Literature DB >> 36264358

Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning.

Tariq A Dam1, Luca F Roggeveen2, Fuda van Diggelen3, Lucas M Fleuren2, Ameet R Jagesar2, Martijn Otten2, Heder J de Vries2, Diederik Gommers4, Olaf L Cremer5, Rob J Bosman6, Sander Rigter7, Evert-Jan Wils8, Tim Frenzel9, Dave A Dongelmans10, Remko de Jong11, Marco A A Peters12, Marlijn J A Kamps13, Dharmanand Ramnarain14, Ralph Nowitzky15, Fleur G C A Nooteboom16, Wouter de Ruijter17, Louise C Urlings-Strop18, Ellen G M Smit19, D Jannet Mehagnoul-Schipper20, Tom Dormans21, Cornelis P C de Jager22, Stefaan H A Hendriks23, Sefanja Achterberg24, Evelien Oostdijk25, Auke C Reidinga26, Barbara Festen-Spanjer27, Gert B Brunnekreef28, Alexander D Cornet29, Walter van den Tempel30, Age D Boelens31, Peter Koetsier32, Judith Lens33, Harald J Faber34, A Karakus35, Robert Entjes36, Paul de Jong37, Thijs C D Rettig38, Sesmu Arbous39, Sebastiaan J J Vonk40, Tomas Machado40, Willem E Herter40, Harm-Jan de Grooth2, Patrick J Thoral2, Armand R J Girbes2, Mark Hoogendoorn3, Paul W G Elbers2.   

Abstract

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 PaO2/FiO2 ratio, ventilatory ratio, respiratory system compliance, or mechanical power. Separate models were created for each of these outcomes. Re-supination within 4 h after pronation was labeled as failure. We also developed models using a 20 mmHg improvement cut-off for PaO2/FiO2 ratio and using a combined outcome parameter. For all models, we evaluated feature importance expressed as contribution to predictive performance based on their relative ranking.
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 PaO2/FiO2 ratio using Logistic Regression, Random Forest and XGBoost. Feature importance was inconsistent between models for different outcomes. Notably, not even being a previous responder to prone positioning, or PEEP-levels before prone positioning, provided any meaningful contribution to predicting a successful next proning episode.
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).

Entities:  

Keywords:  Acute respiratory distress syndrome; COVID-19; Mechanical ventilation

Year:  2022        PMID: 36264358      PMCID: PMC9583049          DOI: 10.1186/s13613-022-01070-0

Source DB:  PubMed          Journal:  Ann Intensive Care        ISSN: 2110-5820            Impact factor:   10.318


  16 in total

1.  Prone positioning in severe acute respiratory distress syndrome.

Authors:  Claude Guérin; Jean Reignier; Jean-Christophe Richard; Pascal Beuret; Arnaud Gacouin; Thierry Boulain; Emmanuelle Mercier; Michel Badet; Alain Mercat; Olivier Baudin; Marc Clavel; Delphine Chatellier; Samir Jaber; Sylvène Rosselli; Jordi Mancebo; Michel Sirodot; Gilles Hilbert; Christian Bengler; Jack Richecoeur; Marc Gainnier; Frédérique Bayle; Gael Bourdin; Véronique Leray; Raphaele Girard; Loredana Baboi; Louis Ayzac
Journal:  N Engl J Med       Date:  2013-05-20       Impact factor: 91.245

2.  Acute respiratory distress syndrome: the Berlin Definition.

Authors:  V Marco Ranieri; Gordon D Rubenfeld; B Taylor Thompson; Niall D Ferguson; Ellen Caldwell; Eddy Fan; Luigi Camporota; Arthur S Slutsky
Journal:  JAMA       Date:  2012-06-20       Impact factor: 56.272

3.  Physiologic Analysis and Clinical Performance of the Ventilatory Ratio in Acute Respiratory Distress Syndrome.

Authors:  Pratik Sinha; Carolyn S Calfee; Jeremy R Beitler; Neil Soni; Kelly Ho; Michael A Matthay; Richard H Kallet
Journal:  Am J Respir Crit Care Med       Date:  2019-02-01       Impact factor: 30.528

4.  Mechanical power at a glance: a simple surrogate for volume-controlled ventilation.

Authors:  Lorenzo Giosa; Mattia Busana; Iacopo Pasticci; Matteo Bonifazi; Matteo Maria Macrì; Federica Romitti; Francesco Vassalli; Davide Chiumello; Michael Quintel; J J Marini; Luciano Gattinoni
Journal:  Intensive Care Med Exp       Date:  2019-11-27

Review 5.  Prone position in COVID 19-associated acute respiratory failure.

Authors:  Aileen Kharat; Marie Simon; Claude Guérin
Journal:  Curr Opin Crit Care       Date:  2022-02-01       Impact factor: 3.687

6.  Comparing different supervised machine learning algorithms for disease prediction.

Authors:  Shahadat Uddin; Arif Khan; Md Ekramul Hossain; Mohammad Ali Moni
Journal:  BMC Med Inform Decis Mak       Date:  2019-12-21       Impact factor: 2.796

Review 7.  Prone position in ARDS patients: why, when, how and for whom.

Authors:  Claude Guérin; Richard K Albert; Jeremy Beitler; Luciano Gattinoni; Samir Jaber; John J Marini; Laveena Munshi; Laurent Papazian; Antonio Pesenti; Antoine Vieillard-Baron; Jordi Mancebo
Journal:  Intensive Care Med       Date:  2020-11-10       Impact factor: 41.787

Review 8.  The Down Side of Prone Positioning: The Case of a Coronavirus 2019 Survivor.

Authors:  Minh Quan Le; Richard Rosales; Lauren T Shapiro; Laura Y Huang
Journal:  Am J Phys Med Rehabil       Date:  2020-10       Impact factor: 3.412

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.