Kang Hyojung, Haswell Ethan
Department of Kinesiology and Community Health, College of Applied Health Sciences, University of Illinois at Urbana-Champaign, Champaign, IL.
Department of Systems and Information Engineering, School of Engineering, University of Virginia, Charlottesville, VA.
JCO Oncol Pract. 2020 Dec;16(12):e1471-e1480. doi: 10.1200/OP.20.00119. Epub 2020 Jul 6.
Electronic health records (EHRs) have been mainly used to analyze bottlenecks in care processes of outpatient oncology clinics. However, EHR data lead to some limitations in understanding patient flow because they are manually entered and not updated in real time. Data generated from a real-time location system (RTLS) can supplement EHR data. This study aims to demonstrate how RTLS data combined with EHR data can be used to evaluate potential interventions to improve patient flow in an outpatient cancer center.
EHR and RTLS data obtained from a large cancer center in central Virginia were analyzed to estimate process times and determine the various patient paths patients follow during their visit for infusion. Using the input data, we developed a discrete-event simulation (DES) model and assessed 5 what-if scenarios involving changes in staff scheduling and care processes.
Raw RTLS data including > 3.5 million observations were preprocessed to remove noise and extract meaningful information. The DES results showed that new nursing schedules for the infusion center and improved pharmacy processes have positive impacts on reducing patient waiting times by approximately 20% and overall length of stay by approximately 3.4% to 4.6%, compared with the current system.
Combining EHR and RTLS data, we were able to capture dynamic aspects of patient flow more realistically. DES models that represent a complex system based on accurate input data can help decision making on determining operational changes to improve patient flow.
电子健康记录（EHRs）主要用于分析门诊肿瘤诊所护理流程中的瓶颈。然而，EHR数据在理解患者流程方面存在一些局限性，因为它们是手动录入且未实时更新。实时定位系统（RTLS）生成的数据可以补充EHR数据。本研究旨在证明如何将RTLS数据与EHR数据结合起来，用于评估改善门诊癌症中心患者流程的潜在干预措施。
分析从弗吉尼亚州中部一家大型癌症中心获得的EHR和RTLS数据，以估计流程时间，并确定患者在输液就诊期间遵循的各种患者路径。利用输入数据，我们开发了一个离散事件模拟（DES）模型，并评估了5种假设情景，涉及人员排班和护理流程的变化。
对包括超过350万条观察记录的原始RTLS数据进行预处理，以去除噪声并提取有意义的信息。DES结果表明，与当前系统相比，输液中心新的护理排班和改进的药房流程对减少患者等待时间约20%以及总体住院时间约3.4%至4.6%有积极影响。
通过结合EHR和RTLS数据，我们能够更真实地捕捉患者流程的动态方面。基于准确输入数据表示复杂系统的DES模型有助于在确定运营变化以改善患者流程方面进行决策。
