Equity-Preserving Public Health Resource Allocation Using Multi-Objective Safe Reinforcement Learning: Evidence from...

Equitable allocation of public health budgets across multiple intervention domains remains a major challenge in regional health governance. In Thailand's Health Region 10, annual healthcare budgets must address diverse health burdens across several provinces, while current planning approaches rely on expert deliberation and historical precedent without systematic exploration of alternative allocation strategies. Public health resource allocation decisions are inherently multi-criteria, integrating health impact, cost-effectiveness, equity, disease severity, clinical and ethical priorities, feasibility, and alignment with national health policy agendas-dimensions that cannot be reduced to a single metric. This study introduces H-RL-MUSYA (Hierarchical Reinforcement Learning for Multi-Domain Unified System of Yielding Adaptive allocations), a decision-support framework designed to assist-not replace-public health practitioners by systematically generating and evaluating a menu of Pareto-efficient allocation strategies across four priority domains: nutrition, mental health, behavioral risk, and accident prevention. The framework explicitly acknowledges that DALYs averted and cost-effectiveness ratios are valuable but partial indicators, and that final resource allocation must integrate additional considerations-including underpinning health policies, priority population needs, feasibility, and contextual judgment-that lie beyond the model's scope.

Applied to Thailand's Health Region 10 (4.6 million inhabitants), H-RL-MUSYA identified 127 Pareto-efficient policies yielding a representative compromise allocation that averted 847,293 DALYs (34.1% improvement over historical allocations), improved cost-effectiveness by 31.3%, and reduced the health equity Gini coefficient from 0.243 to 0.187. A 12-month prospective pilot confirmed +23.1% composite health improvement with 91% stakeholder acceptance.

H-RL-MUSYA demonstrates that AI-assisted policy exploration can meaningfully enrich public health decision-making by surfacing non-intuitive allocation strategies and quantifying equity-efficiency trade-offs, while human expertise, policy context, and democratic deliberation remain essential for final allocation decisions.