• Pressure injury surveillance i...

*Result*: Pressure injury surveillance in the intensive care unit: Development, validation, and clinical application of a natural language processing algorithm.

Title:
Pressure injury surveillance in the intensive care unit: Development, validation, and clinical application of a natural language processing algorithm.
Authors:
Pilowsky JK; Intensive Care NSW, NSW Agency for Clinical Innovation, Australia; School of Public Health, Faculty of Medicine and Health, University of Sydney, Australia. Electronic address: Julia.Pilowsky@sydney.edu.au., Choi JW; Intensive Care NSW, NSW Agency for Clinical Innovation, Australia; eHealth NSW, Australia., Nguyen N; Intensive Care NSW, NSW Agency for Clinical Innovation, Australia; Sydney School of Medicine (Nepean Clinical School), Faculty of Medicine and Health, University of Sydney, Australia; Nepean Hospital, NSW, Australia., Williams L; Intensive Care NSW, NSW Agency for Clinical Innovation, Australia., Jones SL; St George Hospital, NSW, Australia.
Source:
Australian critical care : official journal of the Confederation of Australian Critical Care Nurses [Aust Crit Care] 2026 Feb; Vol. 39 (1), pp. 101487. Date of Electronic Publication: 2025 Nov 27.
Publication Type:
Journal Article; Multicenter Study; Validation Study
Language:
English
Journal Info:
Publisher: Confederation of Australian Critical Care Nurses Country of Publication: Australia NLM ID: 9207852 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1036-7314 (Print) Linking ISSN: 10367314 NLM ISO Abbreviation: Aust Crit Care Subsets: MEDLINE
Imprint Name(s):
Publication: North Strathfield : Confederation of Australian Critical Care Nurses
Original Publication: North Strathfield, NSW : The Confederation, [1992-
MeSH Terms:
Pressure Ulcer*/epidemiology , Intensive Care Units* , Algorithms* , Natural Language Processing*, Australia/epidemiology ; Humans ; Retrospective Studies ; Female ; Male ; Middle Aged ; Aged ; Adult
Contributed Indexing:
Keywords: Adults; Critical care; Natural language processing; Pressure injury; Public health surveillance
Entry Date(s):
Date Created: 20251128 Date Completed: 20260131 Latest Revision: 20260131
Update Code:
20260201
DOI:
10.1016/j.aucc.2025.101487
PMID:
41314153
Database:
MEDLINE

*Further Information*

*Introduction: Pressure injuries (PIs) are one of the most common hospital-acquired complications in patients admitted to an intensive care unit (ICU). Existing PI surveillance systems are known to have multiple limitations, including poor data quality. Previous studies investigating PI acquisition in critically ill populations have had relatively small sample sizes and have not considered when PIs occur during the ICU admission.
Objectives: The objective of this study was to develop and validate an algorithm capable of performing PI surveillance in the adult ICU population and to use this algorithm to describe the number of patients with PIs identified in the cohort and clinical characteristics associated with PI development.
Methods: A multicentre, retrospective cohort study was conducted across five Australian ICUs from June 2017 to June 2023. Natural language processing techniques were used to develop the surveillance algorithm, which detected PIs documented in the progress notes. The surveillance algorithm was externally validated using a combination of clinical codes and manual chart review. Data from the algorithm were then linked to the Australian and New Zealand Intensive Care Society Adult Patient Database to obtain the clinical characteristics for the cohort.
Results: Data from 40,033 patients were included in the study, including over 120 million free-text fields. The surveillance algorithm demonstrated satisfactory overall performance (F1 score: 0.743-0.749) on external validation. PIs were identified in 8.35% (n = 3344) of the cohort, with 63.19% (n = 2113) of these acquired during the ICU admission. PIs acquired in the ICU tended to occur early in the ICU admission, with 70.3% (n = 1486) identified within the first 5 days. Patients identified as having a PI had a higher severity of illness (median Acute Physiology and Chronic Health Evaluation III score: 67 vs 49) and were more likely to have received invasive ventilation (57.1% vs 32.5%).
Conclusions: Natural language processing can be used to perform PI surveillance in the ICU and facilitate the conduct of observational research. Future studies should consider integrating the finding that ICU-acquired PIs occur early in the ICU stay into quality improvement programs aimed at reducing PI incidence.
(Copyright © 2025 The Author(s). Published by Elsevier Ltd.. All rights reserved.)*

*Declaration of competing interests The authors declare they have no financial disclosures or conflicts of interest.*