Data-driven efficiency optimization in Chinese medicine hospitals: A hybrid DEA-fsQCA modeling approach from Gansu Province

This study proposes a data-driven modeling framework to investigate the service efficiency optimization paths in Chinese medicine hospitals, combining Data Envelopment Analysis (DEA) and fuzzy-set Qualitative Comparative Analysis (fsQCA). Focusing on fourteen regions of Gansu Province in 2023, we first employ DEA modeling to quantify the service efficiency scores, followed by fsQCA configurational modeling to identify multidimensional improvement paths. The DEA efficiency model reveals a high overall service efficiency level (mean = 0.946) with significant regional disparities. Through fsQCA group analysis, we establish three distinct optimization paths with robust validity (total coverage = 0.664, consistency = 0.900):1.Environment-led driving path-External factors dominate efficiency gains; 2.Internal and external coordination driving path-Synergy between internal and external elements; 3.Balanced driving path-Integrated resource allocation. The hybrid modeling approach demonstrates that hospital efficiency emerges from nonlinear interactions of system components. Practical implications suggest targeted strategies: optimizing environmental conditions (Path 1), strengthening cross-department coordination (Path 2), and rebalancing resource inputs (Path 3). This study provides a computational decision-support tool for healthcare administrators to implement context-specific efficiency enhancement policies.