EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Predicting severe renal dysfunction in alcohol-associated cirrhosis: Comparative performance of liver function scores and machine learning models

Julian Müller-Kühnle iD, Moritz Schanz, Severin Schricker, Christian Benignus, Julia Todoroff, Jörg Latus, Wolfram Zoller, Dominik Marschner

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Machine LearningLiver Cirrhosis, AlcoholicRenal Insufficiency, ChronicHumansMaleMiddle AgedFemaleRetrospective StudiesAgedSeverity of Illness IndexLiver Function Tests

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}
}
Kostenlos starten →