JMIR Publications

ABSTRACT

Background:

Early treatment is critical to improve eating disorder prognosis. Single session interventions (SSIs) have been proposed as a strategy to provide short term support to people on waitlists for eating disorder treatment, however, it is not always possible to access this early intervention. We co-designed and developed a rule-based chatbot, called ED ESSI™, which delivered an SSI, and previously demonstrated its acceptability and feasibility. However, the effectiveness of ED ESSI™ is yet to be investigated.

Objective:

The overall aim of this study was to investigate the effectiveness of an SSI delivered by ED ESSI™ chatbot. Specifically, the chatbot’s impacts on eating disorder pathology, psychosocial impairment, depression, anxiety, stress and motivation for change/treatment in individuals aged 16 and over on waitlists for treatment for eating disorders of all types.

Methods:

This was a multi-centre two-armed randomized controlled trial (RCT) with 60 people on waitlists for eating disorder treatment in the chatbot intervention group (n=30) or the control group (n=30). The ED ESSI™ chatbot guided participants through a 30-minute SSI of assessment and psychoeducation while the control group received online information on the same core topics covered in the SSI. There were 4 timepoints – pre-intervention/baseline (T1), post-intervention which was within 72 hours of baseline (T2), 1-month post-baseline (T3) and 3 months post-baseline (T4). Eating disorder pathology (primary outcome), and psychosocial impairment, depression, anxiety and stress (secondary outcomes) were measured at T1, T3 and T4, and motivation for change/treatment (secondary outcome) was measured at all 4 timepoints. The system usability scale was also employed at T2 for the chatbot intervention group only.

Results:

The chatbot intervention induced significantly greater reductions compared to the control group in the primary outcome of eating disorder pathology, as well as secondary outcomes of psychosocial impairment, depression and anxiety over the 1- and 3-month time points with small to moderate effects. Chatbot usage also induced an increase in participant confidence in their ability to change (secondary outcome) immediately after use (T2). The chatbot was rated as “excellent” in terms of usability. Moreover, a significantly higher proportion of participants in the chatbot group entered treatment by 3 months, upon the opportunity being offered to them, compared to the control.

Conclusions:

The SSI delivered by ED ESSI™ chatbot promptly induced improvements in eating disorder pathology, psychosocial impairment, depression and anxiety detectable at 1 month and maintained to 3 months. This was not the case for the control, which replicated typical waitlist conditions. ED ESSI™ potentially represents an effective, accessible and scalable form of early intervention for people aged 16 and over waiting for eating disorder treatment. However, further research is needed to determine the longer-term effectiveness of ED ESSI™. Clinical Trial: Australia New Zealand Clinical Trial Registry ACTRN12623000680662; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=386003&isReview=true