Managing Admission and Discharge Processes in Intensive Care Units
The intensive care unit (ICU) is one of the most crucial and expensive resources in a health care system. While high fixed costs usually lead to tight capacities, intensive care units face a very volatile, stochastic demand. Shortages, however, have severe consequences. Thus, various challenging issues exist: When should an ICU admit or reject arriving patients in general? Should ICUs always be able to admit critical patients or rather focus on high utilization? More generally, different performance perspectives might be chosen, such as a medical and a monetary perspective. On an operational level, both admission control of arriving patients and demand-driven early discharge of currently residing patients are decision variables and should be considered simultaneously. These decisions are complex, as they involve immediate and delayed consequences. Both the rejection of an arriving patient and the early discharge of a residing patient result in an increased mortality risk and a monetary opportunity loss. In addition, the decision affects future intensive care unit occupancy and, thus, future decisions. This talk discusses the trade-off between medical and monetary goals when managing intensive care units. The problem is modeled as a Markov decision process. Optimal decisions from a medical and a monetary point of view are discussed and compared to an intuitive, myopic rule mimicking decision-making in practice.