重症监护医学信息数据库Ⅲ中的重症患者早期急性肾损伤风险分析  

Risk factors analysis of early acute kidney injury in critically ill patients based on the medical information mart for intensive careⅢdatabase

作　　者：曹璐 韩欣妍 唐伟丽 李崇 董亚琳[3] 邢建峰[1] CAO Lu;HAN Xinyan;TANG Weili;LI Chong;DONG Yalin;XING Jianfeng(Department of Medicine,Xi’an Jiaotong University,Xi’an 710061,China;Department of Pharmacy,Hospital of Stomatology Xi’an Jiaotong University,Xi’an 710004,China;Department of Pharmacy,the First Affiliated Hospital of Xi’an Jiaotong University,Xi’an 710061,China)

机构地区：[1]西安交通大学药学院,西安710061 [2]西安交通大学口腔医院药剂科,西安710004 [3]西安交通大学第一附属医院药学部,西安710061

出　　处：《西北药学杂志》2022年第4期162-167,共6页Northwest Pharmaceutical Journal

基　　金：国家自然科学基金项目(编号:81973253,81773663)。

摘　　要：目的对重症患者入重症监护室(ICU)48 h内发生急性肾损伤(AKI)的影响因素进行分析,确定风险预测因素。方法以重症监护医学信息数据库Ⅲ(MIMIC-Ⅲ)为基础,提取符合条件的患者以及相应的临床信息。通过单因素及多因素Logistic回归分析确定重症患者入ICU后48 h内发生AKI的风险因素,并通过受试者工作特征曲线(ROC)确定所建立回归模型的预测效能。结果纳入重症患者34599例,早期AKI的发生率为6.21%,发生早期AKI的患者死亡率为12.10%。多因素分析结果显示,性别、年龄、序贯器官衰竭评分(SOFA)、冠状动脉疾病、白细胞计数、糖尿病、贫血、血尿素氮、血清肌酐及血小板计数是重症患者发生早期AKI的独立影响因素。所建立的回归模型预测效能良好,ROC曲线下面积为0.762(95%CI:0.751~0.772)。结论所建立的风险预测模型能够在患者入ICU时鉴别出48 h内发生AKI的高风险患者,帮助临床医生进行早期诊断,及时对患者进行监测和早期预防。Objective To analyze the risk factors of acute kidney injury(AKI)in critically ill patients within 48 hours after intensive care unit(ICU)admission.Methods We extracted eligible patients and corresponding clinical information from the medical information mart for intensive careⅢ(MIMIC-Ⅲ)database.Univariate analysis and multivariate logistic regression analysis were used to identify the risk factors of AKI within 48 hours after ICU admission,and receiver operating characteristic(ROC)curve was used to evaluate the predictive capability of the established regression model.Results A total of 34599 critically ill patients were included.The early AKI incidence was 6.21%and the mortality rate was 12.10%.Multivariate analysis suggested that the age,sequential organ failure assessment(SOFA)score,coronary artery disease,leukocyte count,diabetes,anemia,male,blood urea nitrogen,serum creatinine,and platelet count were independent factors affecting the onset of early AKI in critically ill patients.The regression model established in this study is effective with area under the ROC curve of 0.762(95%CI:0.751-0.772).Conclusion The risk prediction model established in this study could identify high-risk patients with AKI within 48 hours after ICU admission and assist clinicians in early diagnosis,timely monitoring and early prevention.

关 键 词：急性肾损伤 重症患者 影响因素 风险评估 重症监护医学信息数据库 

分 类 号：R969.3[医药卫生—药理学]