Agent-based Patient Admission Scheduling in Hospitals

Scheduling decisions in hospitals are often taken in a decentralized way. This means that different specialized hospital units decide autonomously on patient admissions or operating room schedules. In this paper we present an agent-based model for the selection of an optimal mix for patient admissions. Admitting the right mix of patients is important in order to optimize the resource usage and patient throughput. Our model is based on an extensive case analysis, involving data analysis and interviews, conducted in a case study at a large hospital in the Netherlands. We focus on the coordination of different surgical patient types with probabilistic treatment processes involving multiple hospital units. We also consider the unplanned arrival of other patients requiring (partly) the same hospital resources. Simulation experiments show the applicability of our agent-based decision support tool. The simulation tool allows for the assessment of resource network usage as a function of different policies for decision making. Furthermore, the tool incorporates a first optimization module for the resource allocation of postoperative care beds.