Hospital-Wide Inpatient Flow Optimization
提出一种结合机器学习的多阶段自适应鲁棒优化方法，统一全院床位分配，减少非专科安置和急诊、麻醉后病房的滞留时间，经600床位医院数据验证有效。
An ideal that supports quality and delivery of care is to have hospital operations that are coordinated and optimized across all services in real time. As a step toward this goal, we propose a multistage adaptive robust optimization approach combined with machine learning techniques. Informed by data and predictions, our framework unifies the bed assignment process across the entire hospital and accounts for present and future inpatient flows, discharges, and bed requests from the emergency department, scheduled surgeries and admissions, and outside transfers. We evaluate our approach through simulations calibrated on historical data from a large academic medical center. For the 600-bed institution, our optimization model was solved in seconds and reduced off-service placement by 24% on average and boarding delays in the emergency department and postanesthesia units by 35% and 18%, respectively. We also illustrate the benefit of using adaptive linear decision rules instead of static assignment decisions. This paper was accepted by Carri Chan, healthcare management. Supplemental Material: The data files and online appendix are available at https://doi.org/10.1287/mnsc.2023.4933 .