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
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 d...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Antibiotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6382/11/11/1610 |
| _version_ | 1827645128375795712 |
|---|---|
| author | Silvia Würstle Alexander Hapfelmeier Siranush Karapetyan Fabian Studen Andriana Isaakidou Tillman Schneider Roland M. Schmid Stefan von Delius Felix Gundling Julian Triebelhorn Rainer Burgkart Andreas Obermeier Ulrich Mayr Stephan Heller Sebastian Rasch Tobias Lahmer Fabian Geisler Benjamin Chan Paul E. Turner Kathrin Rothe Christoph D. Spinner Jochen Schneider |
| author_facet | Silvia Würstle Alexander Hapfelmeier Siranush Karapetyan Fabian Studen Andriana Isaakidou Tillman Schneider Roland M. Schmid Stefan von Delius Felix Gundling Julian Triebelhorn Rainer Burgkart Andreas Obermeier Ulrich Mayr Stephan Heller Sebastian Rasch Tobias Lahmer Fabian Geisler Benjamin Chan Paul E. Turner Kathrin Rothe Christoph D. Spinner Jochen Schneider |
| author_sort | Silvia Würstle |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T18:31:04Z |
| format | Article |
| id | doaj.art-3d88ba136aed42e1a07b4aafa6087976 |
| institution | Directory Open Access Journal |
| issn | 2079-6382 |
| language | English |
| last_indexed | 2024-03-09T18:31:04Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Antibiotics |
| spelling | doaj.art-3d88ba136aed42e1a07b4aafa60879762023-11-24T07:30:36ZengMDPI AGAntibiotics2079-63822022-11-011111161010.3390/antibiotics11111610A 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 StudySilvia Würstle0Alexander Hapfelmeier1Siranush Karapetyan2Fabian Studen3Andriana Isaakidou4Tillman Schneider5Roland M. Schmid6Stefan von Delius7Felix Gundling8Julian Triebelhorn9Rainer Burgkart10Andreas Obermeier11Ulrich Mayr12Stephan Heller13Sebastian Rasch14Tobias Lahmer15Fabian Geisler16Benjamin Chan17Paul E. Turner18Kathrin Rothe19Christoph D. Spinner20Jochen Schneider21Department of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyInstitute of General Practice and Health Services Research, School of Medicine, Technical University of Munich, 81667 Munich, GermanyInstitute of AI and Informatics in Medicine, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, RoMed Hospital Rosenheim, 83022 Rosenheim, GermanyDepartment of Gastroenterology, Hepatology, and Gastrointestinal Oncology, Bogenhausen Hospital of the Munich Municipal Hospital Group, 81925 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyClinic of Orthopaedics and Sports Orthopaedics, School of Medicine, Technical University of Munich, 81675 Munich, GermanyClinic of Orthopaedics and Sports Orthopaedics, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyClinic of Orthopaedics and Sports Orthopaedics, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Ecology and Evolutionary Biology, Yale University, New Haven, CT 06520, USADepartment of Ecology and Evolutionary Biology, Yale University, New Haven, CT 06520, USAInstitute for Medical Microbiology, Immunology and Hygiene, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyDepartment of Internal Medicine II, University Hospital rechts der Isar, School of Medicine, Technical University of Munich, 81675 Munich, GermanyThis 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.https://www.mdpi.com/2079-6382/11/11/1610ascitesliver cirrhosisproton pump inhibitorspontaneous bacterial peritonitissecondary peritonitis |
| spellingShingle | Silvia Würstle Alexander Hapfelmeier Siranush Karapetyan Fabian Studen Andriana Isaakidou Tillman Schneider Roland M. Schmid Stefan von Delius Felix Gundling Julian Triebelhorn Rainer Burgkart Andreas Obermeier Ulrich Mayr Stephan Heller Sebastian Rasch Tobias Lahmer Fabian Geisler Benjamin Chan Paul E. Turner Kathrin Rothe Christoph D. Spinner Jochen Schneider 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 ascites liver cirrhosis proton pump inhibitor spontaneous bacterial peritonitis secondary peritonitis |
| title | 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 |
| title_full | 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 |
| title_fullStr | 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 |
| title_full_unstemmed | 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 |
| title_short | 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 |
| title_sort | 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 |
| topic | ascites liver cirrhosis proton pump inhibitor spontaneous bacterial peritonitis secondary peritonitis |
| url | https://www.mdpi.com/2079-6382/11/11/1610 |
| work_keys_str_mv | AT silviawurstle anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT alexanderhapfelmeier anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT siranushkarapetyan anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT fabianstuden anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT andrianaisaakidou anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT tillmanschneider anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT rolandmschmid anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT stefanvondelius anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT felixgundling anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT juliantriebelhorn anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT rainerburgkart anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT andreasobermeier anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT ulrichmayr anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT stephanheller anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT sebastianrasch anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT tobiaslahmer anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT fabiangeisler anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT benjaminchan anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT pauleturner anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT kathrinrothe anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT christophdspinner anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT jochenschneider anovelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT silviawurstle novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT alexanderhapfelmeier novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT siranushkarapetyan novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT fabianstuden novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT andrianaisaakidou novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT tillmanschneider novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT rolandmschmid novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT stefanvondelius novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT felixgundling novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT juliantriebelhorn novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT rainerburgkart novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT andreasobermeier novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT ulrichmayr novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT stephanheller novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT sebastianrasch novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT tobiaslahmer novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT fabiangeisler novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT benjaminchan novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT pauleturner novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT kathrinrothe novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT christophdspinner novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy AT jochenschneider novelmachinelearningbasedpointscoremodelasanoninvasivedecisionmakingtoolforidentifyinginfectedascitesinpatientswithhydropicdecompensatedlivercirrhosisaretrospectivemulticentrestudy |