文献速递呼吸衰竭与机械通气重症综合管理与镇静镇痛创伤与烧伤

机器学习对创伤诱导急性呼吸窘迫综合征患者院内死亡率的预测价值:基于MIMIC III数据库的分析

[Predictive value of machine learning for in-hospital mortality for trauma-induced acute respiratory distress syndrome patients: an analysis using the data from MIMIC III].
PubMed 文献 · Zhonghua Wei Zhong Bing Ji Jiu Yi Xue · 2022-01-01
一句话结论在创伤合并ARDS患者中,包含年龄、BMI、BUN、乳酸、RDW、HCT、高血压、感染、急性肾衰竭和脓毒症的Logistic回归、XGBoost和人工神经网络模型对院内死亡均有良好预测价值,三者AUC无显著差异。

本研究为回顾性非干预病例对照研究,从MIMIC III数据库提取符合柏林定义的创伤合并ARDS患者760例,其中轻度346例、中度301例、重度113例;院内生存618例、死亡142例;736例接受机械通气、65例接受连续性肾脏替代治疗。多因素Logistic回归筛选出年龄、BMI、血尿素氮、乳酸、红细胞体积分布宽度、血细胞比容、高血压、感染、急性肾衰竭和脓毒症等显著变量,并据此构建Logistic回归模型、XGBoost模型和人工神经网络模型。三种模型预测院内死亡的AUC分别为0.737(95%CI 0.659-0.815)、0.745(95%CI 0.672-0.819)和0.757(95%CI 0.680-0.884),任意两模型间差异均无统计学意义(均P>0.05)。作者认为上述模型对创伤合并ARDS患者的院内死亡具有良好预测价值。

要点

  • 760例创伤合并ARDS患者中,院内死亡142例、生存618例;轻度346例、中度301例、重度113例。
  • 多因素Logistic回归显示年龄(OR=1.035,95%CI 1.020-1.050,P<0.001)、乳酸(OR=1.213,95%CI 1.124-1.309,P<0.001)、RDW(OR=1.249,95%CI 1.102-1.416,P<0.001)、急性肾衰竭(OR=2.021,95%CI 1.267-3.224,P=0.003)、脓毒症(OR=2.105,95%CI 1.265-
  • BMI(OR=0.949,95%CI 0.917-0.983,P=0.003)、高血压(OR=0.614,95%CI 0.389-0.968,P=0.036)、感染(OR=0.463,95%CI 0.289-0.741,P=0.001)与院内死亡呈负相关。
  • Logistic回归模型、XGBoost模型和人工神经网络模型预测院内死亡的AUC分别为0.737(95%CI 0.659-0.815)、0.745(95%CI 0.672-0.819)和0.757(95%CI 0.680-0.884),两两比较均P>0.05。
  • 736例接受机械通气、65例接受连续性肾脏替代治疗。

适用人群与场景

  • 从MIMIC III数据库提取的符合柏林定义的创伤合并急性呼吸窘迫综合征患者,共760例(轻度346例、中度301例、重度113例)。

诊断标准与关键阈值

  • 创伤合并ARDS的诊断采用柏林定义。

研究设计与关键结果

  • 研究类型为回顾性非干预病例对照研究,样本量760例,人群为MIMIC III数据库中符合柏林定义的创伤合并ARDS患者;736例接受机械通气,65例接受连续性肾脏替代治疗;院内生存618例、死亡142例。
  • 多因素Logistic回归筛选出与院内死亡显著相关的变量:年龄(OR=1.035,95%CI 1.020-1.050,P<0.001)、BMI(OR=0.949,95%CI 0.917-0.983,P=0.003)、血尿素氮(OR=1.019,95%CI 1.004-1.033,P=0.010)、乳酸(OR=1.213,95%CI 1.124-1.309,P<0.001)、红细胞体积分布宽度(OR=1.249,95%CI 1.102-1.416,P<0.001)、血细胞比容(OR=1.057,95%CI 1.019-1.097,P=0.003)、高血压(OR=0.614,95%CI 0.389-0.968,P=0.036)、感染(OR=0.463,95%CI 0.289-0.741,P=0.001)、急性肾衰竭(OR=2.021,95%CI 1.267-3.224,P=0.003)、脓毒症
  • 以上述变量构建的Logistic回归模型、XGBoost模型和人工神经网络模型预测院内死亡的AUC分别为0.737(95%CI 0.659-0.815)、0.745(95%CI 0.672-0.819)和0.757(95%CI 0.680-0.884),任意两模型间差异均无统计学意义(均P>0.05)。

证据类型、等级与局限

  • 证据类型为回顾性非干预病例对照研究;局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,包含年龄、BMI、BUN、乳酸、RDW、HCT、高血压、感染、急性肾衰竭和脓毒症的Logistic回归模型、XGBoost模型和人工神经网络模型对创伤合并ARDS患者的院内死亡具有良好预测价值。

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 investigate the value of machine learning methods for predicting in-hospital mortality in trauma patients with acute respiratory distress syndrome (ARDS).

METHODS: A retrospective non-intervention case-control study was performed. Trauma patients with ARDS met the Berlin definition were extracted from the the Medical Information Mart for Intensive Care III (MIMIC III) database. The basic information [including gender, age, body mass index (BMI), pH, oxygenation index, laboratory indexes, length of stay in the intensive care unit (ICU), the proportion of mechanical ventilation (MV) or continuous renal replacement therapy (CRRT), acute physiology score III (APS III), sequential organ failure score (SOFA) and simplified acute physiology score II (SAPS II)], complications (including hypertension, diabetes, infection, acute hemorrhagic anemia, sepsis, shock, acidosis and pneumonia) and prognosis data of patients were collected. Multivariate Logistic regression analysis was used to screen meaningful variables (P < 0.05). Logistic regression model, XGBoost model and artificial neural network model were constructed, and the receiver operator characteristic curve (ROC) was performed to evaluate the predictive value of the three models for in-hospital mortality in trauma patients with ARDS.

RESULTS: A total of 760 trauma patients with ARDS were enrolled, including 346 mild cases, 301 moderate cases and 113 severe cases; 618 cases survived and 142 cases died in hospital; 736 cases received MV and 65 cases received CRRT. Multivariate Logistic regression analysis screened out significant variables, including age [odds ratio (OR) = 1.035, 95% confidence interval (95%CI) was 1.020-1.050, P < 0.001], BMI (OR = 0.949, 95%CI was 0.917-0.983, P = 0.003), blood urea nitrogen (BUN; OR = 1.019, 95%CI was 1.004-1.033, P = 0.010), lactic acid (Lac; OR = 1.213, 95%CI was 1.124-1.309, P < 0.001), red cell volume distribution width (RDW; OR = 1.249, 95%CI was 1.102-1.416, P < 0.001), hematocrit (HCT, OR = 1.057, 95%CI was 1.019-1.097, P = 0.003), hypertension (OR = 0.614, 95%CI was 0.389-0.968, P = 0.036), infection (OR = 0.463, 95%CI was 0.289-0.741, P = 0.001), acute renal failure (OR = 2.021, 95%CI was 1.267-3.224, P = 0.003) and sepsis (OR = 2.105, 95%CI was 1.265-3.502, P = 0.004). All the above variables were used to construct the model. Logistic regression model, XGBoost model and artificial neural network model predicted in-hospital mortality with area under the curve (AUC) of 0.737 (95%CI was 0.659-0.815), 0.745 (95%CI was 0.672-0.819) and 0.757 (95%CI was 0.680-0.884), respectively. There was no significant difference between any two models (all P > 0.05).

CONCLUSIONS: Logistic regression model, XGBoost model and artificial neural network model including age, BMI, BUN, Lac, RDW, HCT, hypertension, infection, acute renal failure and sepsis have good predictive value for in-hospital mortality of trauma patients with ARDS.

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. Tang R, Tang W, Wang D, et al. [Predictive value of machine learning for in-hospital mortality for trauma-induced acute respiratory distress syndrome patients: an analysis using the data from MIMIC III]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2022. PMID: 35574742. doi:10.3760/cma.j.cn121430-20211117-01741

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。