目的基于决策树构建急诊创伤患者低体温早期预警模型并进行验证。 方法回顾性选取2020年5月至2021年4月某院收治的急诊创伤患者376例作为研究对象，根据患者是否出现低体温分为低体温组、体温正常组。收集两组患者临床资料，通过单因素分析急诊创伤患者发生低体温的影响因素并作为建模变量；随后以3∶1的比例随机分为训练集与验证集，其中训练集构建决策树模型，验证集用于评估模型预测效能。 结果决策树模型筛选出急诊创伤患者低体温发生的影响因素主要排序为入室时休克、修正的创伤评分（revised trauma score，RTS）、受伤时环境温度和衣物潮湿；决策树模型在训练集中与验证集中的受试者工作特征曲线 (receiver operating characteristic curve，ROC)曲线下面积（area under curve，AUC）分别为0.704、0.681。 结论基于入室时休克、RTS评分、受伤时环境温度和衣物潮湿构建决策树模型，能有效预测急诊创伤低体温风险。

Objective To develop an early warning model for predicting hypothermia among emergency trauma patients using decision tree analysis. Methods A total of 376 trauma patients were retrospectively selected from the Department of Emergency in a hospital from May，2020 to April，2021.The participants were divided into the hypothermia group and the normal temperature group according to the occurrence of hypothermia.The clinical data of the two groups were collected.The influencing factors of hypothermia among emergency trauma patients were determined by single factor analysis and used as modeling variables.The participants were randomly divided into the training set and the validation set at a ratio of 3:1.The training set was used to construct the decision tree model，and the validation set was used to evaluate the prediction efficiency of the model. Results The influencing factors of hypothermia among emergency trauma patients were screened out by the decision tree model，including shock at admission，RTS，environment temperature at injury and clothing humidity in sequence.The area under ROC of the decision tree model in the training set and the validation set were 0.704 and 0.681，respectively. Conclusions The decision tree model based on shock at admission，RTS，environment temperature at injury and clothing humidity can effectively predict the risks of emergency trauma hypothermia.

R472.2；R826

陕西省重点研发计划项目（2017SF-056）