JMIR Publications

ABSTRACT

Background:

Acute kidney injury (AKI) frequently occurs in critically ill patients with coronary heart disease (CHD), and its development markedly elevates mortality rates and prolongs hospitalization duration. Early AKI prediction is crucial for timely intervention and amelioration of patient outcomes.

Objective:

This study aims to develop and verify a clinical prediction model for the occurrence of AKI upon admission in the critically ill CHD population through machine learning (ML).

Methods:

Data from the MIMIC-IV (version 2.2) database were gathered and included information on critically ill CHD individuals in the intensive care unit (ICU). The dataset was randomized into a training set (70%) and a test set (30%).LASSO regression was employed for feature variable selection. ML models, including logistic regression (LG), decision trees (DT), naive bayes (NB), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM), were constructed using the training set. The six models were compared in the test set to identify the best-performing model. Subsequently, the model was assessed by Calibration curve and decision curve analysis. External validation was conducted using data from the Second Affiliated Hospital of Zhengzhou University.Ultimately, the predictive model was interpreted via SHapley Additive Explanations (SHAP) values.

Results:

2,810 ICU-admitted CHD patients were selected, with 1,866 (66.4%) having AKI. Nineteen variables were selected to construct the six ML models. XGBoost exhibited the best performance regarding discrimination (AUC = 0.767), accuracy (0.723), and sensitivity (0.758). External validation using a cohort of 180 patients confirmed the strong generalizability of the XGBoost model (AUC = 0.808).SHAP analysis identified five key features promoting AKI development: mechanical ventilation, use of antiplatelet drugs, history of old myocardial infarction, NT-proBNP levels, and APSIII score.

Conclusions:

ML models can serve as reliable tools for forecasting AKI in the critically ill CHD cohort. The XGBoost model is highly accurate and may aid doctors in identifying high-risk individuals for early intervention to lower mortality.