Rethinking the Design of Adolescent Crisis Stabilization Units: A Mixed-Methods Study Using Physical Mock-Up Simulations and Artificial Intelligence.

Abstract

Limited research has examined safety features in nonhospital settings for adolescents experiencing behavioral health crises, including the crisis stabilization unit (CSU). This mixed-methods study investigated safety through design features (eg, open versus semi-enclosed nursing stations) in an adolescent CSU with experts (clinicians and health care designers) and design trainees (N = 17) using physical mock-up simulations and artificial intelligence (AI). Participants' feedback was obtained using questionnaires and focus groups. Simulations were video-recorded, manually coded, and an AI-driven tool was developed for automatic, real-time analysis of videos. Findings revealed that experts rated the semi-enclosed nursing station higher in visibility, whereas design trainees reported significantly higher perceived privacy in the open nursing station ( P = 0.036). AI-driven video analyses demonstrated high-accuracy performance in detecting and tracking participants (>80%) when compared with manual data. This study proposed a methodology to improve safety in future adolescent CSUs by integrating AI-driven tools and clinical mock-up simulations during the design process.