Benefit packages design based on the optimization of depression burden: Evidence from urban China

Achieving equitable health resource allocation under Universal Health Coverage (UHC) requires reconciling complex trade-offs between healthcare cost containment, clinical efficacy, and patient financial protection. To address this challenge, we propose a dual-perspective framework integrating societal and household-level disease burden optimization, with depression—a leading global disability cause—as the case study. Our bi-objective model prioritizes evidence-based antidepressant therapies for inclusion in national health benefit packages, thereby guiding insurance reimbursement policies and clinical practices to optimize resource allocation across macroeconomic and microeconomic dimensions. Given the model’s high-dimensional non-convex characteristics, we developed the Triple-Population Cooperative Particle Swarm Optimization for BDD (TPCPSO_BD), an advanced swarm intelligence-based computational tool integrating two key methodological advancements (triple-population partitioning for cooperative optimization and an adaptive particle correction mechanism that enhances convergence efficiency while maintaining solution diversity). Validated using real-world data from City S, China, TPCPSO_BD demonstrates superior performance in accuracy, efficiency, and policy impact (48.97% reduction in household out-of-pocket expenditures through optimized reimbursement schedules). This methodology establishes a transferable decision-support system for mental health financing in low- and middle-income countries, advancing Sustainable Development Goal 3 through technical innovation in handling non-linear health-economic interactions, dynamic prioritization of cost-effective interventions, and explicit incorporation of household financial risk protection, thereby providing a robust mechanism to promote sustainable healthcare equity.