Development and usability testing of a chatbot to promote mental health services use among individuals with eating disorders following screening

Abstract

Objective: A significant gap exists between those who need and those who receive care for eating disorders (EDs). Novel solutions are needed to encourage service use and address treatment barriers. This study developed and evaluated the usability of a chatbot designed for pairing with online ED screening. The tool aimed to promote mental health service utilization by improving motivation for treatment and selfefficacy among individuals with EDs.Methods: A chatbot prototype, Alex, was designed using decision trees and theoretically-informed components: psychoeducation, motivational interviewing, personalized recommendations, and repeated administration. Usability testing was conducted over four iterative cycles, with user feedback informing refinements to the next iteration. Post-testing, participants (N= 21) completed the System Usability Scale (SUS), the Usefulness, Satisfaction, and Ease of Use Questionnaire (USE), and a semi-structured interview.Results: Interview feedback detailed chatbot aspects participants enjoyed and aspects necessitating improvement. Feedback converged on four themes: user experience, chatbot qualities, chatbot content, and ease of use. Following refinements, users described Alex as humanlike, supportive, and encouraging. Content was perceived as novel and personally relevant. USE scores across domains were generally above average (5 out of 7), and SUS scores indicated "good" to "excellent" usability across cycles, with the final iteration receiving the highest average score. Discussion: Overall, participants generally reflected positively on interactions with Alex, including the initial version. Refinements between cycles further improved user experiences. This study provides preliminary evidence of the feasibility and acceptance of a chatbot designed to promote motivation for and use of services among individuals with EDs. Public Significance: Low rates of service utilization and treatment have been observed among individuals following online eating disorder screening. Tools are

Decreasing the public health burden of eating disorders: Commentary Schleider et al. (2023)

“…In collaboration with NEDA and Cass (previously called X2AI), a mental health chatbot company, we developed a chatbot named Alex designed primarily as an SSI, for use by those identified by the NEDA screen as having an ED but reporting not being in treatment (Shah et al, 2022). Alex was designed to deliver four theoretically informed components to target service use: psychoeducation, motivational interviewing, and personalized services recommendations based on preferences-all intended to be delivered as an SSI immediately following screening-along with repeated check-ins to ask about service seeking and offer support and troubleshooting in the weeks following screening.…”

“…Alex was designed to deliver four theoretically informed components to target service use: psychoeducation, motivational interviewing, and personalized services recommendations based on preferences—all intended to be delivered as an SSI immediately following screening—along with repeated check‐ins to ask about service seeking and offer support and troubleshooting in the weeks following screening. Alex underwent an iterative, user‐centered design process, in order to ensure the chatbot would meet the needs of its diverse end‐users, and overall, participants reflected very positively on the bot (Shah et al, 2022). We wanted to know, though, which components of the chatbot may be uniquely important in increasing services use, and so we conducted an optimization trial, randomizing participants using a factorial design to a chatbot with some combination of those elements (i.e., randomized to have each turned on or off).…”

Evidence-Based Assessments for Transdiagnostic Eating Disorder Symptoms: Guidelines for Current Use and Future Directions

“…Research suggests early detection and treatment of ED cognitions and behaviors (i.e., symptoms) is associated with better health and psychological outcomes, including shorter duration of illness, decreased symptom severity, and increased ED recovery rates (Austin et al, 2021; Treasure et al, 2015). In addition, some research suggests that simply screening for EDs may not significantly facilitate increased treatment-seeking behavior among people at risk of an ED, indicating a possible need for the simultaneous provision of screening and treatment interventions (Shah et al, 2022). Furthermore, EDs are most often detected and diagnosed by a primary care provider (PCP; Striegel-Moore et al, 2008), signifying the need for accurate and comprehensive ED screening assessments that can be used within primary and other health care settings.…”

Argumentation Effect of a Chatbot for Ethical Discussions about Autonomous AI Scenarios

“…The healthcare sector has also witnessed considerable attention in chatbot research. For instance, Shah et al devised a chatbot using decision trees and rule-based systems to assist individuals with eating disorders [11]. Concurrently, Rebelo et al developed a chatbot-based patient education system focusing on radiotherapy, employing IBM Watson as their platform of choice [12].…”