Xu Yang, Song Chunxiao, Wei Wenping, Miao Runfeng
Department of Emergency, Affiliated Hospital of Yangzhou University, Yangzhou University, Jiangsu, China.
Department of Pediatrics, Affiliated Hospital of Yangzhou University, Yangzhou University, Jiangsu, China.
PLoS One. 2025 Jun 12;20(6):e0325151. doi: 10.1371/journal.pone.0325151. eCollection 2025.
This study aimed to develop an innovative early prediction model for acute kidney injury (AKI) following cardiac surgery in intensive care unit (ICU) settings, leveraging preoperative and postoperative clinical variables, and to identify key risk factors associated with AKI.
Retrospective data from 1,304 cardiac surgery patients (1,028 AKI cases and 276 non-AKI controls) were extracted from the MIMIC-IV database. We analyzed three datasets: preoperative 48-hour averages, preoperative 48-hour maxima, and postoperative 24-hour maxima of critical physiological parameters. Using logistic regression, LASSO regression, and random forest (RF) algorithms, we constructed nine prediction models, evaluating their performance via AUROC, sensitivity, specificity, Youden's index, decision curve analysis (DCA), and calibration curves.
Our findings demonstrate that all models achieved AUROC values >0.7, with three models exceeding 0.75. Notably, the logistic regression model incorporating preoperative 48-hour maximum values and postoperative 24-hour maximum values exhibited the highest predictive accuracy (AUROC = 0.755, 95%CI: 0.7185-0.7912), outperforming other configurations. This model's superiority lies in its integration of dynamic preoperative and postoperative variables, capturing both baseline risks and acute postoperative changes. By systematically comparing multiple machine learning approaches, our study highlights the utility of combining temporal physiological metrics to enhance AKI risk stratification. These results offer a robust, clinically applicable tool for early AKI prediction, enabling proactive interventions to improve outcomes in cardiac surgery patients.
本研究旨在利用术前和术后临床变量，开发一种用于重症监护病房（ICU）环境下心脏手术后急性肾损伤（AKI）的创新早期预测模型，并识别与AKI相关的关键风险因素。
从MIMIC-IV数据库中提取1304例心脏手术患者的回顾性数据（1028例AKI病例和276例非AKI对照）。我们分析了三个数据集：关键生理参数的术前48小时平均值、术前48小时最大值和术后24小时最大值。使用逻辑回归、LASSO回归和随机森林（RF）算法，我们构建了九个预测模型，并通过受试者工作特征曲线下面积（AUROC）、灵敏度、特异性、约登指数、决策曲线分析（DCA）和校准曲线评估其性能。
我们的研究结果表明，所有模型的AUROC值均>0.7，其中三个模型超过0.75。值得注意的是，纳入术前48小时最大值和术后24小时最大值的逻辑回归模型表现出最高的预测准确性（AUROC = 0.755，95%置信区间：0.7185 - 0.7912），优于其他配置。该模型的优势在于其整合了术前和术后的动态变量，既捕捉了基线风险，又捕捉了术后急性变化。通过系统地比较多种机器学习方法，我们的研究强调了结合时间生理指标以增强AKI风险分层的效用。这些结果为早期AKI预测提供了一个强大的、临床适用的工具，能够进行积极干预以改善心脏手术患者的预后。
