文献速递重症综合管理与镇静镇痛消化、代谢与肾脏急症心脑血管急症

老年脓毒症相关脑病机器学习预测模型的建立与评价

[Establishment and evaluation of a machine learning prediction model for sepsis-related encephalopathy in the elderly].
PubMed 文献 · Zhonghua Wei Zhong Bing Ji Jiu Yi Xue · 2025-01-01
一句话结论基于MIMIC-IV 2.2的老年脓毒症患者数据构建的机器学习模型可预测脓毒症相关脑病,支持向量机模型AUC 0.748、敏感度超85%,有助于早期识别高危患者。

该研究从MIMIC-IV 2.2数据库纳入2008至2023年60岁以上、主要诊断为脓毒症且入住ICU的患者2204例,其中840例发生脓毒症相关脑病(38.1%)。研究采用单因素Logistic回归筛选变量,按7:3随机分为训练集与验证集,构建多因素Logistic回归列线图模型,并比较多层感知机、支持向量机、朴素贝叶斯、梯度提升机、随机森林和极端梯度提升等多种机器学习算法。验证集中列线图模型AUC为0.723,校准曲线显示预测概率与观察概率一致性良好;支持向量机模型与随机森林模型预测性能相对较好,AUC分别为0.748和0.739,敏感度均超过85%。通过SHAP算法解释极端梯度提升模型,显示急性生理评分III(SHAP值0.871)、年龄(SHAP值0.521)和牛津急性疾病严重度评分(SHAP值0.443)是影响模型预测性能的重要因素。作者认为该机器学习模型预测能力良好,对老年脓毒症患者脓毒症相关脑病的早期风险识别有重要应用价值。

要点

  • 研究纳入60岁以上脓毒症ICU患者2204例,脓毒症相关脑病发生率为38.1%(840例)。
  • 多因素Logistic回归显示年龄(OR=1.05,95%CI 1.03-1.06)、急性生理评分III(OR=1.02,95%CI 1.01-1.02)、牛津急性疾病严重度评分(OR=1.04,95%CI 1.03-1.06)与脓毒症相关脑病概率升高相关。
  • 气管插管(OR=0.40,95%CI 0.19-0.88)、气管切开(OR=0.20,95%CI 0.07-0.53)、连续肾脏替代治疗(OR=0.32,95%CI 0.15-0.70)、脑血管病(OR=0.31,95%CI 0.16-0.60)与脓毒症相关脑病概率降低相关。
  • 验证集中列线图模型AUC为0.723,校准曲线一致性良好;支持向量机模型AUC 0.748、随机森林模型AUC 0.739,敏感度均超过85%。
  • SHAP分析显示急性生理评分III(SHAP值0.871)、年龄(SHAP值0.521)、牛津急性疾病严重度评分(SHAP值0.443)是影响极端梯度提升模型预测性能的重要因子。

适用人群与场景

  • 2008至2023年入住ICU、年龄超过60岁、主要诊断为脓毒症的患者,数据来自MIMIC-IV 2.2数据库。

研究设计与关键结果

  • 研究类型为基于MIMIC-IV 2.2数据库的预测模型构建与评价研究,最终纳入2204例老年脓毒症患者,其中840例发生脓毒症相关脑病(38.1%)。
  • 单因素Logistic回归筛选出21个与脓毒症相关脑病相关的变量,数据按7:3随机分为训练集与验证集。
  • 多因素Logistic回归显示与脓毒症相关脑病概率降低相关的因素包括:气管插管(OR=0.40,95%CI 0.19-0.88,P<0.001)、氧疗(OR=0.76,95%CI 0.53-0.95,P=0.023)、气管切开(OR=0.20,95%CI 0.07-0.53,P<0.001)、连续肾脏替代治疗(OR=0.32,95%CI 0.15-0.70,P<0.001)、脑血管病(OR=0.31,95%CI 0.16-0.60,P<0.001)、风湿性疾病(OR=0.44,95%CI 0.19-0.99,P<0.001)、男性(OR=0.68,95%CI 0.54-0.86,P=0.001)、最大阴离子间隙(OR=0.95,95%CI 0.93-0.97,P<0.001)。
  • 多因素Logistic回归显示与脓毒症相关脑病概率升高相关的因素包括:年龄(OR=1.05,95%CI 1.03-1.06,P<0.001)、急性生理评分III(OR=1.02,95%CI 1.01-1.02,P<0.001)、牛津急性疾病严重度评分(OR=1.04,95%CI 1.03-1.06,P<0.001)、住院时长(OR=1.01,95%CI 1.01-1.02,P<0.001)。
  • 基于上述变量构建列线图模型,验证集ROC曲线分析显示AUC为0.723,校准曲线显示模型预测概率与观察概率一致性良好。
  • 在多层感知机、支持向量机、朴素贝叶斯、梯度提升机、随机森林和极端梯度提升算法中,支持向量机模型与随机森林模型预测性能相对较好,AUC分别为0.748和0.739,敏感度均超过85%。
  • 通过SHAP算法解释极端梯度提升模型,结果显示急性生理评分III(SHAP值0.871)、年龄(SHAP值0.521)、牛津急性疾病严重度评分(SHAP值0.443)是影响模型预测性能的重要因素。

证据类型、等级与局限

  • 证据类型为基于MIMIC-IV 2.2数据库的预测模型构建与评价研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为基于机器学习的脓毒症相关脑病预测模型预测能力良好,对老年脓毒症患者脓毒症相关脑病的早期风险识别有重要应用价值。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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 machine learning prediction model for sepsis-associated encephalopathy (SAE), and analyze the application value of the model on early identification of SAE risk in elderly septic patients.

METHODS: Patients aged over 60 years with a primary diagnosis of sepsis admitted to intensive care unit (ICU) from 2008 to 2023 were selected from Medical Information Mart for Intensive Care-IV 2.2 (MIMIC-IV 2.2). Demographic variables, disease severity scores, comorbidities, interventions, laboratory indicators, and hospitalization details were collected. Key factors associated with SAE were identified using univariate Logistic regression analysis. The data were randomly divided into training and validation sets in a 7 : 3 ratio. Multivariable Logistic regression analysis was conducted in the training set and visualized using a nomogram model for prediction of SAE. The discrimination of the model was evaluated in the validation set using the receiver operator characteristic curve (ROC curve), and its calibration was assessed using calibration curve. Furthermore, multiple machine learning algorithms, including multi-layer perceptron (MLP), support vector machine (SVM), naive bayes (NB), gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGB), were constructed in the training set. Their predictive performance was subsequently evaluated on the validation set. Taking the XGB model as an example, the interpretability of the model through the SHapley Additive exPlanations (SHAP) algorithm was enhanced to identify the key predictive factors and their contributions.

RESULTS: A total of 2 204 septic patients were finally enrolled, of whom 840 developed SAE (38.1%). A total of 21 variables associated with SAE were screened through univariate Logistic regression analysis. Multivariable Logistic regression analysis showed that endotracheal intubation [odds ratio (OR) = 0.40, 95% confidence interval (95%CI) was 0.19-0.88, P < 0.001], oxygen therapy (OR = 0.76, 95%CI was 0.53-0.95, P = 0.023), tracheotomy (OR = 0.20, 95%CI was 0.07-0.53, P < 0.001), continuous renal replacement therapy (CRRT; OR = 0.32, 95%CI was 0.15-0.70, P < 0.001), cerebrovascular disease (OR = 0.31, 95%CI was 0.16-0.60, P < 0.001), rheumatic disease (OR = 0.44, 95%CI was 0.19-0.99, P < 0.001), male (OR = 0.68, 95%CI was 0.54-0.86, P = 0.001), and maximum anion gap (AG; OR = 0.95, 95%CI was 0.93-0.97, P < 0.001) were associated with an decreased probability of SAE, and age (OR = 1.05, 95%CI was 1.03-1.06, P < 0.001), acute physiology score III (APSIII; OR = 1.02, 95%CI was 1.01-1.02, P < 0.001), Oxford acute severity of illness score (OASIS; OR = 1.04, 95%CI was 1.03-1.06, P < 0.001), and length of hospital stay (OR = 1.01, 95%CI was 1.01-1.02, P < 0.001) were associated with an increased probability of SAE. A nomogram model was constructed based on these variables. In the validation set, ROC curve analysis showed that the model achieved an area under the ROC curve (AUC) of 0.723, and the calibration curve showed good consistency between the predicted probability of the model and the observed probability. Among the machine learning algorithms, including MLP, SVM, NB, GBM, RF, and XGB, the SVM model and RF model demonstrated relatively good predictive performance, with AUC of 0.748 and 0.739, respectively, and the sensitivity was both exceeding 85%. The predictive performance of the XGB model was explained through SHAP analysis, and the results indicated that APSIII score (SHAP value was 0.871), age (SHAP value was 0.521), and OASIS score (SHAP value was 0.443) were important factors affecting the predictive performance of the model.

CONCLUSIONS: The machine learning-based SAE prediction model exhibits good predictive capability and holds significant application value for the early identification of SAE risk in elderly septic patients.

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. Yue X, Wang Y, Li Z, et al. [Establishment and evaluation of a machine learning prediction model for sepsis-related encephalopathy in the elderly]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2025. PMID: 41331889. doi:10.3760/cma.j.cn121430-20250227-00157

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。