Automatic Workflow Capture & Analysis for Improving Trauma Resuscitation Outcomes

描述（由申请人提供）：尽管创伤复苏方案的大多数偏差是由于管理不同损伤患者所需的灵活性而产生的变化，但其他偏差是可能导致严重不良患者结果的“错误”。我们的长期目标是为创伤复苏和其他快节奏，高风险重症监护设置，监测已知与不良后果相关的偏差的工作流程，并对这些偏差提供警报，允许采取补救措施以防止不良后果。本提案的总体目标是实现这一长期目标的后续步骤，即：(a)开发一种可扩展的方法来识别创伤复苏期间的活动；(b)使用流程挖掘识别与创伤复苏工作流程中不良结果相关的偏差。中心假设是，创伤复苏活动可以实时监测和分析工作流程偏差，从而增加患者不良结果的可能性。拟议研究的理由是，实时确定不良后果的风险条件将使医疗队能够采取措施减少或预防医疗差错的影响。中心假设将通过追求两个具体目标来验证：1)开发一种可扩展和自动的方法来创建创伤复苏期间发生的活动的事件日志；2)识别和描述团队处理创伤复苏期间重大错误的能力。在第一个目标下，该方法将涉及(i)使用射频识别（RFID）技术和其他模式来创建人体运动和物体使用的复苏事件日志，以及（ii）将传感器日志与使用手动视频审查获得的日志进行比较（“地面真相”）。对于第二个目标，该方法将涉及基于知识的复苏工作流模型的开发和改进，该模型使用来自手动捕获的事件日志的一致活动序列。该项目意义重大，因为这些方法是计算机决策支持系统发展的重要早期步骤，该系统可以通过监测和支持重症监护团队的工作来改善结果。拟议的研究具有创新性，因为它代表了对现状的实质性背离，重点是开发从传感器获取数据的方法，以自动跟踪多个并发活动，并在可变工作流程中检测与不利结果相关的偏差。这些方法有望成为医疗团队实时决策支持的计算机化系统的基础，从而改善患者在创伤复苏和其他重症护理过程中的预后。

DESCRIPTION (provided by applicant): Although most deviations from trauma resuscitation protocols are variations that result from the flexibility needed for managing patients with differet injuries, other deviations are "errors" that can contribute to significant adverse patient outcomes Our long-term goal is to develop computerized decision support for trauma resuscitation and other fast-paced, high-risk critical care settings that monitors workflow for deviations that are known to be associated with adverse outcomes and provides alerts to these deviations, allowing remedial actions to be taken to prevent adverse outcomes. The overall objectives for this proposal, which are the next steps in the attainment of this long-term goal, are to: (a) develop a scalable approach for recognizing activities during trauma resuscitation; and (b) identify deviations associated with adverse outcomes within the workflow of trauma resuscitation using process mining. The central hypothesis is that trauma resuscitation activities can be monitored and analyzed in real time for workflow deviations that increase the likelihood of adverse patient outcomes. The rationale for the proposed research is that real-time identification of risk conditions for adverse outcomes will allow medical teams to take measures for reducing or preventing the impact of medical errors. The central hypothesis will be tested by pursuing two specific aims: 1) develop a scalable and automatic approach for creating an event log of activities occurring during trauma resuscitation; and 2) identify and characterize the team's ability to manage major errors during trauma resuscitation. Under the first aim, the approach will involve (i) the use of radiofrequency identification (RFID) technology and other modalities to create resuscitation event logs of human movement and object use and (ii) comparisons of sensor logs with logs obtained using manual video review ("ground truth"). For the second aim, the approach will involve the development and refinement of knowledge-based resuscitation workflow models using consensus sequences of activities from manually captured event logs. This project is significant because these methods are an essential early step toward the development of computerized decision support systems that can improve outcomes by monitoring and supporting the work of critical care teams. The proposed research is innovative because it represents a substantive departure from the status quo, focusing on developing methods for obtaining data from sensors to automatically track multiple, concurrent activities and for detecting deviations associated with adverse outcomes within a variable workflow. These methods are expected to form a basis for computerized systems for real-time decision support of medical teams that improve patient outcome during trauma resuscitation and other critical care processes.