文献速递呼吸衰竭与机械通气创伤与烧伤重症综合管理与镇静镇痛

创伤院前急救麻醉前无创通气的使用:一项结合机器学习的队列分析

Utilization of non-invasive ventilation before prehospital emergency anesthesia in trauma - a cohort analysis with machine learning.
PubMed 文献 · Scand J Trauma Resusc Emerg Med · 2025-03-03
一句话结论德国指南认为,在无 aspiration、严重 head/face injury、unconsciousness 或 non-compliance 时,NIV 可作为院前创伤 preoxygenation 的一种方法;本队列显示其使用与指南一致。

该研究基于德国西南部跨区域院前急救注册登记,纳入2018至2020年间接受紧急麻醉的多发伤患者,用 logistic 回归和机器学习算法分析麻醉诱导前使用无创通气(NIV)的预测因素。992例中333例(34%)使用了NIV。支气管痉挛(OR 119.75)、呼吸困难/发绀(OR 2.28)、中度和重度 head injury(均 OR 3.37)及呼吸频率(OR 1.07)与使用NIV显著相关(p<0.05)。决策树主要分裂点包括听诊(rhonchus 和支气管痉挛)、呼吸频率、心率、年龄、氧饱和度和 head injury,中度 head injury 在NIV组更常见(23% vs. 12%,p<0.01)。两组 aspiration 发生率(0.01%)和意识水平(GCS中位数15)相同(均 p>0.05)。所有算法对NIV使用的预测准确率均高,除多层感知机和 logistic 回归外;例如 Bayes Network 预测NIV使用的 AUC-ROC 为0.96(95% CI 0.95-0.96),PRC 面积0.96[0.96-0.96],排除NIV使用的 PRC 面积0.95[0.95-0.96]。作者认为,无严重 head injury 的伤员若出现呼吸困难、发绀或支气管痉挛,常接受NIV preoxygenation,提示这是常见院前实践,且与现行德国临床指南一致

要点

  • 992例院前紧急麻醉的多发伤患者中,333例(34%)在麻醉诱导前使用了NIV。
  • 与NIV使用显著相关的因素(p<0.05):支气管痉挛 OR 119.75、呼吸困难/发绀 OR 2.28、中度 head injury OR 3.37、重度 head injury OR 3.37、呼吸频率 OR 1.07。
  • 中度 head injury 在NIV组更常见(23% vs. 12%,p<0.01);两组 aspiration 发生率均为0.01%、GCS中位数均为15(均 p>0.05)。
  • Bayes Network 预测NIV使用的 AUC-ROC 为0.96(95% CI 0.95-0.96),PRC 面积0.96[0.96-0.96],排除NIV使用的 PRC 面积0.95[0.95-0.96]。
  • 作者认为,无严重 head injury 的伤员出现呼吸困难、发绀或支气管痉挛时常规接受NIV preoxygenation,与现行德国临床指南一致。

适用人群与场景

  • 德国西南部跨区域院前急救服务中,2018至2020年间接受紧急麻醉的多发伤患者。
  • 德国指南考虑NIV用于院前创伤 preoxygenation 的条件:无 aspiration、无严重 head 或 face injury、无 unconsciousness、无 patient non-compliance。

研究设计与关键结果

  • 研究类型:基于德国西南部跨区域院前急救注册登记的队列分析,纳入2018至2020年间接受紧急麻醉的多发伤患者992例。
  • NIV使用率:992例中333例(34%)在麻醉诱导前接受NIV。
  • logistic 回归显示与NIV使用显著相关(p<0.05)的因素:支气管痉挛 OR 119.75、呼吸困难/发绀 OR 2.28、中度 head injury OR 3.37、重度 head injury OR 3.37、呼吸频率 OR 1.07。
  • 决策树主要分裂点:听诊(rhonchus 和支气管痉挛)、呼吸频率、心率、年龄、氧饱和度、head injury;中度 head injury 在NIV组更常见(23% vs. 12%,p<0.01)。
  • 两组 aspiration 发生率(0.01%)和意识水平(GCS中位数15)相同(均 p>0.05)。
  • 预测效能:Bayes Network 预测NIV使用的 AUC-ROC 0.96(95% CI 0.95-0.96),PRC 面积0.96[0.96-0.96];排除NIV使用的 PRC 面积0.95[0.95-0.96];多层感知机和 logistic 回归除外,其余算法预测准确率均高。

证据类型、等级与局限

  • 证据类型:基于注册登记的队列分析(cohort analysis)。
  • 局限:作者指出当前证据水平有限(the current evidence level is limited),需进一步研究其他决策方面(如气道解剖)以及院前创伤NIV preoxygenation 对相关结局参数的影响。

对床旁实践的改变

  • 作者认为,无严重 head injury 的伤员出现呼吸困难、发绀或支气管痉挛时常规接受NIV preoxygenation,提示这是常见院前实践,与现行德国临床指南一致。
  • 德国指南将NIV列为院前创伤 preoxygenation 的可能方法,条件为无 aspiration、无严重 head 或 face injury、无 unconsciousness、无 patient non-compliance。

指南或共识出处

  • 德国临床指南(German clinical guidelines):考虑NIV作为院前创伤 preoxygenation 的可能方法。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: For preoxygenation, German guidelines consider non-invasive ventilation (NIV) as a possible method in prehospital trauma care in the absence of aspiration, severe head or face injuries, unconsciousness, or patient non-compliance. As data on the utilization and characteristics of patients receiving NIV are lacking, this study aims to identify predictors of NIV usage in trauma patients using machine learning and compare these findings with the current national guideline.

METHODS: A cross-regional registry of prehospital emergency services in southwestern Germany was searched for cases of emergency anesthesia in multiply injured patients in the period from 2018 to 2020. Initial vital signs, oxygen saturation, respiratory rate, heart rate, systolic blood pressure, Glasgow Coma Scale (GCS), injury pattern, shock index and age were examined using logistic regression. A decision tree algorithm was then applied in parallel to reduce the number of attributes, which were subsequently tested in several machine learning algorithms to predict the usage of NIV before the induction of anesthesia.

RESULTS: Of 992 patients with emergency anesthesia, 333 received NIV (34%). Attributes with a statistically significant influence (p < 0.05) in favour of NIV were bronchial spasm (odds ratio (OR) 119.75), dyspnea/cyanosis (OR 2.28), moderate and severe head injury (both OR 3.37) and the respiratory rate (OR 1.07). Main splitting points in the initial decision tree included auscultation (rhonchus and bronchial spasm), respiratory rate, heart rate, age, oxygen saturation and head injury with moderate head injury being more frequent in the NIV group (23% vs. 12%, p < 0.01). The rates of aspiration and the level of consciousness were equal in both groups (0.01% and median GCS 15, both p > 0.05). The prediction accuracy for NIV usage was high for all algorithms, except for multilayer perceptron and logistic regression. For instance, a Bayes Network yielded an AUC-ROC of 0.96 (95% CI, 0.95-0.96) and PRC-areas of 0.96 [0.96-0.96] for predicting and 0.95 [0.95-0.96] for excluding NIV usage.

CONCLUSIONS: Machine learning demonstrated an excellent categorizability of the cohort using only a few selected attributes. Injured patients without severe head injury who presented with dyspnea, cyanosis, or bronchial spasm were regularly preoxygenated with NIV, indicating a common prehospital practice. This usage appears to be in accordance with current German clinical guidelines. Further research should focus on other aspects of the decision making like airway anatomy and investigate the impact of preoxygenation with NIV in prehospital trauma care on relevant outcome parameters, as the current evidence level is limited.

来源:Scand J Trauma Resusc Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Luckscheiter A, Thiel M, Zink W, et al. Utilization of non-invasive ventilation before prehospital emergency anesthesia in trauma - a cohort analysis with machine learning. Scand J Trauma Resusc Emerg Med. 2025. PMID: 40033329. doi:10.1186/s13049-025-01350-1

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。