文献速递重症综合管理与镇静镇痛复苏、休克与脓毒症

基于逻辑回归模型构建联合预测指标用于预测脓毒症及预后

[Formulation of combined predictive indicators using logistic regression model in predicting sepsis and prognosis].
PubMed 文献 · Zhonghua Wei Zhong Bing Ji Jiu Yi Xue · 2017-01-01
一句话结论在ICU危重患者中,逻辑回归构建的联合预测指标诊断脓毒症和预测院内死亡的AUC均高于单一指标,但仅为单中心回顾性建模。

该研究纳入2014年1月至2015年9月长征医院ICU首次入院的362例危重患者(男218例、女144例,平均年龄48.3±19.3岁,66例死亡),用逻辑回归构建联合预测指标并比较ROC曲线下面积。仅含分类协变量的模型显示降钙素原升高、白细胞计数升高和发热是脓毒症的独立危险因素,新联合指标诊断脓毒症的AUC为0.930,高于降钙素原、脂多糖、感染、白细胞计数和发热各自的AUC(0.661、0.503、0.570、0.837、0.800),最佳截断值0.518时灵敏度78.00%、特异度93.36%、诊断准确率87.47%。仅含连续协变量的模型显示APACHE II评分和SOFA评分是院内死亡的独立危险因素,新联合指标预测院内死亡的AUC为0.834,高于APACHE II评分的0.812和SOFA评分的0.813,最佳截断值0.236时灵敏度73.12%、特异度76.51%、诊断准确率75.70%。

要点

  • 在ICU危重患者中,联合预测指标诊断脓毒症的AUC为0.930,高于降钙素原0.661、脂多糖0.503、感染0.570、白细胞计数0.837和发热0.800。
  • 联合预测指标诊断脓毒症的最佳截断值为0.518,对应灵敏度78.00%、特异度93.36%、诊断准确率87.47%。
  • 联合APACHE II评分和SOFA评分预测院内死亡的联合指标AUC为0.834,高于APACHE II评分0.812和SOFA评分0.813。
  • 预测院内死亡的联合指标最佳截断值为0.236,对应灵敏度73.12%、特异度76.51%、诊断准确率75.70%。
  • 降钙素原升高、白细胞计数升高和发热是脓毒症的独立危险因素;APACHE II评分和SOFA评分是院内死亡的独立危险因素。

适用人群与场景

  • 2014年1月至2015年9月长征医院ICU首次入院的危重患者,年龄18-75岁,ICU停留时间超过24小时,病历资料完整。

诊断标准与关键阈值

  • 脓毒症联合预测指标最佳截断值为0.518,计算值大于等于0.518判为脓毒症。
  • 院内死亡联合预测指标最佳截断值为0.236,计算值大于等于0.236判为死亡预后。

研究设计与关键结果

  • 单中心研究纳入362例患者(男218例、女144例),66例死亡,平均年龄48.3±19.3岁。
  • 仅含分类协变量的模型中,降钙素原升高、白细胞计数升高和发热是脓毒症的独立危险因素;联合指标诊断脓毒症的AUC为0.930,高于降钙素原0.661、脂多糖0.503、感染0.570、白细胞计数0.837和发热0.800。
  • 脓毒症联合预测指标最佳截断值0.518,灵敏度78.00%、特异度93.36%、诊断准确率87.47%。
  • 仅含连续协变量的模型中,APACHE II评分和SOFA评分是院内死亡的独立危险因素;联合指标预测院内死亡的AUC为0.834,高于APACHE II评分0.812和SOFA评分0.813。
  • 院内死亡联合预测指标最佳截断值0.236,灵敏度73.12%、特异度76.51%、诊断准确率75.70%。

证据类型、等级与局限

  • 证据类型:单中心研究,采用逻辑回归建模并比较ROC曲线。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,逻辑回归模型构建的联合预测指标在预测脓毒症或院内死亡事件方面优于任何单一指标。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

OBJECTIVE: To explore the method and performance of using multiple indices to diagnose sepsis and to predict the prognosis of severe ill patients.

METHODS: Critically ill patients at first admission to intensive care unit (ICU) of Changzheng Hospital, Second Military Medical University, from January 2014 to September 2015 were enrolled if the following conditions were satisfied: (1) patients were 18-75 years old; (2) the length of ICU stay was more than 24 hours; (3) All records of the patients were available. Data of the patients was collected by searching the electronic medical record system. Logistic regression model was formulated to create the new combined predictive indicator and the receiver operating characteristic (ROC) curve for the new predictive indicator was built. The area under the ROC curve (AUC) for both the new indicator and original ones were compared. The optimal cut-off point was obtained where the Youden index reached the maximum value. Diagnostic parameters such as sensitivity, specificity and predictive accuracy were also calculated for comparison. Finally, individual values were substituted into the equation to test the performance in predicting clinical outcomes.

RESULTS: A total of 362 patients (218 males and 144 females) were enrolled in our study and 66 patients died. The average age was (48.3±19.3) years old. (1) For the predictive model only containing categorical covariants [including procalcitonin (PCT), lipopolysaccharide (LPS), infection, white blood cells count (WBC) and fever], increased PCT, increased WBC and fever were demonstrated to be independent risk factors for sepsis in the logistic equation. The AUC for the new combined predictive indicator was higher than that of any other indictor, including PCT, LPS, infection, WBC and fever (0.930 vs. 0.661, 0.503, 0.570, 0.837, 0.800). The optimal cut-off value for the new combined predictive indicator was 0.518. Using the new indicator to diagnose sepsis, the sensitivity, specificity and diagnostic accuracy rate were 78.00%, 93.36% and 87.47%, respectively. One patient was randomly selected, and the clinical data was substituted into the probability equation for prediction. The calculated value was 0.015, which was less than the cut-off value (0.518), indicating that the prognosis was non-sepsis at an accuracy of 87.47%. (2) For the predictive model only containing continuous covariants, the logistic model which combined acute physiology and chronic health evaluation II (APACHE II) score and sequential organ failure assessment (SOFA) score to predict in-hospital death events, both APACHE II score and SOFA score were independent risk factors for death. The AUC for the new predictive indicator was higher than that of APACHE II score and SOFA score (0.834 vs. 0.812, 0.813). The optimal cut-off value for the new combined predictive indicator in predicting in-hospital death events was 0.236, and the corresponding sensitivity, specificity and diagnostic accuracy for the combined predictive indicator were 73.12%, 76.51% and 75.70%, respectively. One patient was randomly selected, and the APACHE II score and SOFA score was substituted into the probability equation for prediction. The calculated value was 0.570, which was higher than the cut-off value (0.236), indicating that the death prognosis at an accuracy of 75.70%.

CONCLUSIONS: The combined predictive indicator, which is formulated by logistic regression models, is superior to any single indicator in predicting sepsis or in-hospital death events.

来源:Zhonghua Wei Zhong Bing Ji Jiu Yi Xue,查看原文。版权归原作者所有。

参考来源

  1. Duan L, Zhang S, Lin Z, et al. [Formulation of combined predictive indicators using logistic regression model in predicting sepsis and prognosis]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2017. PMID: 28625261. doi:10.3760/cma.j.issn.2095-4352.2017.02.009

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。