Fuzzy Logic Model for Healthcare Resource Allocation Optimization in Diabetes Care: Analysis of Brazilian Unified Health System (SUS) Administrative Databases

IntroductionHealthcare systems worldwide face mounting challenges in resource allocation amid the rising burden of chronic diseases and persistent budgetary constraints. In Brazil, the Unified Health System (SUS) must deliver comprehensive care for people with diabetes mellitus (DM) while optimizing scarce resources. Fuzzy inference approaches provide a flexible framework capable of accommodating these complexities; however, evidence regarding their application to national-level diabetes care planning remains scarce. ObjectiveTo develop and validate a fuzzy logic-based optimization model to identify more effective, equitable, and outcome-oriented resource allocation strategies for diabetes care within SUS. MethodsWe conducted a retrospective cross-sectional study utilizing DATASUS, SIH-SUS, and Hiperdia registries spanning January 2015 to December 2024 across 5,570 Brazilian municipalities, and constructed a hierarchical Mamdani-type fuzzy inference system incorporating epidemiologic, economic, clinical, and structural indicators. The model was calibrated using historical data, validated through technical, empirical, and expert assessment, and embedded within a multi-objective optimization framework to evaluate alternative investment scenarios across varied budget constraints. ResultsThe integrated dataset comprised 8,347,219 diabetes-related hospitalizations. The fuzzy inference system demonstrated 97.3% coverage and outperformed conventional approaches with mean absolute percentage error of 12.4% for expenditure predictions. Under baseline conditions, the model recommended increasing primary care investments from 31.2% to 42.7% while reducing tertiary hospital care from 38.4% to 28.9%. These reallocations predicted 8.4% improvement in glycemic control, 12.7% reduction in hospitalizations, and 6.2% mortality decrease over five years. Geographic analysis identified 847 highest-priority municipalities requiring targeted intervention. ConclusionFuzzy logic-based optimization demonstrates substantial potential for enhancing diabetes care efficiency through strategic reallocation prioritizing primary care expansion and equity-focused interventions in underserved regions.