Explainable machine learning model based prediction of in-hospital acute kidney injury risk in acute aortic dissection patients
Zhao Pengying
Luo Ziran
Shao Xinqua
Jin Sai
Wei zhili
Chen Yang
Li Xuhua
Song Bing
Abstract：Objective This study aims to identify the risk factors for in-hospital acute kidney injury(AKI)in patients with acute aortic dissection(AAD)and to establish a machine learning model for predicting in-hospital AKI.Methods We extracted data on patients with AAD from the MIMIC-IV database and developed five machine learning models:Support Vector Machine(SVM),Gradient Boosting Machine(GBM),Neural Network(NNET),eXtreme Gradient Boosting(XGBoost),and K-Nearest Neighbors(KNN).Model performance was assessed using the area under the receiver operating characteristic curve(AUC),and the optimal model was interpreted using SHAP visualization analysis.Results A total of 351 patients with AAD were identified from the MIMIC-Ⅳdatabase,of which 91 patients(25.93%)developed in-hospital AKI.This study collected 41 features,with 9 selected for model building.Seventy percentage of the patients were randomly allocated to the training set,while the remaining 30%were allocated to the test set.Machine learning models were built on the training set and validated using the test set.Among the five machine learning models,the XGBoost model performed the best,with an AUC of 0.854 in the training set and 0.718 in the test set.SHAP visualization analysis identified the most important risk factors for in-hospital AKI in AAD patients as:Urine output,glucose max,BMI,APSⅢ score,blood urea nitrogen max,Maximum creatinine,weight,blood urea nitrogen min,Minimum creatinine.Conclusion The developed XGBoost model effectively predicts the risk of in-hospital AKI in AAD patients.
Keywords：Acute aortic dissectionAcute kidney injuryMachine learningPrediction model
Publication Date：2025-08-20
Online Publishing Date：2025-10-24(First online date of this platform, not the publication date of the document)
Pages：8( 915-922 )