3 results
Prediction of extubation failure in the paediatric cardiac ICU using machine learning and high-frequency physiologic data
- Sydney R. Rooney, Evan L. Reynolds, Mousumi Banerjee, Sara K. Pasquali, John R. Charpie, Michael G. Gaies, Gabe E. Owens
-
- Journal:
- Cardiology in the Young / Volume 32 / Issue 10 / October 2022
- Published online by Cambridge University Press:
- 20 December 2021, pp. 1649-1656
-
- Article
- Export citation
-
Background:
Cardiac intensivists frequently assess patient readiness to wean off mechanical ventilation with an extubation readiness trial despite it being no more effective than clinician judgement alone. We evaluated the utility of high-frequency physiologic data and machine learning for improving the prediction of extubation failure in children with cardiovascular disease.
Methods:This was a retrospective analysis of clinical registry data and streamed physiologic extubation readiness trial data from one paediatric cardiac ICU (12/2016-3/2018). We analysed patients’ final extubation readiness trial. Machine learning methods (classification and regression tree, Boosting, Random Forest) were performed using clinical/demographic data, physiologic data, and both datasets. Extubation failure was defined as reintubation within 48 hrs. Classifier performance was assessed on prediction accuracy and area under the receiver operating characteristic curve.
Results:Of 178 episodes, 11.2% (N = 20) failed extubation. Using clinical/demographic data, our machine learning methods identified variables such as age, weight, height, and ventilation duration as being important in predicting extubation failure. Best classifier performance with this data was Boosting (prediction accuracy: 0.88; area under the receiver operating characteristic curve: 0.74). Using physiologic data, our machine learning methods found oxygen saturation extremes and descriptors of dynamic compliance, central venous pressure, and heart/respiratory rate to be of importance. The best classifier in this setting was Random Forest (prediction accuracy: 0.89; area under the receiver operating characteristic curve: 0.75). Combining both datasets produced classifiers highlighting the importance of physiologic variables in determining extubation failure, though predictive performance was not improved.
Conclusion:Physiologic variables not routinely scrutinised during extubation readiness trials were identified as potential extubation failure predictors. Larger analyses are necessary to investigate whether these markers can improve clinical decision-making.
Contributors
-
- By Nozomi Akanuma, Gonzalo Alarcón, R. Arunachalam, Sarah H. Bernard, Frank M. C. Besag, Istvan Bodi, Stephen Brown, Franz Brunnhuber, Antonella Cerquiglini, J. Helen Cross, R. Shane Delamont, Archana Desurkar, Lee Drummond, Rona Eade, Robert D. C. Elwes, Bidi Evans, Peter Fenwick, Colin D. Ferrie, Paul L. Furlong, Laura H. Goldstein, Sally Gomersall, Sushma Goyal, Jane Hanna, Yvonne Hart, Dominic C. Heaney, Graham E. Holder, Mrinalini Honavar, Elaine Hughes, Jozef M. Jarosz, John G. R. Jefferys, Jane Juler, Mathias Koepp, Michalis Koutroumanidis, Maureen Lahiff, Louis Lemieux, David McCormick, Brian Meldrum, John D. C. Mellers, Nicholas Moran, John Moriarty, Robin G. Morris, Nandini Mullatti, Lina Nashef, Jennifer Nightingale, T. J. von Oertzen, Corina O'Neill, Philip N. Patsalos, Stella Pearson, Charles E. Polkey, Ronit Pressler, Edward H. Reynolds, Mark P. Richardson, Leone Ridsdale, Robert Robinson, Greg Rogers, Euan M. Ross, Richard P. Selway, Stefano Seri, Simeran Sharma, Graeme J. Sills, Andrew Simmons, Shiri Spector, Mark Stevenson, Jade N. Thai, Brian Toone, Antonio Valentín, Nuria T. Villagra, Matthew Walker, William Whitehouse
- Edited by Gonzalo Alarcón, King's College London, Antonio Valentín, King's College London
-
- Book:
- Introduction to Epilepsy
- Published online:
- 05 July 2012
- Print publication:
- 26 April 2012, pp xii-xv
-
- Chapter
- Export citation
Contributors
-
- By Yasir Abu-Omar, Matthew E. Atkins, Joseph E. Arrowsmith, Alan Ashworth, Rubia Baldassarri, Craig R. Bailey, David J. Barron, Christiana C. Burt, David Cardone, Coralie Carle, Jose Coddens, Alan M. Cohen, Simon Colah, Sarah Conolly, David J. Daly, Helen M. Daly, Stefan G. De Hert, Ravi J. De Silva, Mark Dougherty, John J. Dunning, Maros Elsik, Betsy Evans, Florian Falter, Nigel Farnum, Jens Fassl, Juliet E. Foweraker, Simon P. Fynn, Andrew I. Gardner, Margaret I. Gillham, Martin J. Goddard, Maximilien J. Gourdin, Jon Graham, Stephen J. Gray, Cameron Graydon, Fabio Guarracino, Roger M. O. Hall, Michael Haney, Charles W. Hogue, Ben W. Howes, Bevan Hughes, Siân I. Jaggar, David P. Jenkins, Jörn Karhausen, Todd Kiefer, Khalid Khan, Andrew A. Klein, John D. Kneeshaw, Andrew C. Knowles, Catherine V. Koffel, R. Clive Landis, Trevor W. R. Lee, Clive J. Lewis, Jonathan H. Mackay, Amod Manocha, Jonathan B. Mark, Sarah Marstin, William T. McBride, Kenneth H. McKinlay, Alan F. Merry, Berend Mets, Britta Millhoff, Kevin P. Morris, Samer A. M. Nashef, Andrew Neitzel, Stephane Noble, Rabi Panigrahi, Barbora Parizkova, J. M. Tom Pierce, Mihai V. Podgoreanu, Hans-Joachim Priebe, Paul Quinton, C. Ramaswamy Rajamohan, Doris M. Rassl, Tom Rawlings, Fiona E. Reynolds, Andrew J. Richardson, David Riddington, Andrew Roscoe, Paul H. M. Sadleir, Ving Yuen See Tho, Herve Schlotterbeck, Maura Screaton, Shitalkumar Shah, Harjot Singh, Jon H. Smith, M. L. Srikanth, Yeewei W. Teo, Kamen P. Valchanov, Jean-Pierre van Besouw, Isabeau A. Walker, Stephen T. Webb, Francis C. Wells, John Whitbread, Charles Willmott, Patrick Wouters
- Edited by Jonathan H. Mackay, Joseph E. Arrowsmith
-
- Book:
- Core Topics in Cardiac Anesthesia
- Published online:
- 05 April 2012
- Print publication:
- 15 March 2012, pp x-xiii
-
- Chapter
- Export citation