Pediatric Transport Learning Laboratory

项目摘要/摘要 该项目的总体目标是推进儿科病人(21岁以下)的护理。 在区域网络内从一家医院到另一家医院的医疗地面或空中运输。该项目将在 我们之前在新生儿患者运送方面的经验使用了五个阶段的创新周期，包括： 问题分析、设计、开发、实施和评估，以确定和解决突出问题 区域新生儿转运的问题和风险，需要采取新的和创新的方法。 我们将与运输提供商和其他利益攸关方合作，分析当前的工作流程， 运输记录(地方和全州数据库)，以及转诊和接收设施的设施，以制定 全面了解系统问题，并定义当前和理想状态。这个详细的问题 分析阶段将使实时数据能够集成到交通运输的“数字孪生”模型中进行优化 儿科病人的区域会诊、分诊和运送至适当护理水平的设施 以及可用的空间和人员配备。 在临床运输团队工作人员和利益相关者的参与下，项目团队将与合作者一起工作 来自华盛顿大学工业和系统工程系的集成机器 学习运输监控和通信(T-MAC)系统以支持数据分析 在运输过程中进食。机器学习增强型T-MAC系统将经过反复测试和 修订，以确保它可以在功能上和有效地促进医疗控制之间的信息流动 医生，转介设施和运输团队。 此外，我们将制定强有力的流程，以支持信息流动到患者和家属的围术期- 运输期。为了实现这一目标，我们将与家庭合作，找出沟通中的差距，并 连接到当地和接收设施资源，并确定特定的运输需求。 T-MAC系统的有效性将在真实的现场模拟和临床环境中进行评估。我们是 相信通过这项研究学到的经验教训将改善儿科患者在医疗运输中的安全 并将转移到经历短距离和长距离设施间运输的患者群体。

Project Summary/Abstract The overall goal of this project is to advance the care of pediatric patients (up to 21 years of age) during medical ground or air transport from one hospital to another within a regional network. The project will build on our previous experience with neonatal patient transport and use a five-stage innovation cycle, including: problem analysis, design, development, implementation, and evaluation to identify and address the salient issues and risks of regional neonatal transportation for which new and innovative approaches are needed. In collaboration with transport providers and other stakeholders, we will analyze current workflow processes, transport records (local and statewide databases), and facilities at referral and receiving facilities to develop a complete understanding of system issues and to define the current and ideal states. This detailed problem analysis phase will enable the integration of real-time data into a transport “digital twin” model to optimize regional consultation, triage, and transport of pediatric patients to facilities with the appropriate level of care and availability of space and staffing. With the input of clinical transport team staff and stakeholders, the project team will work with collaborators from the University of Washington Industrial and Systems Engineering Department to integrate machine learning into the Transport Monitoring and Communications (T-MAC) system to support the analysis of data feeds while on transport. The machine learning augmented T-MAC system will undergo repeated testing and revision to ensure that it can functionally and efficiently facilitate information flow between the medical control physician, referring facility and transport team. In addition, we will develop robust processes to support information flow to patients and families in the peri- transport period. To accomplish this, we will work with families to identify gaps in communication and connection to local and receiving facility resources and identify transport-specific needs. The efficacy of the T-MAC system will be evaluated in a realistic in situ simulation and clinical settings. We are confident that the lessons learned through this study will improve pediatric patient safety on medical transports and will be transferable to patient populations that undergo both short and long-range interfacility transports.