文献速递复苏、休克与脓毒症重症综合管理与镇静镇痛

基于MIMIC-III数据库构建脓毒性休克患者死亡风险预测模型的队列研究

[A cohort study of developing a death risk prediction model in patients with septic shock based on MIMIC-III database].
PubMed 文献 · Zhonghua Wei Zhong Bing Ji Jiu Yi Xue · 2022-01-01
一句话结论基于MIMIC-III的回顾性队列构建9变量脓毒性休克30天死亡预测模型,AUC 0.839(95%CI 0.803-0.876),30天死亡率35.8%。

本研究基于开源数据库MIMIC-III v1.4,纳入符合Sepsis-3标准的脓毒性休克患者693例,采用LASSO回归筛选预测变量、Logistic回归构建30天死亡风险预测模型,并用Hosmer-Lemeshow检验评价校准度、ROC曲线评价区分度。30天内死亡248例、存活445例,死亡率35.8%。模型纳入年龄、Elixhauser指数、乳酸、K+、机械通气、收缩压、舒张压、体温、SpO2共9个变量,AUC为0.839(95%CI 0.803-0.876),校准曲线显示预测风险与实际风险一致性良好。作者认为该模型可用于临床计算脓毒性休克患者的死亡风险。

要点

  • 30天死亡248例、存活445例,死亡率35.8%,死亡组与存活组按此结局划分。
  • 年龄(OR 1.023,95%CI 1.010-1.037,P<0.01)、Elixhauser指数(OR 1.047,95%CI 1.022-1.074,P<0.01)与30天死亡风险升高相关。
  • 乳酸(OR 1.213,95%CI 1.133-1.305,P<0.01)、K+(OR 2.241,95%CI 1.664-3.057,P<0.01)、机械通气(OR 2.165,95%CI 1.433-3.301,P<0.01)与30天死亡风险升高相关。
  • 收缩压(OR 0.974,95%CI 0.957-0.990)、舒张压(OR 0.972,95%CI 0.950-0.994)、体温(OR 0.693,95%CI 0.556-0.857)、SpO2(OR 0.971,95%CI 0.949-0.992)降低与30天死亡风险升高相关,均P<0.05。
  • 模型AUC 0.839(95%CI 0.803-0.876),校准曲线显示预测风险与实际一致性良好,作者认为可用于计算脓毒性休克患者死亡风险。

适用人群与场景

  • 基于MIMIC-III v1.4数据库、符合Sepsis-3标准的脓毒性休克患者,共693例,其中30天内死亡248例、存活445例。

诊断标准与关键阈值

  • 纳入标准为符合Sepsis-3标准的脓毒性休克患者;预测变量经LASSO回归筛选,模型经Logistic回归构建。

研究设计与关键结果

  • 研究类型为回顾性队列研究,数据来自MIMIC-III v1.4,纳入693例脓毒性休克患者,30天死亡248例、存活445例,死亡率35.8%。
  • LASSO回归筛选出9个预测变量并构建Logistic回归模型:年龄、Elixhauser指数、乳酸、K+、机械通气与30天死亡风险升高相关,OR分别为1.023(95%CI 1.010-1.037)、1.047(95%CI 1.022-1.074)、1.213(95%CI 1.133-1.305)、2.241(95%CI 1.664-3.057)、2.165(95%CI 1.433-3.301),均P<0.01。
  • 收缩压、舒张压、体温、SpO2降低与30天死亡风险升高相关,OR分别为0.974(95%CI 0.957-0.990)、0.972(95%CI 0.950-0.994)、0.693(95%CI 0.556-0.857)、0.971(95%CI 0.949-0.992),均P<0.05。
  • 校准曲线显示模型预测的脓毒性休克死亡风险与实际风险一致性良好;ROC曲线分析显示模型AUC为0.839(95%CI 0.803-0.876),可区分死亡风险患者与存活风险患者。

证据类型、等级与局限

  • 证据类型为基于MIMIC-III v1.4数据库的回顾性队列研究,采用LASSO-Logistic方法构建并验证模型。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,该脓毒性休克死亡风险预测模型包含9个住院期间易获取的变量(年龄、Elixhauser指数、机械通气、乳酸、K+、收缩压、舒张压、体温、SpO2),临床医生可用于计算脓毒性休克个体的死亡风险。

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 develop and validate a model for predicting death risk in septic shock patients using LASSO-Logistic methods.

METHODS: A retrospective cohort study was conducted. Based on the open-source database Medical Information Mart for Intensive Care-III v1.4 (MIMIC-III v1.4), the septic shock patients meeting the Sepsis-3 criteria were included, and the data on demographic characteristics, major signs, laboratory examinations, hospitalization, and outcomes were extracted. Predictive variables were selected by LASSO regression and predictive models were derived using Logistic regression. The calibration of the model was evaluated using the Hosmer-Lemeshow test and discrimination was evaluated using the receiver operator characteristic curve (ROC curve).

RESULTS: A total of 693 patients with septic shock were enrolled, in which 445 patients survived and 248 patients dead within 30 days and the mortality was 35.8%. Logistic regression model was constructed according to nine predictive variables and outcome variables screened by LASSO regression method, which showed that advanced age, Elixhauser index, blood lactic acid (Lac), K+ level and mechanical ventilation were associated with increased 30-day mortality [odds ratio (OR) and 95% confidence interval (95%CI) was 1.023 (1.010-1.037), 1.047 (1.022-1.074), 1.213 (1.133-1.305), 2.241 (1.664-3.057), 2.165 (1.433-3.301), respectively, all P < 0.01], and reduced systolic blood pressure (SBP), diastolic blood pressure (DBP), body temperature, and pulse oxygen saturation (SpO2) were also associated with increased 30-day mortality [OR (95%CI) was 0.974 (0.957-0.990), 0.972 (0.950-0.994), 0.693 (0.556-0.857), 0.971 (0.949-0.992), respectively, all P < 0.05]. The calibration curve showed that the predicted risk of septic shock death risk prediction model had good agreement with the real situation. ROC curve analysis showed that the area under the ROC curve (AUC) of the prediction model was 0.839 (95%CI was 0.803-0.876), which could distinguish patients at risk of death from those at risk of survival.

CONCLUSIONS: The septic shock death risk prediction model has a good ability to identify the 30-day mortality risk of septic shock patients, including nine hospital readily variables (age, Elixhauser index, mechanical ventilation, Lac, K+, SBP, DBP, body temperature and SpO2). The model could be used by clinicians to calculate the risk of death in septic shock individuals.

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. Li S, Guo P, Tang T, et al. [A cohort study of developing a death risk prediction model in patients with septic shock based on MIMIC-III database]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2022. PMID: 36567553. doi:10.3760/cma.j.cn121430-20211018-01505

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。