Identifying the need for infection-related consultations in intensive care patients using machine learning models.

Autor: Zwerwer LR; Department of Health Sciences, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands. l.r.zwerwer@rug.nl.; Center for Information Technology, University of Groningen, Nettelbosje 1, 9747 AJ, Groningen, The Netherlands. l.r.zwerwer@rug.nl., Luz CF; Department of Medical Microbiology and Infection Prevention, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., Soudis D; Center for Information Technology, University of Groningen, Nettelbosje 1, 9747 AJ, Groningen, The Netherlands., Giudice N; Center for Information Technology, University of Groningen, Nettelbosje 1, 9747 AJ, Groningen, The Netherlands., Nijsten MWN; Department of Critical Care, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., Glasner C; Department of Medical Microbiology and Infection Prevention, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., Renes MH; Department of Critical Care, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., Sinha B; Department of Medical Microbiology and Infection Prevention, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Jan 28; Vol. 14 (1), pp. 2317. Date of Electronic Publication: 2024 Jan 28.
DOI: 10.1038/s41598-024-52741-w
Abstrakt: Infection-related consultations on intensive care units (ICU) have a positive impact on quality of care and clinical outcome. However, timing of these consultations is essential and to date they are typically event-triggered and reactive. Here, we investigate a proactive approach to identify patients in need for infection-related consultations by machine learning models using routine electronic health records. Data was retrieved from a mixed ICU at a large academic tertiary care hospital including 9684 admissions. Infection-related consultations were predicted using logistic regression, random forest, gradient boosting machines, and long short-term memory neural networks (LSTM). Overall, 7.8% of admitted patients received an infection-related consultation. Time-sensitive modelling approaches performed better than static approaches. Using LSTM resulted in the prediction of infection-related consultations in the next clinical shift (up to eight hours in advance) with an area under the receiver operating curve (AUROC) of 0.921 and an area under the precision recall curve (AUPRC) of 0.541. The successful prediction of infection-related consultations for ICU patients was done without the use of classical triggers, such as (interim) microbiology reports. Predicting this key event can potentially streamline ICU and consultant workflows and improve care as well as outcome for critically ill patients with (suspected) infections.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje