Management of hospital beds is a high-impact issue for two-tier healthcare systems, due principally to their critical importance and high costs. Bed capacity in the public sector is generally insufficient to provide immediate care to all critical patients and thus a significant proportion of public expenditure is assigned to the diversion of patients for treatment in the private sector. We formulate and approximately solve a discounted infinite-horizon Markov Decision Process (MDP) that seeks to identify cost-effective policies for transferring ICU patients between hospitals or diverting them to private clinics. The solution approach employs an affine architecture for approximating the value function of the MDP model and solves the equivalent linear programming model using column generation. The approach can handle a high level of dimensionality, enabling it to consider the arriving patients’ many different diagnostic groups and their corresponding lengths of stay. The decisions generated through this approach often differ from the intuitive ones produced in a typical day-by-day decision process, that does not consider the impact of the current day’s decisions on the future performance of the system. In particular, the resulting policies will in many cases proactively transfer patients to a different public facility or divert them to a private one even though the hospital they first arrived at had beds available. The performance of the proposed method was evaluated by simulating a case study based on data from a hospital network in Santiago, Chile, producing savings of almost 49% due mostly to reduced usage of private services.

病床管理对于两级医疗保健系统来说是一个影响很大的问题，主要是由于它们的重要性和高昂的成本。公共部门的床位容量通常不足以为所有危重患者提供即时护理，因此公共支出的很大一部分用于将患者转移到私营部门接受治疗。我们制定并近似解决了一个折扣无限水平马尔可夫决策过程 (MDP)，该过程旨在确定在医院之间转移 ICU 患者或将他们转移到私人诊所的成本效益政策。求解方法采用仿射架构来逼近 MDP 模型的值函数，并使用列生成来求解等效线性规划模型。该方法可以处理高维，使其能够考虑到达患者的许多不同诊断组及其相应的住院时间。通过这种方法生成的决策通常不同于典型的日常决策过程中产生的直观决策，后者不考虑当前决策对系统未来性能的影响。特别是，由此产生的政策在许多情况下会主动将患者转移到不同的公共机构或将他们转移到私人机构，即使他们最初到达的医院有床位。通过模拟基于智利圣地亚哥医院网络数据的案例研究来评估所提出方法的性能，主要是由于减少了私人服务的使用，节省了近 49%。