Feedback

A Novel Machine Learning-Based Point-Score Model as a Non-Invasive Decision-Making Tool for Identifying Infected Ascites in Patients with Hydropic Decompensated Liver Cirrhosis: A Retrospective Multicentre Study

ORCID
0000-0003-0787-3894
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Würstle, Silvia;
ORCID
0000-0001-6765-6352
Affiliation
Institute of General Practice and Health Services Research, School of Medicine, Technical University of Munich, 81667 Munich, Germany
Hapfelmeier, Alexander;
Affiliation
Institute of AI and Informatics in Medicine, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Karapetyan, Siranush;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Studen, Fabian;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Isaakidou, Andriana;
ORCID
0000-0002-5431-2507
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Schneider, Tillman;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Schmid, Roland M.;
Affiliation
Department of Internal Medicine II, RoMed Hospital Rosenheim, 83022 Rosenheim, Germany
von Delius, Stefan;
Affiliation
Department of Gastroenterology, Hepatology, and Gastrointestinal Oncology, Bogenhausen Hospital of the Munich Municipal Hospital Group, 81925 Munich, Germany
Gundling, Felix;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Triebelhorn, Julian;
Affiliation
Clinic of Orthopaedics and Sports Orthopaedics, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Burgkart, Rainer;
ORCID
0000-0002-1774-5194
Affiliation
Clinic of Orthopaedics and Sports Orthopaedics, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Obermeier, Andreas;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Mayr, Ulrich;
Affiliation
Clinic of Orthopaedics and Sports Orthopaedics, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Heller, Stephan;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Rasch, Sebastian;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Lahmer, Tobias;
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Geisler, Fabian;
Affiliation
Department of Ecology and Evolutionary Biology, Yale University, New Haven, CT 06520, USA
Chan, Benjamin;
Affiliation
Department of Ecology and Evolutionary Biology, Yale University, New Haven, CT 06520, USA
Turner, Paul E.;
Affiliation
Institute for Medical Microbiology, Immunology and Hygiene, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Rothe, Kathrin;
ORCID
0000-0002-3875-5367
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Spinner, Christoph D.;
ORCID
0000-0002-0300-0159
Affiliation
Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, Germany
Schneider, Jochen

This study is aimed at assessing the distinctive features of patients with infected ascites and liver cirrhosis and developing a scoring system to allow for the accurate identification of patients not requiring abdominocentesis to rule out infected ascites. A total of 700 episodes of patients with decompensated liver cirrhosis undergoing abdominocentesis between 2006 and 2020 were included. Overall, 34 clinical, drug, and laboratory features were evaluated using machine learning to identify key differentiation criteria and integrate them into a point-score model. In total, 11 discriminatory features were selected using a Lasso regression model to establish a point-score model. Considering pre-test probabilities for infected ascites of 10%, 15%, and 25%, the negative and positive predictive values of the point-score model for infected ascites were 98.1%, 97.0%, 94.6% and 14.9%, 21.8%, and 34.5%, respectively. Besides the main model, a simplified model was generated, containing only features that are fast to collect, which revealed similar predictive values. Our point-score model appears to be a promising non-invasive approach to rule out infected ascites in clinical routine with high negative predictive values in patients with hydropic decompensated liver cirrhosis, but further external validation in a prospective study is needed.

Cite

Citation style:
Could not load citation form.

Access Statistic

Total:
Downloads:
Abtractviews:
Last 12 Month:
Downloads:
Abtractviews:

Rights

License Holder: © 2022 by the authors.

Use and reproduction: