A Multi-Agent AI Framework for MentalHealth Triage in Post-Conflict Arabic-SpeakingPopulations

Background: Syria’s protracted conflict has produced a mental health crisis of ex-traordinary scale, with PTSD, depression, and anxiety prevalence estimated at 7–8times global baselines, against fewer than 0.37 psychiatrists per 100,000 people. Ex-isting AI mental health tools fail in this context due to three simultaneous structuraldeficiencies—extreme clinical scarcity, Arabic NLP underperformance, and culturalmisalignment with Syrian idioms of distress—which we term the Triple Gap.Aim: To propose and specify a multi-agent AI framework for mental health triage thatjointly addresses clinical, technological, and cultural barriers in post-conflict Arabic-speaking populations, aligned with WHO’s mhGAP task-shifting model. Methods: We developed a formally specified four-agent pipeline architecture com-prising Screening, Risk Stratification, Routing, and Follow-up agents, underpinned bya cross-cutting Cultural Adaptation Layer and Human-in-the-Loop governance. Theframework was evaluated through structured comparative analysis against five exist-ing multi-agent mental health frameworks and a comprehensive four-phase validationprotocol was designed. Results: Comparative analysis demonstrates that no existing multi-agent mental healthframework addresses Arabic language support, dialect-aware NLP, cultural adapta-tion, post-conflict deployment, or task-shifting alignment. The proposed validationprotocol specifies four sequential phases—component benchmarking, simulated sce-nario testing, controlled field pilot, and stepped-wedge comparative effectiveness trial—with defined performance thresholds (symptom classification F1 ≥ 0.75; crisis sensi-tivity ≥ 95%; triage concordance κ ≥ 0.60) and ethical safeguards calibrated to fragile-state constraints. Conclusions: The proposed framework provides the first formally specified multi-agent architecture for mental health triage in Arabic-speaking, post-conflict popula-tions. The four-phase validation protocol establishes a concrete roadmap from con-ceptual design to clinical implementation, with participatory construction of a SyrianArabic mental health corpus identified as the critical prerequisite.