Supply Chains Problem During Crises: A Data-Driven Approach

Abstract

Efficient management of hospital evacuations and pharmaceutical supply chains is a critical challenge in modern healthcare, particularly during emergencies. This study addresses these challenges by proposing a novel bi-objective optimization framework. The model integrates a Mixed-Integer Linear Programming (MILP) approach with advanced machine learning techniques to simultaneously minimize total costs and maximize patient satisfaction. A key contribution is the incorporation of a Gated Recurrent Unit (GRU) neural network for accurate drug demand forecasting, enabling dynamic resource allocation in crisis scenarios. The model also accounts for two distinct patient destinations—receiving hospitals and temporary care centers (TCCs)—and includes a specialized pharmaceutical supply chain to prevent medicine shortages. To enhance system robustness, probabilistic demand patterns and disruption risks are considered, ensuring supply chain reliability. The solution methodology combines the Grasshopper Optimization Algorithm (GOA) and the ɛ-constraint method, efficiently addressing the multi-objective nature of the problem. Results demonstrate significant improvements in cost reduction, resource allocation, and service levels, highlighting the model’s practical applicability in real-world scenarios. This research provides valuable insights for optimizing healthcare logistics during critical events, contributing to both operational efficiency and patient welfare.

Keywords

• pharmaceutical supply chain
• mixed-integer linear programming (MILP)
• GRU neural network
• ɛ-constraint method
• grasshopper optimization algorithm (GOA)