For weight/shape concerns, there was a significantly greater reduction in intervention versus control at 3- (d = -0.20; p = .03) and 6-m-follow-up (d = -0.19; p = .04). There were no differences in change in thin-ideal internalization. The intervention was associated with significantly greater reductions than control in overall ED psychopathology at 3- (d = -0.29; p = .003) but not 6-month follow-up. There were no differences in change in depression or anxiety. The odds of remaining nonclinical for EDs were significantly higher in intervention versus control at both 3- (OR = 2.37, 95% CI [1.37, 4.11]) and 6-month follow-ups (OR = 2.13, 95% CI [1.26, 3.59]). DISCUSSION: Findings provide support for the use of a chatbot-based EDs prevention program in reducing weight/shape concerns through 6-month follow-up, as well as in reducing overall ED psychopathology, at least in the shorter-term. Results also suggest the intervention may reduce ED onset. PUBLIC SIGNIFICANCE: We found that a chatbot, or a computer program simulating human conversation, based on an established, cognitive-behavioral therapy-based eating disorders prevention program, was successful in reducing women's concerns about weight and shape through 6-month follow-up and that it may actually reduce eating disorder onset. These findings are important because this intervention, which uses a rather simple text-based approach, can easily be disseminated in order to prevent these deadly illnesses. TRIAL REGISTRATION: OSF Registries; https://osf.io/7zmbv.

Evaluating change in body image concerns following a single session digital intervention.

Many young individuals at risk for eating disorders spend time on social media and frequently search for information related to their body image concerns. In a large randomized study, we demonstrated that a guided chat-based intervention could reduce weight and shape concerns and eating disorder pathology. The goal of the current study was to determine if a modified single session mini-course, derived from the aforementioned chat-based intervention, could reduce body image concerns among individuals using eating disorder related search terms on a social media platform. Over a two-month period of prompting individuals, 525 people followed the link to the web-based application where the intervention was hosted and subsequently completed the mini-course. This resulted in a significant improvement on the one-time body image satisfaction question pre-to post intervention (p < .001) with a moderate effect size (Cohen's d = 0.54). Additionally, individuals completing the program showed significant improvement on motivation to change their body image (p < .001) with a small effect size (Cohen's d = 0.28). Additionally, users reported that the program was enjoyable and easy to use. These results suggest that a single session micro-intervention, offered to individuals on social media, can help improve body image.

The Challenges in Designing a Prevention Chatbot for Eating Disorders: Observational Study.

BACKGROUND: Chatbots have the potential to provide cost-effective mental health prevention programs at scale and increase interactivity, ease of use, and accessibility of intervention programs. OBJECTIVE: The development of chatbot prevention for eating disorders (EDs) is still in its infancy. Our aim is to present examples of and solutions to challenges in designing and refining a rule-based prevention chatbot program for EDs, targeted at adult women at risk for developing an ED. METHODS: Participants were 2409 individuals who at least began to use an EDs prevention chatbot in response to social media advertising. Over 6 months, the research team reviewed up to 52,129 comments from these users to identify inappropriate responses that negatively impacted users' experience and technical glitches. Problems identified by reviewers were then presented to the entire research team, who then generated possible solutions and implemented new responses. RESULTS: The most common problem with the chatbot was a general limitation in understanding and responding appropriately to unanticipated user responses. We developed several workarounds to limit these problems while retaining some interactivity. CONCLUSIONS: Rule-based chatbots have the potential to reach large populations at low cost but are limited in understanding and responding appropriately to unanticipated user responses. They can be most effective in providing information and simple conversations. Workarounds can reduce conversation errors.

Pilot randomized trial of self-guided virtual reality exposure therapy for social anxiety disorder.

BACKGROUND: Virtual reality exposure therapy (VRE) has shown promising efficacy for the treatment of social anxiety disorder (SAD) and related comorbidities. However, most trials conducted to date were therapist-led, and little is known about the efficacy of self-guided VRE. Therefore, this randomized controlled trial (RCT) aimed to determine the efficacy of a self-directed VRE for SAD. METHOD: Forty-four community-dwelling or undergraduate adults diagnosed with SAD based on the Mini International Neuropsychiatric Interview were randomly assigned to VRE designed to last four sessions or more (n = 26) or waitlist (WL; n = 18). Self-reported SAD severity (Social Phobia Diagnostic Questionnaire and Social Interaction Anxiety Scale), job interview anxiety (Measure of Anxiety in Selection Interviews), trait worry (Penn State Worry Questionnaire), and depression symptoms (Patient Health Questionnaire-9) were administered at baseline, post-treatment, 3-month-follow-up (3MFU), and 6-month-follow-up (6MFU). Piecewise multilevel modeling analyses were conducted to manage clustering in the data. RESULTS: VRE vs. WL resulted in greater reductions in SAD symptom severity, job interview fear, and trait worry, with moderate-to-large effect sizes (Hedge's g = -0.54 to -1.11) from pre-to-post treatment. Although significant between-group differences did not emerge for change in depression, VRE led to change in depression, whereas waitlist did not. These gains were also maintained at 3MFU and 6MFU. Further, facets of presence increased during the course of VRE (g = 0.36-0.45), whereas cybersickness decreased (g = -0.43). DISCUSSION: Brief, self-guided VRE might ameliorate SAD and comorbid worry, for young-to-middle-aged adults with SAD. Other theoretical and practical implications were also discussed.