Interpretable Machine Learning Model for Early Prediction of Acute Kidney Injury in Critically Ill Patients with Cirrhosis: A Retrospective Study
Preprint
Abstract
Background: Cirrhosis is a progressive liver disease with high mortality and frequent complications, notably acute kidney injury (AKI), which occurs in up to 50% of hospitalized patients and worsens outcomes. AKI stems from complex hemodynamic, inflammatory, and metabolic changes, making early detection essential. Many predictive tools lack accuracy, interpretability, and alignment with intensive care unit (ICU) workflows. This study developed an interpretable machine learning model for early AKI prediction in critically ill patients with cirrhosis. Methods: We conducted a retrospective analysis of the MIMIC-IV v2.2 database, identifying 1240 adult ICU patients with cirrhosis and excluding those with ICU stays under 48 hours or missing key data. Laboratory and physiological variables from the first 48 hours were extracted. The pipeline included preprocessing, missingness filtering, LASSO feature selection, and SMOTE class balancing. Six algorithms-LightGBM, CatBoost, XGBoost, logistic regression, naive Bayes, and neural networks-were trained and evaluated using AUROC, accuracy, F1-score, sensitivity, specificity, and predictive values. Results: LightGBM achieved the best performance (AUROC 0.808, 95% CI 0.741-0.856; accuracy 0.704; NPV 0.911). Key predictors included prolonged partial thromboplastin time, absence of outside-facility 20G placement, low pH, and altered pO2, consistent with known cirrhosis-AKI mechanisms and suggesting actionable targets. Conclusion: The LightGBM-based model enables accurate early AKI risk stratification in ICU patients with cirrhosis using routine clinical variables. Its high negative predictive value supports safe de-escalation for low-risk patients, and interpretability fosters clinician trust and targeted prevention. External validation and integration into electronic health record systems are warranted.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Explainable SHAP-XGBoost models for pressure injuries among patients requiring with mechanical ventilation in intensive care unitScientific Reports, 2025
- Acute kidney injury in patients with cirrhosis: Acute Disease Quality Initiative (ADQI) and International Club of Ascites (ICA) joint multidisciplinary consensus meetingJournal of Hepatology, 2024
- Association between glycemic variability and short-term mortality in patients with acute kidney injury: a retrospective cohort study of the MIMIC-IV databaseScientific Reports, 2024
- Prediction of acute kidney injury in patients with liver cirrhosis using machine learning models: evidence from the MIMIC-III and MIMIC-IVInternational Urology and Nephrology, 2023
- Epidemiology, predictors and outcomes of multi drug resistant (MDR) bacterial infections in patients with cirrhosis across the world. Final results of the “Global study”Digestive and Liver Disease, 2018
- Acute Kidney Injury in Cirrhosis: Baseline Serum Creatinine Predicts Patient OutcomesAmerican Journal of Gastroenterology, 2017
- Acute kidney injury after liver transplantation: Recent insights and future perspectivesBest Practice & Research Clinical Gastroenterology, 2017
- Management of acute kidney injury in cirrhosisHepatology International, 2013
- Acute-on-Chronic Liver Failure Is a Distinct Syndrome That Develops in Patients With Acute Decompensation of CirrhosisGastroenterology, 2013
- Association of AKI With Mortality and Complications in Hospitalized Patients With CirrhosisHepatology, 2012