Boosting the accuracy of existing models by updating and extending: using a multicenter COVID-19 ICU cohort as a proxy.

Autor: Meijs DAM; Department of Intensive Care Medicine, Maastricht University Medical Center + (Maastricht UMC+), P. Debyelaan 25, 6229 HX, Maastricht, the Netherlands. daniek.meijs@mumc.nl.; Department of Intensive Care Medicine, Laurentius Ziekenhuis, Roermond, the Netherlands. daniek.meijs@mumc.nl.; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the Netherlands. daniek.meijs@mumc.nl., Wynants L; Department of Epidemiology, Care and Public Health Research Institute (CAPHRI), Maastricht University, Maastricht, the Netherlands.; Department of Development and Regeneration, KULeuven, Leuven, Belgium.; Epi-Centre, KULeuven, Leuven, Belgium., van Kuijk SMJ; Department of Clinical Epidemiology and Medical Technology Assessment, Maastricht UMC+, Maastricht, the Netherlands., Scheeren CIE; Department of Intensive Care Medicine, Zuyderland Medisch Centrum, Heerlen/Sittard, the Netherlands., Hana A; Department of Intensive Care Medicine, Laurentius Ziekenhuis, Roermond, the Netherlands.; Department of Intensive Care Medicine, University Hospital of Zurich, Zurich, Switzerland., Mehagnoul-Schipper J; Department of Intensive Care Medicine, VieCuri Medisch Centrum, Venlo, the Netherlands., Stessel B; Department of Intensive Care Medicine, Jessa Hospital, Hasselt, Belgium.; Faculty of Medicine and Life Sciences, UHasselt, Diepenbeek, Belgium., Vander Laenen M; Department of Intensive Care Medicine, Ziekenhuis Oost-Limburg (ZOL), Genk, Belgium., Cox EGM; Department of Intensive Care Medicine, Maastricht University Medical Center + (Maastricht UMC+), P. Debyelaan 25, 6229 HX, Maastricht, the Netherlands.; Department of Intensive Care Medicine, University Medical Center Groningen (UMCG), Groningen, the Netherlands., Sels JEM; Department of Intensive Care Medicine, Maastricht University Medical Center + (Maastricht UMC+), P. Debyelaan 25, 6229 HX, Maastricht, the Netherlands.; Department of Cardiology, Maastricht UMC+, Maastricht, the Netherlands., Smits LJM; Department of Epidemiology, Care and Public Health Research Institute (CAPHRI), Maastricht University, Maastricht, the Netherlands., Bickenbach J; Department of Intensive Care Medicine, University Hospital Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen, Aachen, Germany., Mesotten D; Faculty of Medicine and Life Sciences, UHasselt, Diepenbeek, Belgium.; Department of Intensive Care Medicine, Ziekenhuis Oost-Limburg (ZOL), Genk, Belgium., van der Horst ICC; Department of Intensive Care Medicine, Maastricht University Medical Center + (Maastricht UMC+), P. Debyelaan 25, 6229 HX, Maastricht, the Netherlands.; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the Netherlands., Marx G; Department of Intensive Care Medicine, University Hospital Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen, Aachen, Germany., van Bussel BCT; Department of Intensive Care Medicine, Maastricht University Medical Center + (Maastricht UMC+), P. Debyelaan 25, 6229 HX, Maastricht, the Netherlands.; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the Netherlands.; Department of Epidemiology, Care and Public Health Research Institute (CAPHRI), Maastricht University, Maastricht, the Netherlands.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Nov 01; Vol. 14 (1), pp. 26344. Date of Electronic Publication: 2024 Nov 01.
DOI: 10.1038/s41598-024-70333-6
Abstrakt: Most published prediction models for Coronavirus Disease 2019 (COVID-19) were poorly reported, at high risk of bias, and heterogeneous in model performance. To tackle methodological challenges faced in previous prediction studies, we investigated whether model updating and extending improves mortality prediction, using the Intensive Care Unit (ICU) as a proxy. All COVID-19 patients admitted to seven ICUs in the Euregio-Meuse Rhine during the first pandemic wave were included. The 4C Mortality and SEIMC scores were selected as promising prognostic models from an external validation study. Five predictors could be estimated based on cohort size. TRIPOD guidelines were followed and logistic regression analyses with the linear predictor, APACHE II score, and country were performed. Bootstrapping with backward selection was applied to select variables for the final model. Additionally, shrinkage was performed. Model discrimination was displayed as optimism-corrected areas under the ROC curve and calibration by calibration slopes and plots. The mortality rate of the 551 included patients was 36%. Discrimination of the 4C Mortality and SEIMC scores increased from 0.70 to 0.74 and 0.70 to 0.73 and calibration plots improved compared to the original models after updating and extending. Mortality prediction can be improved after updating and extending of promising models.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje