摘要
目的基于机器学习算法构建药物中毒患者ICU住院时间延长的预测模型。方法纳入美国重症监护医学信息数据库Ⅳ(MIMIC-Ⅳ)与电子重症监护病房合作研究数据库(eICU-CRD)中的药物中毒患者,按ICU住院时间分为非延长组(≤48 h)和延长组(>48 h)。按7∶3将MIMIC-Ⅳ中1342例患者分为训练集(939例)与测试集(403例),eICU-CRD作为外部测试集(2144例)。在训练集中,通过单因素分析和最小绝对收缩和选择算子(LASSO)回归联合筛选变量,利用6种机器学习算法(逻辑回归、极端梯度提升、轻量级梯度提升机、随机森林、决策树、支持向量机)建模。同时,采用受试者工作特征(ROC)曲线、霍斯默-莱梅肖(H-L)检验、Brier评分及决策曲线分析(DCA)在内部和外部测试集中评估模型性能。结果训练集中共筛选出7个关键变量,分别为脑血管疾病、肝脏疾病、吸入性肺炎、脓毒症、呼吸频率、序贯器官衰竭估计(SOFA)评分和机械通气。逻辑回归模型在训练集中表现最佳[曲线下面积(AUC)=0.767,95%置信区间(CI)(0.667,0.868),P<0.001)],其在内部测试集中的AUC为0.762[95%CI(0.712,0.811),P<0.001],在外部测试集中的AUC为0.732[95%CI(0.708,0.756),P<0.001]。且逻辑回归模型在内部及外部测试中均具良好校准度和净收益。结论本研究构建的逻辑回归模型由7个预测因素组成,包括脑血管疾病、肝脏疾病、吸入性肺炎、脓毒症、呼吸频率、SOFA评分和机械通气,可有效预测药物中毒患者ICU住院时间延长风险,有助于临床早期识别和干预。
Objective To develop a prediction model for the prolonged ICU stay in patients with drug poisoning based on machine learning algorithms.Methods Drug poisoning patients included in the Medical Information Mart for Intensive CareⅣ(MIMIC-Ⅳ)and Electronic Intensive Care Unit-Collaborative Research Database(eICU-CRD)were divided into a non-prolonged group(≤48 hours)and a prolonged group(>48 hours)according to the length of ICU stay.A total of 1342 patients in MIMIC-Ⅳwere divided into a training dataset(939 cases)and a test dataset(403 cases)at a ratio of 7∶3,with eICU-CRD serving as an external test dataset(2144 cases).In the training dataset,variables were jointly screened through single-factor analysis and least absolute shrinkage and selection operator(LASSO)regression.Six machine learning algorithms(logistic regression,extreme gradient boosting,light gradient boosting machine,random forest,decision tree,and support vector machine)were used for modeling.Meanwhile,the receiver operating characteristic(ROC)curve,Hosmer-Lemeshow(H-L)test,Brier score,and decision curve analysis(DCA)were used to evaluate the model performance in both internal and external test datasets.Results Seven critical predictors were screened out in the training dataset:cerebrovascular disease,liver disease,aspiration pneumonia,sepsis,respiratory rate,sequential organ failure assessment(SOFA)score,and mechanical ventilation.The logistic regression model performed best in the training dataset[area under the curve(AUC)=0.767,95%confidence interval(CI)(0.667,0.868),P<0.001].Its AUC was 0.762[95%CI(0.712,0.811),P<0.001]in the internal test dataset,and 0.732[95%CI(0.708,0.756),P<0.001]in the external test dataset.Moreover,the logistic regression model showed good calibration and net returns in both internal and external test datasets.Conclusions The logistic regression model constructed in this study consists of seven predictive factors,including cerebrovascular disease,liver disease,aspiration pneumonia,sepsis,respiratory rate,SOFA score,and mechanical ventilation.It can effectively predict the risk of prolonged ICU stay in drug poisoning patients,which is helpful for early clinical identification and intervention.
作者
戴辉水
吕嵩
张劲松
巴根
石齐芳
Dai Huishui;Lyu Song;Zhang Jinsong;Ba Gen;Shi Qifang(Department of Intensive Care Medicine,Mingguang People's Hospital,Chuzhou 239400,China;Department of Emergency and Critical Care Medicine,the First Affiliated Hospital with Nanjing Medical University,Nanjing 210029,China)
出处
《中华危重症医学杂志(电子版)》
2025年第4期274-281,共8页
Chinese Journal of Critical Care Medicine:Electronic Edition
基金
国家自然科学基金项目(82172184)
