Pressure injury prediction models for critically-ill patients should consider both the case-mix and local factors

Mieke Deschepper, Sonia O. Labeau, Willem Waegeman, Stijn I. Blot, the DecubICUs Study Team, The European Society of Intensive Care Medicine (ESICM) Trials Group, Frances Lin, Ged Williams, Mei Ye, Wei Zhang, Ying Liu, Jing Wang, Yan Wang, Li Chuntang Li, Lei Chen, Yang Liu, Jennifer Hughes, Christopher Barnes

Research output: Contribution to journalLetterpeer-review

15 Citations (Scopus)

Abstract

Dear Editor,
Pressure injuries in intensive care unit (ICU) patients are associated with unfavourable outcomes (Labeau et al., 2021). Models for predicting ICU-acquired pressure injury have been developed using machine learning and classic regression techniques, respectively resulting in areas under the receiver operating characteristic curve (AUC) of 0.79 (Alderden et al., 2018) and 0.89 (Ladios-Martinet al., 2020), but also resulting in large differences among predictors identified.
Original languageEnglish
Article number103033
Number of pages2
JournalIntensive and Critical Care Nursing
Volume65
DOIs
Publication statusPublished - Aug 2021
Externally publishedYes

Keywords

  • pressure injury
  • critically ill patients
  • intensive care unit (ICU)
  • case-control studies

Fingerprint

Dive into the research topics of 'Pressure injury prediction models for critically-ill patients should consider both the case-mix and local factors'. Together they form a unique fingerprint.

Cite this