COVID-19 and the kidney: A retrospective analysis of 37 critically ill patients using machine learning

There is evidence that SARS-CoV2 has a particular affinity for kidney tissue and is often associated with kidney failure. We assessed whether proteinuria can be predictive of kidney failure, the development of chronic kidney disease, and mortality in 37 critically ill COVID-19 patients. We used mach...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	PloS one Ročník 16; číslo 5; s. e0251932
Hlavní autoři:	Herzog, Anna Laura, von Jouanne-Diedrich, Holger K., Wanner, Christoph, Weismann, Dirk, Schlesinger, Tobias, Meybohm, Patrick, Stumpner, Jan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States Public Library of Science 20.05.2021 Public Library of Science (PLoS)
Témata:	Adult Age Aged Aged, 80 and over Algorithms Anesthesia Anesthesiology Artificial intelligence Biology and Life Sciences Body mass Body Mass Index Body size Calcium-binding protein Classification Complications and side effects Computer and Information Sciences Coronaviruses COVID-19 COVID-19 - complications COVID-19 - mortality Critical Illness - mortality Demographics Demography Editing Electronic mail Engineering and Technology Extracorporeal membrane oxygenation Female Hemodialysis Hospitals Humans Hypertension Intensive care Kidney diseases Kidney failure Kidneys Learning algorithms Lung diseases Machine Learning Male Medical research Medicine and Health Sciences Methodology Middle Aged Mortality Nephrology Oxygenation Pandemics Patients Physical Sciences Prognosis Proteinuria Proteinuria - etiology Proteinuria - mortality Renal Insufficiency, Chronic - etiology Renal Insufficiency, Chronic - mortality Renal Replacement Therapy Research and Analysis Methods Retrospective Studies Risk factors Severe acute respiratory syndrome coronavirus 2 Statistical analysis Supervision Troponin Troponin T Tumor necrosis factor-TNF Variance analysis Ventilation Ventilators Viral diseases Weaning Germany
ISSN:	1932-6203, 1932-6203
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	There is evidence that SARS-CoV2 has a particular affinity for kidney tissue and is often associated with kidney failure. We assessed whether proteinuria can be predictive of kidney failure, the development of chronic kidney disease, and mortality in 37 critically ill COVID-19 patients. We used machine learning (ML) methods as decision trees and cut-off points created by the OneR package to add new aspects, even in smaller cohorts. Among a total of 37 patients, 24 suffered higher-grade renal failure, 20 of whom required kidney replacement therapy. More than 40% of patients remained on hemodialysis after intensive care unit discharge or died (27%). Due to frequent anuria proteinuria measured in two-thirds of the patients, it was not predictive for the investigated endpoints; albuminuria was higher in patients with AKI 3, but the difference was not significant. ML found cut-off points of >31.4 kg/m2 for BMI and >69 years for age, constructed decision trees with great accuracy, and identified highly predictive variables for outcome and remaining chronic kidney disease. Different ML methods and their clinical application, especially decision trees, can provide valuable support for clinical decisions. Presence of proteinuria was not predictive of CKD or AKI and should be confirmed in a larger cohort.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Competing Interests: Christoph Wanner received honoraria for steering committee membership and lecturing outside the present work from AstraZeneca, Bayer, Boehringer-Ingelheim, Eli Lilly, Mundipharma, and MSD. This does not alter our adherence to PLOS ONE policies on sharing data and materials. All other authors have nothing to declare.
ISSN:	1932-6203 1932-6203
DOI:	10.1371/journal.pone.0251932