Predicting severe renal dysfunction in alcohol-associated cirrhosis: Comparative performance of liver function scores and machine learning models
PLOS One · 17.09.2025 · 20 (9) · e0332840
DOI: 10.1371/journal.pone.0332840 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 17.09.2025. Verfasst von Julian Müller-Kühnle und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Internal Medicine and Nephrology, Robert Bosch Hospital, Stuttgart, Germany. Hauptthemen laut MEDLINE: Machine Learning, Liver Cirrhosis, Alcoholic, Renal Insufficiency, Chronic. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Eva Mayr-Stihl Stiftung.
Abstract (Originalsprache)
Background
Renal dysfunction is a frequent and clinically relevant complication of cirrhosis, yet chronic kidney disease (CKD) often remains underrecognized, particularly in non-acute settings. Early identification of at-risk patients is essential to guide timely interventions. Although MELD, Child-Pugh Score (CPS), APRI, and FIB-4 are widely used to assess hepatic disease severity, their predictive value for advanced renal dysfunction is uncertain.
Methods
In this retrospective cohort study (2014–2021, Klinikum Stuttgart), we evaluated the ability of MELD, CPS, APRI, and FIB-4 to predict severe renal dysfunction (chronic kidney disease [CKD] stage ≥ 3, according to Kidney Disease: Improving Global Outcomes [KDIGO] classification) in patients with alcoholic cirrhosis. Logistic and linear regression analyses were performed. In addition, machine learning (ML) models were trained to identify non-renal predictors of CKD stage ≥ 3.
Results
Among 131 patients (mean age 62.8 ± 11.3 years; 71% male), 33% met criteria for KDIGO stage ≥ 3. MELD was significantly associated with advanced CKD (OR = 1.379, p < 0.001), with prevalence increasing from 17% (MELD ≤ 9) to 80% (MELD ≥ 20). CPS showed an inverse association (p = 0.002), while APRI and FIB-4 were not predictive. The optimized Random Forest model, refined through ROSE oversampling and feature selection, achieved an AUC of 0.757, with 76% accuracy, 82% sensitivity (KDIGO < 3), and 63% specificity (KDIGO ≥ 3).
Conclusion
MELD was the most reliable conventional score for identifying advanced renal dysfunction in alcoholic cirrhosis. ML-based models incorporating routinely available clinical parameters further improved predictive performance and may support risk stratification in this high-risk population.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of General Internal Medicine and Nephrology, Robert Bosch Hospital, Stuttgart, Germany.
- Robert Bosch Society for Medical Research, Stuttgart, Germany.
- Paracelsus Medical University, Salzburg, Austria.
- Department of General, Visceral, Thoracic, and Pediatric Surgery, Ludwigsburg Hospital, Ludwigsburg, Germany.
- Department of Hematology, Oncology, Stem Cell Transplantation, and Palliative Medicine, Klinikum Stuttgart, Stuttgart, Germany.
- Department of General Internal Medicine, Gastroenterology, Gastrointestinal Oncology, Hepatology, Infectious Diseases, and Pulmonology, Klinikum Stuttgart, Stuttgart, Germany.
ORCID-Profile: Julian Müller-Kühnle
Förderung
- Eva Mayr-Stihl Stiftung
Zitieren
APA
Müller-Kühnle, J., Schanz, M., Schricker, S., Benignus, C., Todoroff, J., Latus, J., Zoller, W., & Marschner, D. (2025). Predicting severe renal dysfunction in alcohol-associated cirrhosis: Comparative performance of liver function scores and machine learning models. PLOS One, 20(9), e0332840. https://doi.org/10.1371/journal.pone.0332840
Vancouver
Müller-Kühnle J, Schanz M, Schricker S, Benignus C, Todoroff J, Latus J, et al. Predicting severe renal dysfunction in alcohol-associated cirrhosis: Comparative performance of liver function scores and machine learning models. PLOS One. 2025;20(9):e0332840. doi:10.1371/journal.pone.0332840
BibTeX
@article{MllerKhnle2025,
author = {Müller-Kühnle, Julian and Schanz, Moritz and Schricker, Severin and Benignus, Christian and Todoroff, Julia and Latus, Jörg and Zoller, Wolfram and Marschner, Dominik},
title = {Predicting severe renal dysfunction in alcohol-associated cirrhosis: Comparative performance of liver function scores and machine learning models},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {9},
pages = {e0332840},
doi = {10.1371/journal.pone.0332840}
}
EUVIMED