Data-Driven Optimization Methodology for Admission Control in Critical Care Units

Problem Definition: The decision of whether to admit a patient to a critical care unit is a crucial operational problem that has significant influence on both hospital performance and patient outcomes. Hospitals currently lack a methodology to selectively admit patients to these units in a way that patient health risk metrics can be incorporated while considering the congestion that will occur. Academic/Practical Relevance: The hospital is modeled as a complex loss queueing network with a stochastic model of how long risk-stratified patients spend time in particular units and how they transition between units. Methodology: A Mixed Integer Programming (MIP) model approximates an optimal admission control policy for the network of units. While enforcing low levels of patient blocking, we optimize a monotonic dual-threshold admission policy. Results: A hospital network including Intermediate Care Units (IMCs) and Intensive Care Units (ICUs) was considered for validation. The optimized model indicated a reduction in the risk levels required for admission, and weekly average admissions to ICUs and IMCs increased by 37% and 12%, respectively, with minimal blocking. Managerial Implications: Our methodology captures utilization and accessibility in a network model of care pathways while supporting the personalized allocation of scarce care resources to the neediest patients. This predictive platform of patient flow based on risk-based admittance enables hospitals to achieve tailored admission policies and evaluate the potential improvement. Because redirecting a high risk patient to a higher level of care on average reduces the total hospital length of stay (LOS), effective admission control may allow the hospital to improve its net throughput in critical care units and reduce overall LOS. The interesting benefits of admission thresholds that vary by day of week are studied