Sun Meina, Liu Shihui, Min Jie, Zhong Lei, Zhang Jinyu, Du Zhian
Department of Intensive Care Unit, First Affiliated Hospital of Jinzhou Medical University, Jinzhou, China.
Department of Intensive Care Unit, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou University, Huzhou, China.
Front Med (Lausanne). 2025 May 8;12:1570928. doi: 10.3389/fmed.2025.1570928. eCollection 2025.
At present, there are no specialized models for predicting mortality risk in patients with alcoholic cirrhosis complicated by severe acute kidney injury (AKI) in the ICU. This study aims to develop and validate machine learning models to predict the mortality risk of this population during hospitalization.
A retrospective analysis was conducted on 856 adult patients with alcoholic cirrhosis complicated by severe AKI, utilizing data from the MIMIC-IV database. Within the dataset, 627 patients from the period 2008-2016 were designated as the training cohort, whereas 229 patients from 2017 to 2019 comprised the temporal external validation cohort. Feature selection was conducted utilizing LASSO regression, which was subsequently followed by the development of eight distinct machine learning models. The performance of these models in the temporal external validation cohort was rigorously assessed using the area under the receiver operating characteristic curve (AUROC) to determine the optimal model. The model was interpreted using the SHAP method, and nomograms were subsequently constructed. A comprehensive evaluation was performed from the perspectives of discrimination (assessed via AUROC and AUPRC), calibration (using calibration curves), and clinical utility (evaluated through DCA curves).
LASSO regression identified nine key features: total bilirubin, acute respiratory failure, vasopressin, septic shock, oliguria, AKI stage, lactate, fresh frozen plasma transfusion, and norepinephrine. In the temporal external validation cohort, the Lasso-LR model achieved the highest AUROC value of 0.809, establishing it as the optimal model. We developed both a static nomogram and a web-based dynamic nomogram (https://zhangjingyu123456.shinyapps.io/dynnomapp/) for visualization purposes. In the nomogram model, the AUROC for the training cohort and temporal external validation cohort were 0.836 (95% CI: 0.802-0.870) and 0.809 (95% CI: 0.754-0.865), respectively. The calibration slope and Brier score for the training cohort were 1.000 and 0.146, respectively; for the temporal external validation cohort, these values were 0.808 and 0.177, respectively. The DCA curves indicate that the model has certain clinical application value.
The Lasso-LR model exhibits robust predictive capability for in-hospital mortality among patients with alcoholic cirrhosis complicated by AKI, offering valuable prognostic insights and individualized treatment decision support for healthcare professionals.
目前，尚无专门用于预测重症监护病房（ICU）中酒精性肝硬化合并严重急性肾损伤（AKI）患者死亡风险的模型。本研究旨在开发并验证机器学习模型，以预测该人群住院期间的死亡风险。
利用多中心重症医学信息数据库第四版（MIMIC-IV）的数据，对856例成年酒精性肝硬化合并严重AKI患者进行回顾性分析。在数据集中，将2008年至2016年期间的627例患者指定为训练队列，而2017年至2019年的229例患者组成时间外部验证队列。利用套索（LASSO）回归进行特征选择，随后开发八个不同的机器学习模型。使用受试者工作特征曲线下面积（AUROC）对这些模型在时间外部验证队列中的性能进行严格评估，以确定最佳模型。使用SHAP方法对模型进行解释，随后构建列线图。从区分度（通过AUROC和AUPRC评估）、校准（使用校准曲线）和临床实用性（通过决策曲线分析（DCA）曲线评估）的角度进行全面评估。
LASSO回归确定了九个关键特征：总胆红素、急性呼吸衰竭、血管加压素、感染性休克、少尿、AKI分期、乳酸、新鲜冰冻血浆输注和去甲肾上腺素。在时间外部验证队列中，Lasso-LR模型获得了最高的AUROC值0.809，被确定为最佳模型。为了便于可视化，我们开发了一个静态列线图和一个基于网络的动态列线图（https://zhangjingyu123456.shinyapps.io/dynnomapp/）。在列线图模型中，训练队列和时间外部验证队列的AUROC分别为0.836（95%CI：0.802-0.870）和0.809（95%CI：0.754-0.865）。训练队列的校准斜率和布里尔（Brier）评分分别为1.000和0.146；时间外部验证队列的这些值分别为0.808和0.177。DCA曲线表明该模型具有一定的临床应用价值。
Lasso-LR模型对酒精性肝硬化合并AKI患者的院内死亡率具有强大的预测能力，为医护人员提供了有价值的预后见解和个性化治疗决策支持。
