Validated risk prediction models for outcomes of acute kidney injury: a systematic review.
Acute kidney injury
Chronic kidney disease
Machine learning
Poor renal outcomes
Prediction model
Systematic review
Journal
BMC nephrology
ISSN: 1471-2369
Titre abrégé: BMC Nephrol
Pays: England
ID NLM: 100967793
Informations de publication
Date de publication:
09 05 2023
09 05 2023
Historique:
received:
23
12
2022
accepted:
03
04
2023
medline:
11
5
2023
pubmed:
10
5
2023
entrez:
10
5
2023
Statut:
epublish
Résumé
Acute Kidney Injury (AKI) is frequently seen in hospitalized and critically ill patients. Studies have shown that AKI is a risk factor for the development of acute kidney disease (AKD), chronic kidney disease (CKD), and mortality. A systematic review is performed on validated risk prediction models for developing poor renal outcomes after AKI scenarios. Medline, EMBASE, Cochrane, and Web of Science were searched for articles that developed or validated a prediction model. Moreover, studies that report prediction models for recovery after AKI also have been included. This review was registered with PROSPERO (CRD42022303197). We screened 25,812 potentially relevant abstracts. Among the 149 remaining articles in the first selection, eight met the inclusion criteria. All of the included models developed more than one prediction model with different variables. The models included between 3 and 28 independent variables and c-statistics ranged from 0.55 to 1. Few validated risk prediction models targeting the development of renal insufficiency after experiencing AKI have been developed, most of which are based on simple statistical or machine learning models. While some of these models have been externally validated, none of these models are available in a way that can be used or evaluated in a clinical setting.
Sections du résumé
BACKGROUND
Acute Kidney Injury (AKI) is frequently seen in hospitalized and critically ill patients. Studies have shown that AKI is a risk factor for the development of acute kidney disease (AKD), chronic kidney disease (CKD), and mortality.
METHODS
A systematic review is performed on validated risk prediction models for developing poor renal outcomes after AKI scenarios. Medline, EMBASE, Cochrane, and Web of Science were searched for articles that developed or validated a prediction model. Moreover, studies that report prediction models for recovery after AKI also have been included. This review was registered with PROSPERO (CRD42022303197).
RESULT
We screened 25,812 potentially relevant abstracts. Among the 149 remaining articles in the first selection, eight met the inclusion criteria. All of the included models developed more than one prediction model with different variables. The models included between 3 and 28 independent variables and c-statistics ranged from 0.55 to 1.
CONCLUSION
Few validated risk prediction models targeting the development of renal insufficiency after experiencing AKI have been developed, most of which are based on simple statistical or machine learning models. While some of these models have been externally validated, none of these models are available in a way that can be used or evaluated in a clinical setting.
Identifiants
pubmed: 37161365
doi: 10.1186/s12882-023-03150-0
pii: 10.1186/s12882-023-03150-0
pmc: PMC10170731
doi:
Types de publication
Systematic Review
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
133Informations de copyright
© 2023. The Author(s).
Références
Chest. 2013 Sep;144(3):866-875
pubmed: 23681257
Clin Chem Lab Med. 2012 Feb 15;50(9):1505-17
pubmed: 22962216
Ann Intern Med. 2006 Mar 21;144(6):427-37
pubmed: 16549855
Crit Care. 2008;12(2):R47
pubmed: 18402655
Front Med (Lausanne). 2021 Dec 10;8:792974
pubmed: 34957162
N Engl J Med. 2008 Jul 3;359(1):7-20
pubmed: 18492867
Int Urol Nephrol. 2010 Mar;42(1):141-50
pubmed: 19582588
AMIA Annu Symp Proc. 2012;2012:436-45
pubmed: 23304314
Nat Rev Nephrol. 2018 Oct;14(10):607-625
pubmed: 30135570
Int Urol Nephrol. 2018 Apr;50(4):705-713
pubmed: 29307055
Circulation. 2009 May 12;119(18):2444-53
pubmed: 19398670
Semin Nephrol. 2016 Jul;36(4):283-92
pubmed: 27475659
Kidney Int Rep. 2019 Jan 28;4(4):571-581
pubmed: 30993232
Nat Rev Nephrol. 2017 Apr;13(4):241-257
pubmed: 28239173
Kidney Int. 2019 Apr;95(4):905-913
pubmed: 30819553
Nephrol Dial Transplant. 2016 Feb;31(2):231-40
pubmed: 26705194
Kidney Int. 2016 Nov;90(5):943-949
pubmed: 27317356
Am J Nephrol. 2012;35(4):349-55
pubmed: 22473149
J Clin Monit Comput. 2023 Feb;37(1):113-125
pubmed: 35532860
Clin J Am Soc Nephrol. 2021 Jul;16(7):1005-1014
pubmed: 34021031
Br J Cancer. 2015 Jan 20;112(2):251-9
pubmed: 25562432
Am J Kidney Dis. 2008 Sep;52(3):395-9
pubmed: 18725011
Stud Health Technol Inform. 2015;216:40-4
pubmed: 26262006
Tanaffos. 2016;15(2):89-95
pubmed: 27904540
BMJ. 2009 Jun 29;338:b2393
pubmed: 19564179
J Nephrol. 2022 Nov;35(8):2087-2095
pubmed: 35441981
Methods Inf Med. 1978 Oct;17(4):227-37
pubmed: 366335
Medicina (Kaunas). 2020 Sep 08;56(9):
pubmed: 32911665
Kidney Int. 2007 Aug;72(3):247-59
pubmed: 17568785
Clin J Am Soc Nephrol. 2015 Aug 7;10(8):1332-9
pubmed: 26048891
Nat Rev Nephrol. 2018 Apr;14(4):217-230
pubmed: 29355173
J Clin Med. 2022 Dec 07;11(24):
pubmed: 36555881
Am J Kidney Dis. 2002 Aug;40(2):221-6
pubmed: 12148093
Radiology. 1982 Apr;143(1):29-36
pubmed: 7063747
Kidney Int. 2011 Jun;79(12):1361-9
pubmed: 21430640
Sci Rep. 2021 Mar 15;11(1):5882
pubmed: 33723337
Crit Care Resusc. 2018 Mar;20(1):54-60
pubmed: 29458322
Kidney Int. 2010 Mar;77(6):527-35
pubmed: 20032961
JAMA. 2017 Nov 14;318(18):1787-1797
pubmed: 29136443
Med Care. 2013 Mar;51(3):251-8
pubmed: 23269109
Crit Care Res Pract. 2013;2013:479730
pubmed: 23573420
BMC Health Serv Res. 2014 Sep 04;14:370
pubmed: 25190184
Lancet. 2012 Aug 25;380(9843):756-66
pubmed: 22617274
Clin J Am Soc Nephrol. 2011 Aug;6(8):1815-23
pubmed: 21757640
Can J Kidney Health Dis. 2015 Oct 06;2:36
pubmed: 26445676
J Thorac Cardiovasc Surg. 2021 May 11;:
pubmed: 34112503
Clin J Am Soc Nephrol. 2015 Feb 6;10(2):187-96
pubmed: 25424992