Treffer: A machine learning-based prediction model for sepsis-associated delirium in intensive care unit patients with sepsis-associated acute kidney injury.

Title:
A machine learning-based prediction model for sepsis-associated delirium in intensive care unit patients with sepsis-associated acute kidney injury.
Authors:
Yu S; Department of Emergency, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China., Pan X; Department of Emergency, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China., Zhang M; Department of Emergency, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China., Zhang J; Department of Emergency, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China., Chen D; Department of Emergency, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China.
Source:
Renal failure [Ren Fail] 2025 Dec; Vol. 47 (1), pp. 2514186. Date of Electronic Publication: 2025 Jun 02.
Publication Type:
Journal Article; Observational Study
Language:
English
Journal Info:
Publisher: Informa Healthcare Country of Publication: England NLM ID: 8701128 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1525-6049 (Electronic) Linking ISSN: 0886022X NLM ISO Abbreviation: Ren Fail Subsets: MEDLINE
Imprint Name(s):
Publication: London : Informa Healthcare
Original Publication: New York, N.Y. : M. Dekker, c1987-
MeSH Terms:
Sepsis-Associated Encephalopathy*/diagnosis , Sepsis-Associated Encephalopathy*/etiology , Acute Kidney Injury*/etiology , Acute Kidney Injury*/psychology , Sepsis*/complications , Sepsis*/psychology , Predictive Learning Models*/statistics & numerical data, Retrospective Studies ; Intensive Care Units ; Databases, Factual ; Logistic Models ; Bayes Theorem ; Area Under Curve ; Reproducibility of Results ; Humans ; Male ; Female ; Middle Aged ; Aged ; Aged, 80 and over ; Predictive Value of Tests
References:
JAMA. 2016 Feb 23;315(8):801-10. (PMID: 26903338)
BMJ. 2012 Feb 09;344:e420. (PMID: 22323509)
Crit Care Med. 2015 Jan;43(1):40-7. (PMID: 25251759)
Med Care. 2018 Oct;56(10):890-897. (PMID: 30179988)
Am J Respir Crit Care Med. 2017 Jun 15;195(12):1597-1607. (PMID: 27854517)
J Crit Care. 2020 Apr;56:140-144. (PMID: 31901649)
Aging Clin Exp Res. 2022 Nov;34(11):2865-2872. (PMID: 36057682)
J Clin Med. 2023 Feb 06;12(4):. (PMID: 36835809)
Intensive Crit Care Nurs. 2025 Feb;86:103834. (PMID: 39299169)
Kidney Int. 2012 May;81(10):942-948. (PMID: 21814177)
PLoS One. 2022 Nov 22;17(11):e0276914. (PMID: 36413529)
Pragmat Obs Res. 2018 May 08;9:11-19. (PMID: 29773957)
J Cardiothorac Surg. 2021 Apr 26;16(1):113. (PMID: 33902644)
Crit Care Med. 2013 Jan;41(1):263-306. (PMID: 23269131)
Burns. 2020 Jun;46(4):797-803. (PMID: 32183993)
Sci Data. 2023 Jan 3;10(1):1. (PMID: 36596836)
Sci Rep. 2023 Aug 4;13(1):12697. (PMID: 37542106)
J Crit Care. 2024 Feb;79:154490. (PMID: 38000230)
Intensive Crit Care Nurs. 2020 Aug;59:102844. (PMID: 32253122)
Sci Data. 2018 Sep 11;5:180178. (PMID: 30204154)
Anesthesiology. 2006 Jan;104(1):21-6. (PMID: 16394685)
Intensive Care Med. 2015 Aug;41(8):1411-23. (PMID: 26162677)
BMJ. 2015 Jun 03;350:h2538. (PMID: 26041151)
J Cardiothorac Surg. 2022 Oct 1;17(1):247. (PMID: 36183105)
Neurotoxicology. 2018 Dec;69:11-16. (PMID: 30149051)
Front Neurol. 2024 Feb 20;15:1344004. (PMID: 38445262)
Nurs Crit Care. 2024 Jul;29(4):646-660. (PMID: 37699863)
BMC Anesthesiol. 2019 Mar 20;19(1):39. (PMID: 30894129)
Kidney Int. 2019 Nov;96(5):1083-1099. (PMID: 31443997)
JAMA. 2009 Feb 4;301(5):489-99. (PMID: 19188334)
Arch Intern Med. 2001 Apr 23;161(8):1099-105. (PMID: 11322844)
BMC Med. 2014 Oct 08;12:141. (PMID: 25300023)
Nurs Crit Care. 2021 May;26(3):150-155. (PMID: 31820554)
Front Cardiovasc Med. 2022 Mar 08;9:828015. (PMID: 35355967)
Nat Rev Nephrol. 2023 Jun;19(6):401-417. (PMID: 36823168)
Arch Intern Med. 2007 Aug 13-27;167(15):1629-34. (PMID: 17698685)
Minerva Anestesiol. 2022 Oct;88(10):815-826. (PMID: 35708040)
Contributed Indexing:
Keywords: MIMIC-IV database; eICU-CRD database; machine learning; predictive model; sepsis-associated acute kidney injury; sepsis-associated delirium
Entry Date(s):
Date Created: 20250602 Date Completed: 20250707 Latest Revision: 20250707
Update Code:
20250707
PubMed Central ID:
PMC12131538
DOI:
10.1080/0886022X.2025.2514186
PMID:
40456706
Database:
MEDLINE

Weitere Informationen

Sepsis-associated acute kidney injury (SA-AKI) patients in the ICU often suffer from sepsis-associated delirium (SAD), which is linked to unfavorable outcomes. This research aimed to develop a machine learning-based model for early SAD prediction in SA-AKI patients. Data was sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD). Various models, including logistic regression, extreme gradient boosting (XGBoost), random forest, k-nearest neighbors, support vector machine, decision tree, and naive Bayes, were constructed and evaluated. The XGBoost model emerged as the best, with an internal validation AUROC of 0.775 and an external validation AUROC of 0.687. Unlike traditional delirium assessments, this model enables earlier SAD prediction and is suitable for patients who are hard to assess conventionally.