目的   通过机器学习方法构建脓毒症谵妄患者30 d死亡的预测模型，并识别关键预测因子。方法   采用基于医疗信息集成重症监护数据库（Medical Information Mart for Intensive Care IV）的回顾性队列研究方法，boruta筛选重要特征，并通过决策树，K近邻，LightGBM，随机森林，支持向量机，XGBoost构建模型进行分析，通过ROC曲线下面积进行评估，利用F1分数、召回率、精确率、特异度、灵敏度和阳性预测值比较模型表现。结果  XGBoost模型在训练集和验证集中的ROC曲线下面积分别为0.906和0.762，表明该模型具有良好的预测能力，入院年龄、红细胞分布宽度和白细胞计数是最重要的预测因子。结论   基于机器学习的脓毒症谵妄患者预后预测模型展现出良好的预测效能，为临床早期干预提供了重要参考依据。

       Objective  To construct a  30-day mortality  prediction model for  patients with  sepsis-associated  delirium using machine learning methods and identify key predictive factors．Methods  A  retrospective cohort study was conducted based on the Medical Information Mart for Intensive Care IV database．Important features were selected using the Boruta algorithm，and models including Decision Tree，K-Nearest Neighbors，LightGBM，Random Forest，Support Vector Machine，and XGBoost were constructed and analyzed．Model performance was evaluated using the area under the reciver operater characteristic（ROC）curve（AUC），along with F1 score，recall，precision，specificity，sensitivity，and positive predictive value．Results  The XGBoost model demonstrated strong predictive performance，with AUC values of 0.906 in the training set and 0.762 in the test set．Key predictors identified included admission age，red blood cell distribution width，and white blood cell count．Conclusions  The machine learning-based prediction model for sepsis-associated delirium prognosis exhibits robust predictive efficacy，providing a valuable tool for early clinical intervention．

目的 构建并验证主动脉夹层B型（TBAD）患者急性期预后的列线图预测模型,帮助临床医生在急性期内更准确地评估TBAD患者的死亡风险,并制定更合适的治疗策略。方法 回顾性分析从重症监护医学信息数据库v2.2 中提取的399例 TBAD患者的人口学资料和临床资料,结局为TBAD患者急性期（≤14 d）内死亡。先采用最小绝对收缩选择算法回归筛选特征变量,再采用多因素分析确定独立预后因素,并据此构建预测模型。通过受试者工作特征曲线、校准曲线、决策曲线分析（DCA）评价列线图预测模型的性能和临床适用性。结果 APS Ⅲ评分、二氧化碳总量、红细胞分布宽度为TBAD患者14 d内死亡的独立预测因素。列线图预测模型在内部验证中的受试者工作特征曲线下面积为0.776（95% CI：0.691 ~ 0.860）,Hosmer-Lemeshow 检验P=0.604,校准曲线和标准曲线高度重合,表明该模型具有良好的区分度和校准度。同时,DCA曲线显示,预测模型在大部分的阈值概率范围内提供了显著的净收益。结论 本研究基于APS Ⅲ评分、二氧化碳总量、红细胞分布宽度构建的列线图预测模型可以较准确地预测TBAD患者14 d内的死亡风险,有助于临床医生制定更合适的个体化治疗策略。

Objective To develop and verify a nomogram for predicting acute phase outcomes in patients with type B aortic dissection（TBAD）,enabling clinicians to more precisely evaluate mortality risk in TBAD patients during the acute stage and to devise better treatment plans．Methods This retrospective study analyzed demographic and clinical data of 399 TBAD patients from the Medical Information Mart for Intensive Care IV v2.2,focusing on mortality within 14 days of the acute phase in TBAD patients． Initially,the Least Absolute Shrinkage and Selection Operator regression was employed for feature variable selection,and then multivariate analysis was used to identify independent prognostic factors for constructing the predictive model．The nomogram predictive model's effectiveness and clinical applicability were assessed via the Receiver Operating Characteristic curve,calibration curve,and Decision Curve Analysis（DCA）．Results Acute Physidogy Score Ⅲ score,total carbon dioxide,and red blood cell distribution width emerged as independent predictors of 14-day mortality in TBAD patients．The internal validation of the nomogram predictive model showed an area under the curve of 0.776（95%CI：0.691-0.860）,with a Hosmer-Lemeshow test P-value of 0.604． The close alignment of the calibration and standard curves suggested the model's strong discriminative power and calibration． Furthermore,the DCA curve revealed that the predictive model offered substantial net benefits within a wide range of threshold probabilities．Conclusions This study's nomogram,developed using APS Ⅲ score,total carbon dioxide,and red blood cell distribution width,accurately predicts the 14-day mortality risk in TBAD patients,assisting clinicians in creating better personalized treatment plans．

       目的   构建并验证主动脉夹层B型（TBAD）患者急性期预后的列线图预测模型，帮助临床医生在急性期内更准确地评估TBAD患者的死亡风险，并制定更合适的治疗策略。方法   回顾性分析从重症监护医学信息数据库v2.2 中提取的399例 TBAD患者的人口学资料和临床资料，结局为TBAD患者急性期（≤14 d）内死亡。先采用最小绝对收缩选择算法回归筛选特征变量，再采用多因素分析确定独立预后因素，并据此构建预测模型。通过受试者工作特征曲线、校准曲线、决策曲线分析（DCA）评价列线图预测模型的性能和临床适用性。结果  APS Ⅲ评分、二氧化碳总量、红细胞分布宽度为TBAD患者14 d内死亡的独立预测因素。列线图预测模型在内部验证中的受试者工作特征曲线下面积为0.776（95% CI：0.691 ~ 0.860），Hosmer-Lemeshow 检验P=0.604，校准曲线和标准曲线高度重合，表明该模型具有良好的区分度和校准度。同时，DCA曲线显示，预测模型在大部分的阈值概率范围内提供了显著的净收益。结论   本研究基于APS Ⅲ评分、二氧化碳总量、红细胞分布宽度构建的列线图预测模型可以较准确地预测TBAD患者14 d内的死亡风险，有助于临床医生制定更合适的个体化治疗策略。

       Objective  To develop and verify a nomogram for predicting acute phase outcomes in patients with type B aortic dissection（TBAD），enabling clinicians to more precisely evaluate mortality  risk in TBAD patients during the acute stage and to devise better treatment plans．Methods  This retrospective study analyzed demographic and clinical data of 399 TBAD patients from the Medical Information Mart for Intensive Care IV v2.2，focusing on mortality within 14 days of the acute phase in TBAD patients．Initially，the Least Absolute Shrinkage and Selection Operator regression was employed for feature variable selection，and then multivariate analysis was used to identify independent prognostic factors for constructing the predictive model．The nomogram predictive model’s effectiveness and clinical applicability were assessed via the Receiver Operating Characteristic curve，calibration curve，and Decision Curve Analysis（DCA）．Results  Acute Physidogy Score Ⅲ score，total carbon dioxide，and red blood cell distribution width emerged as independent predictors of 14-day mortality in TBAD patients．The internal validation of the nomogram predictive model showed an area under the curve of 0.776（95%CI：0.691-0.860），with a Hosmer-Lemeshow test P-value of 0.604．The close alignment of the calibration and standard curves suggested the model’s strong discriminative power and calibration．Furthermore，the DCA curve  revealed that the predictive model offered substantial net benefits within a wide  range of threshold probabilities．Conclusions  This study's nomogram，developed using APS Ⅲ score，total carbon dioxide，and  red blood cell distribution width，accurately predicts the 14-day mortality risk in TBAD patients，assisting clinicians in creating better personalized treatment plans．