基于机器学习构建心肺复苏后急性肾损伤早期预测模型  

Construction of an early prediction model for post cardiopulmonary resuscitation-acute kidney injury based on machine learning

作　　者：王晋祥[1] 华罗刚 李大明 郭红宝 靳衡[1] 续国武[1] Wang Jinxiang;Hua Luogang;Li Daming;Guo Hongbao;Jin Heng;Xu Guowu(Department of Emergency,Tianjin Medical University General Hospital,Tianjin 300052,China;Department of Nephrology,Tianjin Medical University General Hospital,Tianjin 300052,China)

机构地区：[1]天津医科大学总医院急诊科,天津300052 [2]天津医科大学总医院肾内科,天津300052

出　　处：《中华肾脏病杂志》2024年第11期875-881,共7页Chinese Journal of Nephrology

基　　金：国家自然科学基金(82072222);天津市教委科研计划项目(2021KJ211)。

摘　　要：目的基于机器学习构建心肺复苏后急性肾损伤(post cardiopulmonary resuscitation-acute kidney injury,PCPR-AKI)早期预测模型,为早期识别急性肾损伤(acute kidney injury,AKI)高危患者及精准治疗提供依据。方法该研究为单中心、回顾性研究。收集2016年1月1日至2023年10月31日天津医科大学总医院收治的心脏停搏心肺复苏后住院患者的临床资料。研究终点事件定义为心肺复苏后48 h内患者发生AKI。依据AKI诊断标准将患者分为AKI组和非AKI组,比较两组基线临床资料的差异。将符合纳入标准的患者以7∶3的比例随机(采用train_test_split函数,设置随机种子为1、2、3)分为训练集和验证集。运用随机森林(random forest,RF)、支持向量机、决策树、极端梯度提升及轻量梯度提升机5种机器学习算法构建PCPR-AKI早期预测模型。采用受试者工作特征曲线和决策曲线分析分别评估各模型的预测效能和临床实用性,同时筛选最优模型的重要性变量并进行排序。结果该研究纳入547例患者,年龄66(59,70)岁,男性282例(51.6%),心肺复苏后48 h内发生AKI 238例(43.5%),其中AKI 1期182例(76.5%),AKI 2期47例(19.7%),AKI 3期9例(3.8%)。AKI组与非AKI组患者间年龄、达到自主循环恢复时间、心脏停搏至开始心肺复苏时间、初始可除颤心律比例、电除颤比例、机械通气比例、肾上腺素用量、碳酸氢钠用量、冠心病比例、高血压比例、糖尿病比例、血清肌酐、血尿素氮、血乳酸、血钾、脑钠肽、肌钙蛋白、D-二聚体、神经元特异性烯醇化酶及心肺复苏后24 h尿量的差异均有统计学意义(均P<0.05)。在5种机器学习算法模型中,RF模型曲线下面积(AUC)为0.875,敏感度为0.863,特异度为0.956,准确率为90.7%,在预测效能和临床实用性上均优于其他4种模型。在RF模型变量重要性排序中,排在前10位的变量依次是达到自主循环恢复时间、心脏停搏至开始心肺复Objective To construct an early prediction model for post cardiopulmonary resuscitation-acute kidney injury (PCPR⁃AKI) by machine learning and provide a basis for early identification of acute kidney injury (AKI) high⁃risk patients and accurate treatment. Methods It was a single-center retrospective study. The clinical data of patients admitted to Tianjin Medical University General Hospital after cardiopulmonary resuscitation following cardiac arrest from January 1, 2016 to October 31, 2023 were collected. The end-point event of the study was defined as AKI occurring within 48 hours after cardiopulmonary resuscitation. The patients were divided into AKI group and non-AKI group according to the AKI diagnostic criteria, and the differences of baseline clinical data between the two groups were compared. The patients who met the inclusion criteria were randomly (using the train_test_split function, set the random seeds to 1, 2, and 3) divided into training and validation sets at a ratio of 7∶3. Random forest (RF), support vector machine, decision tree, extreme gradient boosting and light gradient boosting machine algorithm were used to develop the early prediction model of PCPR⁃AKI. The receiver-operating characteristic curve and decision curve analysis were used to evaluate the performance and clinical practicality of the predictive models, and the importance of variables in the optimal model was screened and ranked. Results A total of 547 patients were enrolled, with age of 66 (59, 70) years old and 282 males (51.6%). There were 238 patients (43.5%) having incidence of AKI within 48 hours after cardiopulmonary resuscitation. In the AKI group, 182 patients (76.5%) were in stage 1, 47 patients (19.7%) were in stage 2, and 9 patients (3.8%) were in stage 3. There were statistically significant differences in the age, time to reach resuscitation of spontaneous circulation, time from cardiac arrest to starting cardiopulmonary resuscitation, proportion of initial defibrillation rhythm, proportion of electric defi

关 键 词：急性肾损伤 心肺复苏术 机器学习 心脏停搏 预测模型 

分 类 号：R459.7[医药卫生—急诊医学] R692.5[医药卫生—治疗学]