Interpretable machine learning model for early prediction of acute kidney injury in patients with rhabdomyolysis  

作　　者：Ximu Zhang Xiuting Liang Zhangning Fu Yibo Zhou Yao Fang Xiaoli Liu Qian Yuan Rui Liu Quan Hong Chao Liu 

机构地区：[1]Department of Critical Care Medicine,Hainan Hospital of Chinese PLA General Hospital,Sanya,Hainan,China [2]Department of Nursing,The First Medical Center of Chinese People’s Liberation Army General Hospital,Beijing,China [3]Chinese PLA Institute of Nephrology,State Key Laboratory of Kidney Diseases,National Clinical Research Center for Kidney Diseases,Beijing,China [4]Department of Critical Care Medicine,The First Medical Center of Chinese People’s Liberation Army General Hospital,Beijing,China [5]Department of Respiratory and Critical Care Medicine,General Hospital of Center Theater of PLA,Wuhan,Hubei,China [6]Center for Artificial Intelligence in Medicine,The Chinese PLA General Hospital,Beijing,China [7]School of Biological Science and Medical Engineering,Beihang University,Beijing,China [8]Honor Device Co.,Ltd.,Beijing,China [9]Department of Critical Care Medicine,Tangdu Hospital,Air Force Military Medical University,Xi’an,Shaanxi,China

出　　处：《Emergency and Critical Care Medicine》2024年第4期155-162,共8页急危重症医学(英文)

基　　金：This study was supported by National Natural Science Foundation of China(82200780);China Postdoctoral Science Foundation(2022 M723899).

摘　　要：Background:Rhabdomyolysis(RM)is a complex set of clinical syndromes.RM-induced acute kidney injury(AKI)is a common illness in war and military operations.This study aimed to develop an interpretable and generalizable model for early AKI prediction in patients with RM.Methods:Retrospective analyses were performed on 2 electronic medical record databases:the eICU Collaborative Research Data-base and the Medical Information Mart for Intensive Care III database.Data were extracted from the first 24 hours after patient admission.Data from the two datasets were merged for further analysis.The extreme gradient boosting(XGBoost)model with the Shapley additive explanation method(SHAP)was used to conduct early and interpretable predictions of AKI.Results:The analysis included 938 eligible patients with RM.The XGBoost model exhibited superior performance(area under the re-ceiver operating characteristic curve[AUC]=0.767)compared to the other models(logistic regression,AUC=0.711;support vector ma-chine,AUC=0.693;random forest,AUC=0.728;and naive Bayesian,AUC=0.700).Conclusion:Although the XGBoost model performance could be improved from an absolute perspective,it provides better predictive performance than other models for estimating the AKI in patients with RM based on patient characteristics in the first 24 hours after ad-mission to an intensive care unit.Furthermore,including SHAP to elucidate AKI-related factors enables individualized patient treatment,potentially leading to improved prognoses for patients with RM.

关 键 词：Acute kidney injury eICU-CRD MIMIC-III RHABDOMYOLYSIS XGBoost 

分 类 号：R69[医药卫生—泌尿科学]