HIV and Substance use reduction for Youth Experiencing Homelessness: Intervention Message Development and Acceptability (Preprint)

BACKGROUND Youth experiencing homelessness (YEH) face heightened vulnerability to HIV infection and substance use due to complex structural, psychosocial, and behavioral factors. Despite increased mobile phone access among YEH, few mHealth interventions have been tailored to their unique needs, and fewer still have applied behavioral theory to inform message development. OBJECTIVE This study aimed to develop and refine theory-driven, tailored HIV prevention and substance use reduction messages for use in a Just-in-Time Adaptive Intervention (JITAI) app, MYRIDE, designed for YEH aged 18–25. METHODS Building on a 2018 pilot study that developed and tested prevention messages grounded in Social Cognitive Theory and HIV communication strategies, we convened a new Youth Working Group (YWG) in 2024. Participants were recruited from shelters and drop-in centers in southeast Texas. Messages were reviewed, rated, and revised across four structured meetings. An AI tool, Microsoft Copilot, was used to generate additional messages based on top-rated messages, and these were reviewed for relevance and acceptability. Ratings and feedback guided the selection and refinement of messages for final integration into the MYRIDE app. RESULTS The initial message pool included 386 pilot-tested messages across seven content domains. Following study team expansion and message generation via Copilot, the total message set increased to 934. Of these, 886 were rated acceptable or highly acceptable by YWG participants. AI-generated messages demonstrated a 99% approval rate. The finalized set was integrated into the MYRIDE JITAI app to support personalized, real-time intervention delivery. CONCLUSIONS Co-developing messages with YEH and leveraging AI tools proved feasible and effective for tailoring HIV prevention and substance use content. This approach supports scalable mHealth interventions for marginalized populations and informs future efforts to design engaging, theory-based digital health strategies. A randomized controlled trial of the MYRIDE intervention is underway. CLINICALTRIAL ClinicalTrials.gov NCT06074354; https://clinicaltrials.gov/study/NCT06074354