Artificial intelligence-driven improvement of hospital logistics management resilience: a practical exploration based on H Hospital

ABSTRACT

Hospital logistics management faces increasing challenges from growing service demands and external emergencies. While artificial intelligence offers potential solutions, its role in enhancing logistics resilience remains underexplored. This study investigates how artificial intelligence can improve the resilience of hospital logistics management, using H Hospital as a case study. Methods: we employed a mixed-methods design combining qualitative interviews (n=12) with a questionnaire survey of all logistics department staff (n=151). The analytical framework was developed using the PDCA cycle to examine AI's enabling role across the logistics process. Data were analyzed using thematic analysis for qualitative data and hierarchical regression analysis for quantitative data. Results: AI adoption was widely recognized (94.7%), with strongest improvements reported in equipment maintenance (41.1%) and resource allocation (33.1%). However, overall logistics resilience faces challenges including institutional misalignment, low system integration, talent shortages, and insufficient funding. Hierarchical regression confirmed AI integration significantly positively correlates with resilience level (β=0.642, p<0.001), with management system adaptability playing a crucial moderating role (β=0.208, p<0.01). Path analysis revealed the PDCA cycle fully mediates the AI-resilience relationship. Conclusion: AI enhances hospital logistics resilience, but its effectiveness depends on adaptive management systems and structured continuous improvement mechanisms. We propose corresponding optimization strategies including integrated platforms, resilience evaluation systems, and strengthened knowledge management to form an intelligent closed-loop mechanism.