Design and Evaluation of a Culturally Adapted Multimodal Virtual Agent for PTSD Screening
Post-traumatic stress disorder (PTSD) is prevalent yet underreported among combat-exposed military personnel. We present Molhim, a culturally adapted multimodal conversational platform, and examine its PTSD screening configuration in a Saudi military healthcare context. The system pairs a system-controlled virtual agent with speech recognition, a large language model, visual understanding, and text-to-speech to deliver structured Arabic-language screening, including the PTSD Checklist for DSM-5 (PCL-5), and automated post-session analysis. In an observer-based feasibility pilot, ten soldiers rated the agent as respectful, safe, and potentially useful, with concordant clinician observations. We discuss design considerations for socially cooperative human-AI systems.