Department of Surgery, College of Medicine, National Taiwan University, Taipei, Taiwan.
Department of Information Management, College of Management, National Taiwan University, Taipei, Taiwan.
BMC Health Serv Res. 2021 Nov 20;21(1):1254. doi: 10.1186/s12913-021-07148-y.
Late cancellations of physical examination has severe impact on the operations of a physical examination center since it is often too late to fill vacancy. A booking control policy that considers overbooking is then one natural solution. Unlike appointment scheduling problems for clinics and hospitals, in which treating a patient mostly requires only one type of resource, a physical examination set typically requires multiple types of resources. Traditional methods that do not consider set-resource relationship thus may be inapplicable.
We formulate a stochastic mathematical programming model that maximizes the expected net reward, which is the examination revenue minus overage cost. A complete search algorithm and a greedy search algorithm are designed to search for optimal booking limits for all examination sets. To estimate the late cancellation probability for each individual consumer, we apply logistic regression to identify significant factors affecting the probability. After clustering is used to estimate individual probabilities, Monte Carlo simulation is conducted to generate probability distributions for the number of consumers without late cancellations. A discrete-event simulation is performance to evaluate the effectiveness of our proposed solution.
We collaborate with a leading physical examination center to collect real data to evaluate our proposed overbooking policies. We show that the proposed overbooking policy may significantly increase the expected net reward. Our simulation results also help us understand the impact of overbooking on the expected number of customers and expected overage. A sensitivity analysis is conducted to demonstrate that the benefit of overbooking is insensitive to the accuracy of cost estimation. A Pareto efficiency analysis gives practitioners suggestions regarding policy determination considering multiple performance indications.
Our proposed overbooking policies may greatly enhance the overall performance of a physical examination center.
体检预约的临时取消对体检中心的运营有严重影响，因为往往来不及填补空缺。因此，考虑超额预订的预订控制策略是一种自然的解决方案。与诊所和医院的预约调度问题不同，治疗患者通常只需要一种类型的资源，而体检套餐通常需要多种类型的资源。因此，不考虑套餐资源关系的传统方法可能不适用。
我们制定了一个随机数学规划模型，该模型最大化了期望净收益，即检查收入减去超额成本。设计了完全搜索算法和贪婪搜索算法来搜索所有检查套餐的最佳预订限制。为了估计每个个体消费者的晚期取消概率，我们应用逻辑回归来识别影响概率的显著因素。在使用聚类估计个体概率后，我们进行蒙特卡罗模拟以生成没有晚期取消的消费者数量的概率分布。进行离散事件模拟以评估我们提出的解决方案的有效性。
我们与一家领先的体检中心合作收集真实数据来评估我们提出的超额预订策略。我们表明，提出的超额预订策略可以显著提高预期净收益。我们的模拟结果还帮助我们了解超额预订对预期客户数量和预期超额预订的影响。进行敏感性分析以证明超额预订的收益对成本估算的准确性不敏感。帕累托效率分析为从业者提供了考虑多个绩效指标的政策制定建议。
我们提出的超额预订策略可以大大提高体检中心的整体绩效。
