Machine learning approach for the prediction of 30-day mortality in patients with sepsis-associated encephalopathy.
Machine learning
Model interpretation
SAE
Sepsis-associated encephalopathy
Web-based calculator
Journal
BMC medical research methodology
ISSN: 1471-2288
Titre abrégé: BMC Med Res Methodol
Pays: England
ID NLM: 100968545
Informations de publication
Date de publication:
04 07 2022
04 07 2022
Historique:
received:
08
02
2022
accepted:
23
06
2022
entrez:
5
7
2022
pubmed:
6
7
2022
medline:
7
7
2022
Statut:
epublish
Résumé
Our study aimed to identify predictors as well as develop machine learning (ML) models to predict the risk of 30-day mortality in patients with sepsis-associated encephalopathy (SAE). ML models were developed and validated based on a public database named Medical Information Mart for Intensive Care (MIMIC)-IV. Models were compared by the area under the curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive values, and Hosmer-Lemeshow good of fit test. Of 6994 patients in MIMIC-IV included in the final cohort, a total of 1232 (17.62%) patients died following SAE. Recursive feature elimination (RFE) selected 15 variables, including acute physiology score III (APSIII), Glasgow coma score (GCS), sepsis related organ failure assessment (SOFA), Charlson comorbidity index (CCI), red blood cell volume distribution width (RDW), blood urea nitrogen (BUN), age, respiratory rate, PaO The ML models, as demonstrated by our study, can be used to evaluate the prognosis of SAE patients in the intensive care unit (ICU). Online calculator could facilitate the sharing of predictive models.
Identifiants
pubmed: 35787248
doi: 10.1186/s12874-022-01664-z
pii: 10.1186/s12874-022-01664-z
pmc: PMC9252033
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
183Informations de copyright
© 2022. The Author(s).
Références
Intensive Care Med. 2017 Aug;43(8):1075-1084
pubmed: 28466149
BMJ. 2015 Jan 07;350:g7594
pubmed: 25569120
BMC Pregnancy Childbirth. 2018 Aug 15;18(1):333
pubmed: 30111303
Front Microbiol. 2021 Aug 19;12:737066
pubmed: 34489922
Shock. 2018 Feb;49(2):120-125
pubmed: 28767543
Br J Haematol. 2009 Apr;145(1):24-33
pubmed: 19222477
Arch Pathol Lab Med. 2009 Apr;133(4):628-32
pubmed: 19391664
N Engl J Med. 2013 Oct 31;369(18):1726-34
pubmed: 24171518
Clin Hemorheol Microcirc. 2015;59(4):379-85
pubmed: 25159489
J Clin Neurophysiol. 1992 Jan;9(1):145-52
pubmed: 1552002
Chest. 2016 Jan;149(1):252-61
pubmed: 26378980
Crit Care Med. 1990 Aug;18(8):801-6
pubmed: 2379391
Crit Care Med. 1986 Aug;14(8):754-5
pubmed: 3087704
JAMA. 2010 Oct 27;304(16):1787-94
pubmed: 20978258
Arch Intern Med. 2009 Mar 23;169(6):588-94
pubmed: 19307522
Clin Invest Med. 1990 Dec;13(6):297-304
pubmed: 2078909
Circulation. 2000 Jun 13;101(23):E215-20
pubmed: 10851218
Crit Care Med. 2013 Jan;41(1):263-306
pubmed: 23269131
Chin Med J (Engl). 2012 Mar;125(5):828-31
pubmed: 22490582
JAMA. 2016 Feb 23;315(8):801-10
pubmed: 26903338
J Intensive Care. 2020 Jul 02;8:45
pubmed: 32637121
J Intern Med. 2015 Mar;277(3):277-293
pubmed: 25418337
J Am Soc Nephrol. 2019 Jul;30(7):1151-1161
pubmed: 31076465
BMC Emerg Med. 2020 Oct 6;20(1):77
pubmed: 33023479
BMJ. 2015 Jun 03;350:h2538
pubmed: 26041151
J Clin Med. 2020 Mar 05;9(3):
pubmed: 32150970
JAMA. 2004 Apr 14;291(14):1753-62
pubmed: 15082703
N Engl J Med. 2014 Jan 9;370(2):184
pubmed: 24401070
Blood. 2016 Jun 16;127(24):3062-72
pubmed: 26956172
JAMA. 1996 Feb 14;275(6):470-3
pubmed: 8627969
Cell. 2020 Apr 2;181(1):92-101
pubmed: 32243801
Scand J Trauma Resusc Emerg Med. 2019 Apr 30;27(1):51
pubmed: 31039813
JAMA. 1993 Dec 22-29;270(24):2957-63
pubmed: 8254858
Crit Care Med. 2006 Jan;34(1):15-21
pubmed: 16374151
Lancet Neurol. 2014 Jun;13(6):630-6
pubmed: 24849863
Nat Rev Neurol. 2012 Oct;8(10):557-66
pubmed: 22986430