<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>1890</id>
    <completedYear>2021</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>15</pageLast>
    <pageNumber/>
    <edition/>
    <issue>Online/2021</issue>
    <volume>2021</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2021-07-05</completedDate>
    <publishedDate>2021-05-20</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">COVID-19 and the kidney: A retrospective analysis of 37 critically ill patients using machine learning</title>
    <abstract language="eng">Introduction&#13;
There is evidence that SARS-CoV2 has a particular affinity for kidney tissue and is often&#13;
associated with kidney failure.&#13;
Methods&#13;
We assessed whether proteinuria can be predictive of kidney failure, the development of&#13;
chronic kidney disease, and mortality in 37 critically ill COVID-19 patients. We used machine&#13;
learning (ML) methods as decision trees and cut-off points created by the OneR package to&#13;
add new aspects, even in smaller cohorts.&#13;
Results&#13;
Among a total of 37 patients, 24 suffered higher-grade renal failure, 20 of whom required kidney&#13;
replacement therapy. More than 40% of patients remained on hemodialysis after intensive&#13;
care unit discharge or died (27%). Due to frequent anuria proteinuria measured in two-thirds of&#13;
the patients, it was not predictive for the investigated endpoints; albuminuria was higher in&#13;
patients with AKI 3, but the difference was not significant. ML found cut-off points of &gt;31.4 kg/&#13;
m2 for BMI and &gt;69 years for age, constructed decision trees with great accuracy, and identified&#13;
highly predictive variables for outcome and remaining chronic kidney disease.&#13;
Conclusions&#13;
Different ML methods and their clinical application, especially decision trees, can provide&#13;
valuable support for clinical decisions. Presence of proteinuria was not predictive of CKD or&#13;
AKI and should be confirmed in a larger cohort.</abstract>
    <parentTitle language="eng">Plos one</parentTitle>
    <identifier type="url">https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0251932</identifier>
    <identifier type="doi">https://doi.org/10.1371/journal.pone.0251932</identifier>
    <enrichment key="copyright">1</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - es gilt das deutsche Urheberrecht</licence>
    <author>Anna Laura Herzog</author>
    <editor>Raffaele Serra</editor>
    <author>Holger K. von Jouanne-Diedrich</author>
    <author>Christoph Wanner</author>
    <author>Dirk Weismann</author>
    <author>Tobias Schlesinger</author>
    <author>Patrick Meybohm</author>
    <author>Jan Stumpner</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>COVID-19</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Maschinelles Lernen</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Niereninsuffizienz</value>
    </subject>
    <collection role="forschungsschwerpunkte" number="">Business Transformation and Innovation Management</collection>
    <file>https://opus4.kobv.de/opus4-h-ab/files/1890/journal.pone.0251932.pdf</file>
  </doc>
</export-example>
