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
Würstle S, Hapfelmeier A, Karapetyan S, Studen F, Isaakidou A, Schneider T, Schmid R, von Delius S, Gundling F, Triebelhorn J, Burgkart R, Obermeier A, Mayr U, Heller S, Rasch S, Lahmer T, Geisler F, Chan B, Turner P, Rothe K, Spinner C, Schneider J. 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. Antibiotics 2022, 11: 1610. PMID: 36421254, PMCID: PMC9686825, DOI: 10.3390/antibiotics11111610.Peer-Reviewed Original ResearchDecompensated liver cirrhosisInfected ascitesLiver cirrhosisPredictive valueHigh negative predictive valueRetrospective multicentre studySimilar predictive valuePre-test probabilityEpisodes of patientsFurther external validationNegative predictive valuePositive predictive valuePromising non-invasive approachLaboratory featuresMulticentre studyProspective studyAscitesCirrhosisPatientsNon-invasive approachClinical routineLASSO regression modelExternal validationAbdominocentesisRegression models