An XGBoost machine learning model outperformed other models in predicting 30-day hospital readmission in patients with chronic kidney disease, achieving an accuracy of >90%.
Cohort (n=277)
No
Do machine learning models accurately predict 30-day hospital readmission in hospitalized patients with chronic kidney disease?
Machine learning models, particularly XGBoost, can predict 30-day hospital readmission in CKD patients with high accuracy (>90%) using clinical and laboratory features.
Effect estimate: Accuracy >90%
INTRODUCTION: Chronic Kidney Disease (CKD) is associated with high 30-day hospital readmission rates due to progressive renal dysfunction, multiple comorbidities, and complications related to dialysis and catheter use. Artificial Intelligence (AI) and Machine Learning (ML) offer promising tools for early identification of high-risk patients. To develop and evaluate ML models for predicting 30-day hospital readmission among CKD patients and identify key clinical and laboratory predictors related to readmission risk. METHODS: This retrospective study analyzed 277 hospitalized patients with CKD at Hasheminejad Kidney Center (2019-2022). Forty-four demographic, clinical, and laboratory features were included. Preprocessing included handling missing data, normalization, outlier removal, categorical encoding, and oversampling. Six ML models, including eXtreme Gradient Boosting (XGBoost), Random Forest, Decision Tree, AdaBoost, Multilayer Perceptron (MLP), and Logistic Regression, were trained using a 70/30 train-test split with cross-validation. Feature selection employed SHAP values, mutual information, F-values, SVM, and chi-squared tests. RESULTS: XGBoost outperformed other models (accuracy > 90%). The strongest predictors were estimated Glomerular Filtration Rate (eGFR), Blood Urea Nitrogen (BUN) and creatinine levels, age, presence of diabetes mellitus and hypertension, catheter-related infection, and triglycerides, intact Parathyroid hormone (iPTH), and albumin levels. Catheter infection emerged as a modifiable, high-impact predictor. The SHAP values analysis confirmed strong contributions of kidney function markers, inflammatory indicators, and metabolic variables to re-admission risk. CONCLUSION: ML-based prediction models, particularly XGBoost, demonstrated high accuracy in identifying CKD patients at risk of 30-day readmission. Integration of these models into clinical workflows may improve early intervention, reduce hospital readmissions, and support evidence-based nephrology care.
Sanadgol et al. (Sun,) conducted a cohort in Chronic Kidney Disease (n=277). Machine Learning models (XGBoost) vs. Other ML models was evaluated on 30-day hospital readmission (Accuracy >90%). An XGBoost machine learning model outperformed other models in predicting 30-day hospital readmission in patients with chronic kidney disease, achieving an accuracy of >90%.