摘要目的:探讨判别分析预测创伤出血性休克患者院内死亡的风险。方法:回顾性分析2013年9月—2020年8月在北京大学人民医院就诊的238例创伤出血性休克患者的临床资料，根据院内生存情况将创伤出血性休克患者分为生存组（214例）和死亡组（24例），比较两组的相关指标，利用逐步判别分析建立判别模型，预测创伤出血性休克的死亡风险。结果:生存组和死亡组之间脑卒中病史（9.8%比25.0%）、主要出血部位（四肢）（58.9%比29.2%）、急性生理与慢性健康评分Ⅱ（APACHE）评分（16.4±5.1比23.2±6.1）、血乳酸［2.1（1.1~3.5） mmol/L比4.9（2.0~13.4） mmol/L］及手术（92.5%比58.3%）指标比较差异均有统计学意义（均 P<0.05），进入最终判别模型的指标有5个：脑卒中病史、主要出血部位（四肢）、血乳酸、APACHEⅡ评分及手术。预测创伤出血性休克患者死亡风险的ROC曲线下面积为0.857，95% CI 0.754~0.959。 结论:所建立判别模型预测创伤出血性休克患者院内死亡风险的准确度较高。脑卒中病史、血乳酸水平及APACHEⅡ评分与创伤出血性休克的死亡风险增加有关，四肢出血和手术治疗与创伤出血性休克的死亡风险降低有关。

abstractsObjective:To investigate the use of discriminant analysis to predict the risk of nosocomial mortality in patients with traumatic hemorrhagic shock.Methods:The clinical data of 238 patients with traumatic hemorrhagic shock admitted to Peking University People's Hospital from Sep 2013 to Aug 2020 were retrospectively analyzed. Patients were divided into survival group (214 cases) and death group (24 cases). Stepwise discriminant analysis was used to establish a discriminant model.Results:The difference of history of stroke (9.8% vs. 25.0%), main site of bleeding (extremities)(58.9% vs. 29.2%), APACHEⅡ score (16.4±5.1 vs. 23.2±6.1), blood lactic acid [2.1(1.1-3.5) mmol/L vs. 4.9(2.0-13.4) mmol/L] and surgery (92.5% vs. 58.3%) between the two groups was all statistically significant (all P<0.05). Finally, There are five indicators that entered the discriminant model: history of stroke, main site of bleeding (extremities), blood lactic acid, APACHE Ⅱ score and surgery. The area under the ROC curve for predicting the risk of mortality in patients with traumatic hemorrhagic shock was 0.857, 95% CI 0.754-0.959. Conclusions:The established discriminant model has a high accuracy in predicting the risk of in-hospital mortality in patients with traumatic hemorrhagic shock.