文献速递复苏、休克与脓毒症重症综合管理与镇静镇痛

基于监督机器学习算法构建脓毒性休克患者死亡风险预测模型

[Constructing a predictive model for the death risk of patients with septic shock based on supervised machine learning algorithms].
PubMed 文献 · Zhonghua Wei Zhong Bing Ji Jiu Yi Xue · 2024-01-01
一句话结论基于MIMIC-IV中3295例脓毒性休克患者,用16个变量构建的Logistic回归模型预测28天死亡风险最佳,验证集AUC为0.806(95%CI 0.778-0.835)。

该研究从MIMIC-IV v2.0数据库中纳入符合Sepsis-3标准的脓毒性休克患者3295例,按70%与30%随机分为训练集(2307例,28天死亡792例,死亡率34.33%)和验证集(988例,28天死亡339例,死亡率34.31%)。比较CART、RF、SVM、LR和SL五种机器学习算法构建的模型,RF、SVM、LR在验证集预测28天死亡的AUC分别为0.823、0.823、0.810,高于CART(0.750)和SL(0.756)。通过LASSO回归、RF和XGBoost算法交叉确定16个最优预测变量,构建的Logistic回归模型在验证集AUC为0.806(95%CI 0.778-0.835),校准曲线和DCA显示准确性高、净获益最高可达0.3,优于传统单一功能评分模型(APS III、SAPS III、SOFA)。

要点

  • 在3295例脓毒性休克患者中,28天死亡1131例,总死亡率为34.32%。
  • 验证集中RF、SVM、LR模型预测28天死亡的AUC分别为0.823(95%CI 0.795-0.849)、0.823(95%CI 0.796-0.849)、0.810(95%CI 0.782-0.838),均高于CART(0.750,95%CI 0.717-0.782)和SL(0.756,95%CI 0.724-0.789)。
  • 基于16个最优预测变量(包括最高pH值、最高Alb、最高体温、最低Lac、最高Lac、最高SCr、最高Ca2+、最低Hb、最低WBC、年龄、SAPS III评分、最高WBC、APS III评分、最低Na+、BMI、最短APTT)构建的Logistic回归模型在验证集AUC为0.806(95%CI 0.778-0.835)。
  • 该模型校准曲线和DCA显示准确性高,净获益最高可达0.3,优于基于单一功能评分的传统模型:APS III评分AUC 0.746(95%CI 0.715-0.778)、SAPS III评分0.765(95%CI 0.734-0.796)、SOFA评分0.625(95%CI 0.589-0.661)。

适用人群与场景

  • 从MIMIC-IV v2.0数据库中选取符合Sepsis-3标准的脓毒性休克患者,共3295例,其中28天内死亡1131例(34.32%),存活2164例。

诊断标准与关键阈值

  • 脓毒性休克诊断采用Sepsis-3标准。

研究设计与关键结果

  • 研究类型为基于MIMIC-IV v2.0数据库的预测模型构建与验证研究,共纳入3295例脓毒性休克患者,按随机分配原则70%为训练集(2307例,28天死亡792例,死亡率34.33%),30%为验证集(988例,28天死亡339例,死亡率34.31%)。
  • 从人口学特征和基础生命体征、ICU入住24小时内血清指标、可能影响指标的并发症、功能评分和高级生命支持三方面提取预测变量。
  • 比较五种主流机器学习算法(CART、RF、SVM、LR、SL)构建的模型对脓毒性休克患者28天死亡的预测效能,验证集中RF、SVM、LR的AUC分别为0.823(95%CI 0.795-0.849)、0.823(95%CI 0.796-0.849)、0.810(95%CI 0.782-0.838),高于CART(AUC=0.750,95%CI 0.717-0.782)和SL(AUC=0.756,95%CI 0.724-0.789),确定上述三种为最佳算法模型。
  • 通过LASSO回归、RF和XGBoost算法交叉确定16个最优预测变量:最高pH值、最高白蛋白(Alb)、最高体温、最低乳酸(Lac)、最高Lac、最高血清肌酐(SCr)、最高Ca2+、最低血红蛋白(Hb)、最低白细胞计数(WBC)、年龄、简化急性生理学评分III(SAPS III)、最高WBC、急性生理学评分III(APS III)、最低Na+、体重指数(BMI)、ICU入住24小时内最短活化部分凝血活酶时间(APTT)。
  • 用上述16个变量构建的Logistic回归模型为最佳预测模型,验证集AUC为0.806(95%CI 0.778-0.835);校准曲线和DCA曲线显示该模型准确性高,净获益最高可达0.3,显著优于基于单一功能评分的传统模型:APS III评分AUC 0.746(95%CI 0.715-0.778)、SAPS III评分AUC 0.765(95%CI 0.734-0.796)、SOFA评分AUC 0.625(95%CI 0.589-0.661)。

证据类型、等级与局限

  • 证据类型:基于MIMIC-IV v2.0数据库的预测模型构建与验证研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,使用pH值、Alb、体温、Lac、SCr、Ca2+、Hb、WBC、SAPS III评分、APS III评分、Na+、BMI、APTT等16个最优预测变量构建的Logistic回归模型,是预测脓毒性休克患者28天死亡风险的最佳预测模型,其性能稳定,具有较高的区分能力和准确性。

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 construct and validate the best predictive model for 28-day death risk in patients with septic shock based on different supervised machine learning algorithms.

METHODS: The patients with septic shock meeting the Sepsis-3 criteria were selected from Medical Information Mart for Intensive Care-IV v2.0 (MIMIC-IV v2.0). According to the principle of random allocation, 70% of these patients were used as the training set, and 30% as the validation set. Relevant predictive variables were extracted from three aspects: demographic characteristics and basic vital signs, serum indicators within 24 hours of intensive care unit (ICU) admission and complications possibly affecting indicators, functional scoring and advanced life support. The predictive efficacy of models constructed using five mainstream machine learning algorithms including decision tree classification and regression tree (CART), random forest (RF), support vector machine (SVM), linear regression (LR), and super learner [SL; combined CART, RF and extreme gradient boosting (XGBoost)] for 28-day death in patients with septic shock was compared, and the best algorithm model was selected. The optimal predictive variables were determined by intersecting the results from LASSO regression, RF, and XGBoost algorithms, and a predictive model was constructed. The predictive efficacy of the model was validated by drawing receiver operator characteristic curve (ROC curve), the accuracy of the model was assessed using calibration curves, and the practicality of the model was verified through decision curve analysis (DCA).

RESULTS: A total of 3 295 patients with septic shock were included, with 2 164 surviving and 1 131 dying within 28 days, resulting in a mortality of 34.32%. Of these, 2 307 were in the training set (with 792 deaths within 28 days, a mortality of 34.33%), and 988 in the validation set (with 339 deaths within 28 days, a mortality of 34.31%). Five machine learning models were established based on the training set data. After including variables at three aspects, the area under the ROC curve (AUC) of RF, SVM, and LR machine learning algorithm models for predicting 28-day death in septic shock patients in the validation set was 0.823 [95% confidence interval (95%CI) was 0.795-0.849], 0.823 (95%CI was 0.796-0.849), and 0.810 (95%CI was 0.782-0.838), respectively, which were higher than that of the CART algorithm model (AUC = 0.750, 95%CI was 0.717-0.782) and SL algorithm model (AUC = 0.756, 95%CI was 0.724-0.789). Thus above three algorithm models were determined to be the best algorithm models. After integrating variables from three aspects, 16 optimal predictive variables were identified through intersection by LASSO regression, RF, and XGBoost algorithms, including the highest pH value, the highest albumin (Alb), the highest body temperature, the lowest lactic acid (Lac), the highest Lac, the highest serum creatinine (SCr), the highest Ca2+, the lowest hemoglobin (Hb), the lowest white blood cell count (WBC), age, simplified acute physiology score III (SAPS III), the highest WBC, acute physiology score III (APS III), the lowest Na+, body mass index (BMI), and the shortest activated partial thromboplastin time (APTT) within 24 hours of ICU admission. ROC curve analysis showed that the Logistic regression model constructed with above 16 optimal predictive variables was the best predictive model, with an AUC of 0.806 (95%CI was 0.778-0.835) in the validation set. The calibration curve and DCA curve showed that this model had high accuracy and the highest net benefit could reach 0.3, which was significantly outperforming traditional models based on single functional score [APS III score, SAPS III score, and sequential organ failure assessment (SOFA) score] with AUC (95%CI) of 0.746 (0.715-0.778), 0.765 (0.734-0.796), and 0.625 (0.589-0.661), respectively.

CONCLUSIONS: The Logistic regression model, constructed using 16 optimal predictive variables including pH value, Alb, body temperature, Lac, SCr, Ca2+, Hb, WBC, SAPS III score, APS III score, Na+, BMI, and APTT, is identified as the best predictive model for the 28-day death risk in patients with septic shock. Its performance is stable, with high discriminative ability and accuracy.

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. Xie Z, Jin J, Liu D, et al. [Constructing a predictive model for the death risk of patients with septic shock based on supervised machine learning algorithms]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2024. PMID: 38813626. doi:10.3760/cma.j.cn121430-20230930-00832

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。