Fairness-Aware AI for Healthcare Supply Chain Equity: Integrating Social Determinants of Health, Causal Modeling, and Geospatial Optimization
Journal of Ai ML DL · 01.06.2026 · 2 (1) · 1-11
DOI: 10.25163/ai.2110782 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Ai ML DL, online erschienen am 01.06.2026.
Abstract (Originalsprache)
Background
Healthcare supply chains increasingly rely on artificial intelligence for demand forecasting and resource allocation, yet most existing frameworks optimize for efficiency while remaining blind to the structural inequities embedded in the data they learn from. Social Determinants of Health (SDOH) — income, race, education, geography, and environmental risk — are established drivers of healthcare demand and access disparities, but remain largely excluded from operational AI decision systems.
Methods
This study presents a fairness-aware AI framework integrating SDOH data, a Structural Causal Model (SCM) for bias pathway identification, geospatial machine learning (Graph Neural Network combined with gradient boosting), and fairness-constrained multi-objective optimization into a unified healthcare supply chain system. Three models were compared — a conventional ML baseline (M1), an SDOH-augmented model (M2), and the proposed fairness-constrained framework (M3) — across 312 U.S. counties over a 24-month period, evaluated under normal, surge, and resource-constrained operational scenarios.
Results
M3 achieved a 5.6% improvement in demand forecast accuracy, a 23.5% reduction in logistics cost, and a 47.6% reduction in the Fairness Disparity Index relative to M1, with statistically significant gains across all three dimensions. Pareto frontier analysis indicated that substantial fairness improvements were achievable with minimal efficiency cost within the tested operational range. Under pandemic-surge simulation, M3 maintained superior equity resilience compared to both baseline models.
Conclusion
These findings suggest that, with appropriate structural design, fairness and operational efficiency in healthcare supply chain AI are reinforcing rather than competing objectives, offering a scalable framework for more equitable healthcare logistics.
Zitieren
APA
(2026). Fairness-Aware AI for Healthcare Supply Chain Equity: Integrating Social Determinants of Health, Causal Modeling, and Geospatial Optimization. Journal of Ai ML DL, 2(1), 1-11. https://doi.org/10.25163/ai.2110782
Vancouver
Fairness-Aware AI for Healthcare Supply Chain Equity: Integrating Social Determinants of Health, Causal Modeling, and Geospatial Optimization. Journal of Ai ML DL. 2026;2(1):1-11. doi:10.25163/ai.2110782
BibTeX
@article{euvimed2026,
title = {Fairness-Aware AI for Healthcare Supply Chain Equity: Integrating Social Determinants of Health, Causal Modeling, and Geospatial Optimization},
journal = {Journal of Ai ML DL},
year = {2026},
volume = {2},
number = {1},
pages = {1--11},
doi = {10.25163/ai.2110782}
}
EUVIMED