Simulating the behavior of patients who leave a public hospital emergency department without being seen by a physician: a cellular automaton and agent-based framework

The objective of this study was to develop an agent based modeling (ABM) framework to simulate the behavior of patients who leave a public hospital emergency department (ED) without being seen (LWBS). In doing so, the study complements computer modeling and cellular automata (CA) techniques to simulate the behavior of patients in an ED. After verifying and validating the model by comparing it with data from a real case study, the significance of four preventive policies including increasing number of triage nurses, fast-track treatment, increasing the waiting room capacity and reducing treatment time were investigated by utilizing ordinary least squares regression. After applying the preventing policies in ED, an average of 42.14% reduction in the number of patients who leave without being seen and 6.05% reduction in the average length of stay (LOS) of patients was reported. This study is the first to apply CA in an ED simulation. Comparing the average LOS before and after applying CA with actual times from emergency department information system showed an 11% improvement. The simulation results indicated that the most effective approach to reduce the rate of LWBS is applying fast-track treatment. The ABM approach represents a flexible tool that can be constructed to reflect any given environment. It is also a support system for decision-makers to assess the relative impact of control strategies.

本研究旨在构建基于智能体的建模（Agent Based Modeling，ABM）框架，以模拟公立医院急诊科（Emergency Department，ED）内未就诊离开（Leave Without Being Seen，LWBS）的患者行为。在此研究过程中，本研究结合计算机建模与元胞自动机（Cellular Automata，CA）技术，实现对急诊科患者行为的模拟。随后，本研究将模型与实际案例研究的数据进行比对以完成验证，并通过普通最小二乘回归分析，探究了四项预防性政策的影响显著性，包括增加分诊护士数量、开设快速诊疗通道、扩大候诊室容量以及缩短单患者诊疗时长。在急诊科应用上述预防性政策后，研究结果显示未就诊离开的患者数量平均减少42.14%，患者平均停留时长（Length of Stay，LOS）平均降低6.05%。本研究首次将元胞自动机技术应用于急诊科模拟场景中。将应用元胞自动机前后的平均停留时长与急诊科信息系统的实际监测数据进行比对后发现，模型拟合精度提升了11%。模拟结果表明，降低未就诊离开率的最有效干预手段为实施快速诊疗通道策略。基于智能体的建模方法是一种灵活的建模工具，可针对任意特定场景环境进行定制化搭建，同时可为决策者评估各类管控策略的相对影响提供决策支持。