DYNAMIC RESOURCE ALLOCATION FOR EFFICIENT PATIENT SCHEDULING： A DATA-DRIVEN APPROACH

作     者：Monique Bakker Kwok-Leung Tsui 

作者机构：Department of Systems Engineering and Engineering Management City University of Hong Kong China 

出 版 物：《Journal of Systems Science and Systems Engineering》 (系统科学与系统工程学报（英文版）)

年 卷 期：2017年第26卷第4期

页      面：448-462页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 0835[工学-软件工程] 081001[工学-通信与信息系统] 081202[工学-计算机软件与理论] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Patient scheduling dynamic rostering patient care path discrete-event simulation 

摘      要：Efficient staff rostering and patient scheduling to meet outpatient demand is a very complex and dynamic task. Due to fluctuations in demand and specialist availability, specialist allocation must be very flexible and non-myopic. Medical specialists are typically restricted in sub-specialization, serve several patient groups and are the key resource in a chain of patient visits to the clinic and operating room （OR）. To overcome a myopic view of once-off appointment scheduling, we address the patient flow through a chain of patient appointments when allocating key resources to different patient groups. We present a new, data-driven algorithmic approach to automatic allocation of specialists to roster activities and patient groups. By their very nature, simplified mathematical models cannot capture the complexity that is characteristic to the system being modeled. In our approach, the allocation of specialists to their day-to-day activities is flexible and responsive to past and present key resource availability, as well as to past resource allocation. Variability in roster activities is actively minimized, in order to enhance the supply chain flow. With discrete-event simulation of the application case using empirical data, we illustrate how our approach improves patient Service Level （SL, percentage of patients served on-time） as well as Wait Time （days）, without change in resource capacity.