Zhang Tao, Nan Zi-Han, Fan Xiao-Xuan, Pang Jing-Xiao, Zhao Cong-Cong, Xin Yan, Hu Zhen-Jie, Guo Shao-Han
Department of Intensive Care Unit, The Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei Province, 050000, People's Republic of China.
Department of Intensive Care Unit, The Third Hospital of Shijiazhuang, Shijiazhuang, Hebei Province, 050000, People's Republic of China.
J Multidiscip Healthc. 2025 Sep 5;18:5535-5550. doi: 10.2147/JMDH.S533031. eCollection 2025.
This study aimed to develop and validate an interpretable machine learning (ML) model to predict 28-day all-cause mortality in critically ill patients undergoing continuous renal replacement therapy (CRRT), facilitating early risk stratification and clinical decision-making.
Data from 1362 CRRT patients were analyzed, including 1224 from the Medical Information Mart for Intensive Care IV database (training cohort) and 138 from a Chinese hospital (external validation cohort). Feature selection was performed using least absolute shrinkage and selection operator, support vector machine-recursive feature elimination, and Boruta algorithms. Nine machine learning models were constructed and compared, including Gaussian process (GP), ensemble methods (gradient boosting machine and eXtreme gradient boosting), and other classifiers. Model performance was assessed via the area under the receiver operating characteristic curve (AUC), decision curve analysis, and other metrics. The SHapley Additive exPlanation (SHAP) method was used to interpret the ML models.
The GP model demonstrated consistent predictive performance across all cohorts, with training (AUC=0.841, accuracy=76.8%, sensitivity=65.5%), internal validation (AUC=0.794, accuracy=73.4%, sensitivity=60.0%), and external validation (AUC=0.780, accuracy=63.8%, sensitivity=39.0%) sets. Key predictors included red cell distribution width, age, lactate, septic shock, and vasoactive drug use. SHAP analysis provided transparent insights into feature contributions.
The GP-based model accurately predicts 28-day mortality in CRRT patients and demonstrates strong generalizability. By integrating SHAP explanations, it offers clinicians an interpretable tool to identify high-risk patients early, potentially improving outcomes.
本研究旨在开发并验证一种可解释的机器学习（ML）模型，以预测接受持续肾脏替代治疗（CRRT）的危重症患者的28天全因死亡率，促进早期风险分层和临床决策。
分析了1362例CRRT患者的数据，其中1224例来自重症监护医学信息集市IV数据库（训练队列），138例来自一家中国医院（外部验证队列）。使用最小绝对收缩和选择算子、支持向量机递归特征消除和Boruta算法进行特征选择。构建并比较了9种机器学习模型，包括高斯过程（GP）、集成方法（梯度提升机和极端梯度提升）以及其他分类器。通过受试者操作特征曲线下面积（AUC）、决策曲线分析和其他指标评估模型性能。使用SHapley加法解释（SHAP）方法解释ML模型。
GP模型在所有队列中均表现出一致的预测性能，训练集（AUC=0.841，准确率=76.8%，灵敏度=65.5%）、内部验证集（AUC=0.794，准确率=73.4%，灵敏度=60.0%）和外部验证集（AUC=0.780，准确率=63.8%，灵敏度=39.0%）。关键预测因素包括红细胞分布宽度、年龄、乳酸、感染性休克和血管活性药物的使用。SHAP分析提供了关于特征贡献的透明见解。
基于GP的模型能够准确预测CRRT患者的28天死亡率，并具有很强的通用性。通过整合SHAP解释，它为临床医生提供了一种可解释的工具，以便早期识别高危患者，可能改善治疗结果。
