Department of Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR China.
Department of Critical Care Medicine, The First Affiliated Hospital of Guangxi Medical University, Nanning City, PR China.
Ren Fail. 2024 Dec;46(1):2316267. doi: 10.1080/0886022X.2024.2316267. Epub 2024 Feb 18.
This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms.
Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation ( = 2440) and development ( = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP).
A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774-0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis.
The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction.
本研究旨在基于机器学习算法开发和验证用于脓毒症相关急性肾损伤（SA-AKI）危重症患者院内死亡率的预测模型。
在医疗信息集市-重症监护 IV（MIMIC-IV）数据库中确定符合纳入标准的患者，并根据验证队列（n=2440）和开发队列（n=9756，80%）进行划分。采用集成逐步特征选择方法筛选有效特征。通过七种机器学习算法建立短期死亡率预测模型。采用十折交叉验证法验证开发队列中算法的性能。采用受试者工作特征曲线下面积（ROC-AUC）评估验证队列中预测模型的区分准确性和性能。采用 Shapley 加性解释（SHAP）对表现最佳的模型进行解释。
本研究共纳入 12196 例患者。最终选择 11 个变量来开发预测模型。随机森林（RF）模型在十折交叉验证和评估中的 AUC 值最高（AUC：0.798，95%CI：0.774-0.821）。根据 SHAP 图，年龄较大、格拉斯哥昏迷评分（GCS）较低、AKI 分期较高、尿量减少、简化急性生理学评分（SAPS II）较高、呼吸频率较高、体温较低、绝对淋巴细胞计数较低、肌酐水平较高、电解质紊乱和低体重指数（BMI）增加了预后不良的风险。
本研究中开发的 RF 模型是 ICU 中 SA-AKI 患者院内死亡率的良好预测指标，可能具有预测死亡率的应用潜力。
