BACKGROUND
Eating disorders are a global concern and access to early treatment is critical to improve prognosis. Single session interventions have been proposed as an opportunity to provide short term support to people on waitlists for eating disorder treatment, however, there are not enough clinicians to provide this early intervention. Conversational artificial intelligence agents or “chatbots” reflect a unique opportunity to fill this gap in service provision.
OBJECTIVE
To co-design a novel chatbot capable of delivering a single session intervention for people on the waitlist for eating disorder treatment across the eating disorder diagnostic spectrum and ascertain its preliminary acceptability and feasibility.
METHODS
The study followed the design process of the Double Diamond model including four phases: discover, define, develop, and deliver. The study involved the co-design of a chatbot with 17 participants in total; 10 adults with a lived experience of eating disorders and 7 eating disorder clinicians, by conducting interviews and workshops with the participants. Feedback from the interviews and workshops of each phase informed the ideas and development of the next phase of the study. A final prototype of a single session intervention chatbot was presented to the participants in the deliver phase.
RESULTS
Qualitative thematic analysis identified four main themes that were present across the four rounds of interviews/workshops: conversational tone, safety and risk management, user journey and session structure, and content.
CONCLUSIONS
Overall, the feedback on the single session intervention chatbot was positive throughout the Double Diamond process from both people with a lived experience of eating disorders and clinicians. Incorporating the feedback across the four themes and four phases allowed for refinement of the chatbot. Further research is required to evaluate the chatbot’s efficacy in early treatment settings.
CLINICALTRIAL
N/A