Machine Learning Models predicting Decompensation in Cirrhosis
Journal of Gastrointestinal and Liver Diseases · 2025
DOI: 10.15403/jgld-5876 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Gastrointestinal and Liver Diseases, 2025. Verfasst von Sophie Elisabeth Müller und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany; Institute of Medical Microbiology and Hygiene, …. Hauptthemen laut MEDLINE: Liver Cirrhosis, Machine Learning, Decision Support Techniques. Die Arbeit wurde bisher 10-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background and Aims: Decompensation of cirrhosis significantly decreases survival, thus, prevention of complications is paramount. We used machine learning techniques to identify parameters predicting decompensation.
Methods
Several machine learning techniques were applied to the INCA trial database containing pro- and retrospective data from 983 patients. Laboratory, clinical, and genetic data were analysed. After performing hierarchical clustering, Permutation Feature Importance was used to evaluate the impact of parameters on the prediction of decompensation.
Results
Achieving an accuracy of 81.6% on training and 70.5% on test data, Random Forests were best for retrospective prediction. In prospective assessment, Support Vector Machines performed best with an accuracy of 78.6% and 73.8%, respectively. Permutation Feature Importance demonstrated that baseline albumin and bilirubin levels and maximum bilirubin were the highest ranked parameters associated with former decompensation. In the prospective analysis, the maximum bilirubin value and the baseline values of sodium and albumin were ranked highest. In addition to the parameters of established scores, NOD2 genotype and inflammatory markers were highly ranked.
Conclusions
Laboratory parameters, genetic variants and infections can help to predict the risk of cirrhosis decompensation. This proof-of-concept study adds data for the future development of advanced models to identify patients at risk.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany; Institute of Medical Microbiology and Hygiene, Center for Infectious Diseases, Saarland University, Homburg, Germany.…
- Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany. m.casper@caritasklinikum.de.
- Department of Internal Medicine IV, University Hospital Jena, Jena, Germany; Clinic for Internal Medicine I, University Hospital Halle, Halle, Germany. Cristina.Ripoll@med.uni-jena.de.
- Department of Internal Medicine IV, University Hospital Jena, Jena, Germany; Clinic for Internal Medicine I, University Hospital Halle, Halle, Germany. zipprich@gmx.de.
- Department of Internal Medicine IV, University Hospital Jena, Jena, Germany; Department of Hepatology and Gastroenterology, Charité - Universitätsmedizin Berlin, Berlin, Germany. paul.horn@charite.de.
- Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany. marcin.krawczyk@uks.eu.
Zitieren
APA
Müller, S. E., Casper, M., Ripoll, C., Zipprich, A., Horn, P., Krawczyk, M., Lammert, F., & Reichert, M. C. (2025). Machine Learning Models predicting Decompensation in Cirrhosis. Journal of Gastrointestinal and Liver Diseases. https://doi.org/10.15403/jgld-5876
Vancouver
Müller SE, Casper M, Ripoll C, Zipprich A, Horn P, Krawczyk M, et al. Machine Learning Models predicting Decompensation in Cirrhosis. Journal of Gastrointestinal and Liver Diseases. 2025. doi:10.15403/jgld-5876
BibTeX
@article{Mller2025,
author = {Müller, Sophie Elisabeth and Casper, Markus and Ripoll, Cristina and Zipprich, Alexander and Horn, Paul and Krawczyk, Marcin and Lammert, Frank and Reichert, Matthias Christian},
title = {Machine Learning Models predicting Decompensation in Cirrhosis},
journal = {Journal of Gastrointestinal and Liver Diseases},
year = {2025},
doi = {10.15403/jgld-5876}
}
EUVIMED