Feinberg School of Medicine, Northwestern University, Chicago, Illinois.
Department of Neurology, University of Chicago, Chicago, Illinois.
Shock. 2024 Nov 1;62(5):644-649. doi: 10.1097/SHK.0000000000002420. Epub 2024 Jul 1.
Background : This study sought to predict time to patient hemodynamic stabilization during trauma resuscitations of hypotensive patient encounters using electronic medical record (EMR) data. Methods: This observational cohort study leveraged EMR data from a nine-hospital academic system composed of Level I, Level II, and nontrauma centers. Injured, hemodynamically unstable (initial systolic blood pressure, <90 mm Hg) emergency encounters from 2015 to 2020 were identified. Stabilization was defined as documented subsequent systolic blood pressure of >90 mm Hg. We predicted time to stabilization testing random forests, gradient boosting, and ensembles using patient, injury, treatment, EPIC Trauma Narrator, and hospital features from the first 4 hours of care. Results: Of 177,127 encounters, 1,347 (0.8%) arrived hemodynamically unstable; 168 (12.5%) presented to Level I trauma centers, 853 (63.3%) to Level II, and 326 (24.2%) to nontrauma centers. Of those, 747 (55.5%) were stabilized with a median of 50 min (interquartile range, 21-101 min). Stabilization was documented in 94.6% of unstable patient encounters at Level I, 57.6% at Level II, and 29.8% at nontrauma centers ( P < 0.001). Time to stabilization was predicted with a C-index of 0.80. The most predictive features were EPIC Trauma Narrator measures, documented patient arrival, provider examination, and disposition decision. In-hospital mortality was highest at Level I, 3.0% vs. 1.2% at Level II, and 0.3% at nontrauma centers ( P < 0.001). Importantly, nontrauma centers had the highest retriage rate to another acute care hospital (12.0%) compared to Level II centers (4.0%, P < 0.001). Conclusion: Time to stabilization of unstable injured patients can be predicted with EMR data.
本研究旨在利用电子病历（EMR）数据预测低血压患者创伤复苏期间患者血流动力学稳定的时间。
本观察性队列研究利用了由一级、二级和非创伤中心组成的九个医院学术系统的 EMR 数据。从 2015 年至 2020 年，确定了受伤、血流动力学不稳定（初始收缩压<90mmHg）的急诊就诊。稳定定义为记录到随后的收缩压>90mmHg。我们使用患者、损伤、治疗、EPIC 创伤叙述者以及前 4 小时护理中的医院特征，通过随机森林、梯度提升和集成来预测稳定时间测试。
在 177127 次就诊中，有 1347 次（0.8%）到达时血流动力学不稳定；168 次（12.5%）就诊于一级创伤中心，853 次（63.3%）就诊于二级，326 次（24.2%）就诊于非创伤中心。其中，747 次（55.5%）通过中位数为 50 分钟（四分位距，21-101 分钟）的治疗得到稳定。一级不稳定患者就诊中 94.6%稳定，二级为 57.6%，非创伤中心为 29.8%（P<0.001）。稳定时间的预测准确率为 0.80。最具预测性的特征是 EPIC 创伤叙述者的措施、记录的患者到达、提供者检查和处置决策。一级的院内死亡率最高，为 3.0%，二级为 1.2%，非创伤中心为 0.3%（P<0.001）。重要的是，非创伤中心与二级中心相比（4.0%，P<0.001），再分诊到另一家急性护理医院的比例最高（12.0%）。
利用 EMR 数据可以预测不稳定受伤患者的稳定时间。
