Designing an efficient blood supply chain network in crisis: neural learning, optimization and case study

In recent years, attention to blood supply chain in disaster circumstances has significantly increased. Disasters, especially earthquakes, have adverse consequences such as destruction, loss of human lives, and undermining the effectiveness of health services. This research considers a six-echelon blood supply chain which consists of donors, blood collection centers (permanent and temporary), regional blood centers, local blood centers, regional hospitals, and local hospitals. For the first time, we considered that helicopters could carry blood from regional hospitals to local hospitals and return injured people that cannot be treated in local hospitals to regional hospitals due to the limited capacity. In addition to the above, different transportations with limited capacities regarded, where the optimal number of required transportations equipment determined after the solution process. This research aims to avoid the worst consequences of a disaster using a neural-learning process to gain from past experiences to meet new challenges. For this aim, this article considers three objective functions that are minimizing total transportation time and cost while minimizing unfulfilled demand. The model implemented based on a real-world case study from the most recent earthquake in the Iran–Iraq border which named the deadliest earthquake of 2017. Based on our results, we learned how to design an efficient blood supply chain that can fulfill hospitals blood demand quickly with the lowest cost using simulation and optimization processes. Moreover, we performed in-depth analyses and provided essential managerial insights at last.