Machine learning for the prediction of preoxygenation technique in trauma

Background Preoxygenation can be achieved best by non-invasive ventilation techniques (NIV). Objective With the help of machine learning, the decision-making process against or in favour of NIV for preoxygenation in severely injured preclinical patients shall be evaluated. Methods A registry-based, retrospective analysis in preclinical adult trauma patients in south-western Germany between 2018 to 2020 was conducted. Attributes considered were the initial vital signs, Glasgow Coma Scale, airway devices, administered medication, description of difficult airway, emergency interventions, shock index, age and pre emergency status. A decision tree model (REPTree) and two Bayesian network (BN) were created, one with all and the other with the attributes occurring in the decision tree. Results 992 datasets with 333 cases of NIV (33%) were identified. Main splitting points in the decision tree model were the attributes rhonchus and bronchial spasm, videolaryngoscopy, respiratory rate, heart rate, age, oxygen saturation and head injury. The area under the receiver operating characteristics was between 0.97 (original BN; 95% CI, 0.96-0.97) and 0.93 (REPTree, 95% CI, 0.92-0.93). For the prediction, the precision-recall area was 0.96 (BN, 95% CI, 0.96-0.97) and 0.88 (REPTree, 95% CI, 0.87-0.89) and for exclusion 0.96 (BN, 95% CI, 0.96-0.97) and 0.94 (REPTree, 65% CI, 0.93-0.94). The simplified BN performed equally to the original BN. Conclusion The presented models demonstrated a feasibility for modeling decision making as well as an excellent performance. An expended model should contain internal and neurological patients as well as the effectiveness of the chosen method and could therefore support emergency medical crews. Files: Supplement Bayesian Network max 3 nodes XML BIF.xml • XML data file with all nodes and probabilities of the final Bayesian network with a maximum of 3 parental nodes that can be implemented in WEKA Supplement Simplified Bayesian Network max 3 nodes XML BIF.xml • XML data file with all nodes and probabilities of the simplified Bayesian network with a maximum of 3 parental nodes that can be implemented in WEKA背景：预氧合的最优实现方式为无创通气技术（non-invasive ventilation techniques, NIV）。 目的：借助机器学习技术，评估院前重伤患者实施预氧合时，支持或反对采用NIV的决策过程。 方法：本研究针对2018年至2020年德国西南部地区的院前成年创伤患者开展了一项基于登记队列的回顾性分析。本研究纳入的特征指标包括初始生命体征、格拉斯哥昏迷量表（Glasgow Coma Scale）、气道器具使用情况、给药方案、困难气道特征描述、急诊干预措施、休克指数、年龄及院前急救状态。本研究构建了决策树模型（REPTree）与两个贝叶斯网络（Bayesian network, BN）：其一纳入全部特征指标，其二仅包含决策树模型中出现的特征指标。 结果：本研究共纳入992份数据集，其中333例（33%）采用了NIV。决策树模型的主要分裂节点特征为喘鸣、支气管痉挛、视频喉镜检查、呼吸频率、心率、年龄、血氧饱和度及颅脑损伤。受试者工作特征曲线下面积（area under the receiver operating characteristics, AUC）介于0.97（原始贝叶斯网络；95%置信区间：0.96~0.97）与0.93（REPTree；95%置信区间：0.92~0.93）之间。在预测选用NIV的场景中，精确召回曲线下面积分别为0.96（贝叶斯网络；95%置信区间：0.96~0.97）与0.88（REPTree；95%置信区间：0.87~0.89）；在预测排除NIV的场景中，该指标分别为0.96（贝叶斯网络；95%置信区间：0.96~0.97）与0.94（REPTree；95%置信区间：0.93~0.94）。简化版贝叶斯网络的模型性能与原始贝叶斯网络相当。 结论：本研究所构建的模型证实了决策建模的可行性，且展现出优异的模型性能。后续可构建扩展模型，纳入内科与神经科患者数据，并补充所选干预手段的有效性信息，进而为急诊医疗团队提供决策支持。 附属文件： 1. Supplement Bayesian Network max 3 nodes XML BIF.xml：可在WEKA软件中运行的、包含最多3个父节点的最终贝叶斯网络所有节点与概率信息的XML数据文件。 2. Supplement Simplified Bayesian Network max 3 nodes XML BIF.xml：可在WEKA软件中运行的、包含最多3个父节点的简化版贝叶斯网络所有节点与概率信息的XML数据文件。