Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning.
| Autor: | Dam TA; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands. t.dam@amsterdamumc.nl., Roggeveen LF; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., van Diggelen F; Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, VU University, Amsterdam, The Netherlands., Fleuren LM; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., Jagesar AR; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., Otten M; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., de Vries HJ; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., Gommers D; Department of Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands., Cremer OL; Intensive Care, UMC Utrecht, Utrecht, The Netherlands., Bosman RJ; ICU, OLVG, Amsterdam, The Netherlands., Rigter S; Department of Anesthesiology and Intensive Care, St. Antonius Hospital, Nieuwegein, The Netherlands., Wils EJ; Department of Intensive Care, Franciscus Gasthuis & Vlietland, Rotterdam, The Netherlands., Frenzel T; Department of Intensive Care Medicine, Radboud University Medical Center, Nijmegen, The Netherlands., Dongelmans DA; Department of Intensive Care Medicine, Amsterdam UMC, Amsterdam, The Netherlands., de Jong R; Intensive Care, Bovenij Ziekenhuis, Amsterdam, The Netherlands., Peters MAA; Intensive Care, Canisius Wilhelmina Ziekenhuis, Nijmegen, The Netherlands., Kamps MJA; Intensive Care, Catharina Ziekenhuis Eindhoven, Eindhoven, The Netherlands., Ramnarain D; Department of Intensive Care, ETZ Tilburg, Tilburg, The Netherlands., Nowitzky R; Intensive Care, HagaZiekenhuis, Den Haag, The Netherlands., Nooteboom FGCA; Intensive Care, Laurentius Ziekenhuis, Roermond, The Netherlands., de Ruijter W; Department of Intensive Care Medicine, Northwest Clinics, Alkmaar, The Netherlands., Urlings-Strop LC; Intensive Care, Reinier de Graaf Gasthuis, Delft, The Netherlands., Smit EGM; Intensive Care, Spaarne Gasthuis, Haarlem en Hoofddorp, The Netherlands., Mehagnoul-Schipper DJ; Intensive Care, VieCuri Medisch Centrum, Venlo, The Netherlands., Dormans T; Intensive Care, Zuyderland MC, Heerlen, The Netherlands., de Jager CPC; Department of Intensive Care, Jeroen Bosch Ziekenhuis, Den Bosch, The Netherlands., Hendriks SHA; Intensive Care, Albert Schweitzerziekenhuis, Dordrecht, The Netherlands., Achterberg S; ICU, Haaglanden Medisch Centrum, Den Haag, The Netherlands., Oostdijk E; ICU, Maasstad Ziekenhuis Rotterdam, Rotterdam, The Netherlands., Reidinga AC; ICU, SEH, BWC, Martiniziekenhuis, Groningen, The Netherlands., Festen-Spanjer B; Intensive Care, Ziekenhuis Gelderse Vallei, Ede, The Netherlands., Brunnekreef GB; Department of Intensive Care, Ziekenhuisgroep Twente, Almelo, The Netherlands., Cornet AD; Department of Intensive Care, Medisch Spectrum Twente, Enschede, The Netherlands., van den Tempel W; Department of Intensive Care, Ikazia Ziekenhuis Rotterdam, Rotterdam, The Netherlands., Boelens AD; Antonius Ziekenhuis Sneek, Sneek, The Netherlands., Koetsier P; Intensive Care, Medisch Centrum Leeuwarden, Leeuwarden, The Netherlands., Lens J; ICU, IJsselland Ziekenhuis, Capelle aan den IJssel, The Netherlands., Faber HJ; ICU, WZA, Assen, The Netherlands., Karakus A; Department of Intensive Care, Diakonessenhuis Hospital, Utrecht, The Netherlands., Entjes R; Department of Intensive Care, Adrz, Goes, The Netherlands., de Jong P; Department of Anesthesia and Intensive Care, Slingeland Ziekenhuis, Doetinchem, The Netherlands., Rettig TCD; Department of Anesthesiology, Intensive Care and Pain Medicine, Amphia Ziekenhuis, Breda, The Netherlands., Arbous S; LUMC, Leiden, The Netherlands., Vonk SJJ; Pacmed, Amsterdam, The Netherlands., Machado T; Pacmed, Amsterdam, The Netherlands., Herter WE; Pacmed, Amsterdam, The Netherlands., de Grooth HJ; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., Thoral PJ; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., Girbes ARJ; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands., Hoogendoorn M; Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, VU University, Amsterdam, The Netherlands., Elbers PWG; Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Annals of intensive care [Ann Intensive Care] 2022 Oct 20; Vol. 12 (1), pp. 99. Date of Electronic Publication: 2022 Oct 20. |
| DOI: | 10.1186/s13613-022-01070-0 |
| Abstrakt: | Background: For mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, prone positioning is labor intensive and comes with potential adverse effects. Therefore, identifying which critically ill intubated COVID-19 patients will benefit may help allocate labor resources. Methods: From the multi-center Dutch Data Warehouse of COVID-19 ICU patients from 25 hospitals, we selected all 3619 episodes of prone positioning in 1142 invasively mechanically ventilated patients. We excluded episodes longer than 24 h. Berlin ARDS criteria were not formally documented. We used supervised machine learning algorithms Logistic Regression, Random Forest, Naive Bayes, K-Nearest Neighbors, Support Vector Machine and Extreme Gradient Boosting on readily available and clinically relevant features to predict success of prone positioning after 4 h (window of 1 to 7 h) based on various possible outcomes. These outcomes were defined as improvements of at least 10% in PaO Results: The median duration of prone episodes was 17 h (11-20, median and IQR, N = 2632). Despite extensive modeling using a plethora of machine learning techniques and a large number of potentially clinically relevant features, discrimination between responders and non-responders remained poor with an area under the receiver operator characteristic curve of 0.62 for PaO Conclusions: In mechanically ventilated COVID-19 patients, predicting the success of prone positioning using clinically relevant and readily available parameters from electronic health records is currently not feasible. Given the current evidence base, a liberal approach to proning in all patients with severe COVID-19 ARDS is therefore justified and in particular regardless of previous results of proning. (© 2022. The Author(s).) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |