院内急诊抢救室心脏骤停风险预测模型构建及验证  

Construction and validation of a model for predicting the risk of in-hospital cardiac arrest in emergency rooms

作　　者：李永凯 李转运 何小静[3] 李丹丹[1] 袁新 李昕[1] 江树青 夏来百提姑·赛买提 徐军[4] 杨建中[1] Li Yongkai;Li Zhuanyun;He Xiaojing;Li Dandan;Yuan Xin;Li Xin;Jiang Shuqing;Xialaibaitigu Saimaiti;Xu Jun;Yang Jianzhong(Emergency Trauma Center,The First Affiliated Hospital of Xinjiang Medical University,Wulumuqi 830000,China;Department of Emergency Medicine,Union Hospital,Tongji Medical College,Huazhong University of Science and Technology,Wuhan 430074,China;Department of Obstetrics and Gynecology,The Second Affiliated Hospital of Hebei Medical University,Shijiazhuang 050000,China;Department of Emergency,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences,Beijing 100730,China)

机构地区：[1]新疆医科大学第一附属医院急救创伤中心,乌鲁木齐830000 [2]华中科技大学同济医学院附属协和医院急诊科,武汉430074 [3]河北医科大学第二附属医院妇产科,石家庄050000 [4]中国医学科学院北京协和医院急诊科,北京100730

出　　处：《中华急诊医学杂志》2024年第1期20-27,共8页Chinese Journal of Emergency Medicine

基　　金：科技援疆计划项目(2022E02046);研究生创新创业项目(CXCY2022009)。

摘　　要：目的基于Logistic回归构建和验证院内急诊抢救室心脏骤停患者预测模型。方法本研究为回顾性队列研究,纳入2020年1月至2021年7月新疆医科大学第一附属医院急诊抢救室的患者。收集患者的一般资料、生命体征、临床症状及实验室检查结果等,观察结局为患者在24 h内发生心脏骤停。按照7∶3的比例随机将患者分为建模组和验证组。用LASSO回归和多因素Logistic回归筛选预测因素,并构建院内急诊抢救室患者发生心脏骤停的预测模型。采用受试者工作特征曲线下面积(area under the curve,AUC)、校准曲线和临床决策曲线评估预测模型的价值。结果共纳入784例急诊抢救室患者参与研究,发生心脏骤停患者384例。最终筛选出10个变量并构建心脏骤停风险预测模型:Logit(P)=-4.503+2.159×改良早期预警评分(modified early warning score,MEWS)评分+2.095×胸痛+1.670×腹痛+2.021×呕血+2.015×手脚湿冷+5.521×气管插管+0.388×静脉血乳酸-0.100×白蛋白+0.768×血K^(+)+0.001×D-二聚体。建模组AUC为0.984(95%CI:0.976~0.993),验证组的AUC为0.972(95%CI:0.951~0.993),该预测模型具有良好的校准度、区分度和临床应用价值。结论基于MEWS评分、胸痛、腹痛、呕血、手脚湿冷、气管插管、静脉血乳酸、白蛋白、血K^(+)和D-二聚体构建院内急诊抢救室心脏骤停预测模型,预测急诊抢救室患者发生心脏骤停的概率并及时调整治疗策略。Objective The predictive model of cardiac arrest in the emergency room was constructed and validated based on Logistic regression.Methods This study was a retrospective cohort study.Patients admitted to the emergency room of the First Affiliated Hospital of Xinjiang Medical University from January 2020 to July 2021 were included.The general information,vital signs,clinical symptoms,and laboratory examination results of the patients were collected,and the outcome was cardiac arrest within 24 hours.The patients were randomly divided into modeling and validation group at a ratio of 7:3.LASSO regression and multivariable logistic regression were used to select predictive factors and construct a prediction model for cardiac arrest in the emergency room.The value of the prediction model was evaluated using the area under the receiver operator characteristic curve(AUC),calibration curve,and decision curve analysis(DCA).Results A total of 784 emergency room patients were included in the study,384 patients occurred cardiac arrest.The 10 variables were ultimately selected to construct a risk prediction model for cardiac arrest:Logit(P)=-4.503+2.159×modified early warning score(MEWS score)+2.095×chest pain+1.670×abdominal pain+2.021×hematemesis+2.015×cold extremities+5.521×endotracheal intubation+0.388×venous blood lactate-0.100×albumin+0.768×K^(+)+0.001×D-dimer.The AUC of the model group was 0.984(95%CI:0.976-0.993)and that of the validation group was 0.972(95%CI:0.951-0.993).This prediction model demonstrates good calibration,discrimination,and clinical applicability.Conclusions Based on the MEWS score,chest pain,abdominal pain,hematemesis,cold extremities,tracheal intubation,venous blood lactate,albumin,K^(+),and D-dimer,a predictive model for cardiac arrest in the in-hospital emergency room was constructed to predict the probability of cardiac arrest in emergency room patients and adjust the treatment strategy in time.

关 键 词：心脏骤停 急诊 Nomogram图 预测模型 LASSO回归 

分 类 号：R541.78[医药卫生—心血管疾病]