Hostname: page-component-cd9895bd7-dzt6s Total loading time: 0 Render date: 2024-12-23T13:04:51.619Z Has data issue: false hasContentIssue false
  • English
  • Français

Prediction of extubation failure in the paediatric cardiac ICU using machine learning and high-frequency physiologic data

Published online by Cambridge University Press:  20 December 2021

Sydney R. Rooney Open the ORCID record for Sydney R. Rooney [Opens in a new window] ,
Evan L. Reynolds ,
Mousumi Banerjee ,
Sara K. Pasquali ,
John R. Charpie ,
Michael G. Gaies  and
Gabe E. Owens
Sydney R. Rooney
Affiliation:
Department of Pediatrics, Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA Department of Pediatrics, Division of Cardiology, C.S. Mott Children’s Hospital, University of Michigan, Ann Arbor, MI, USA
Evan L. Reynolds
Affiliation:
Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, USA
Mousumi Banerjee
Affiliation:
Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, USA Center for Healthcare Outcomes and Policy, University of Michigan, Ann Arbor, MI, USA
Sara K. Pasquali
Affiliation:
Department of Pediatrics, Division of Cardiology, C.S. Mott Children’s Hospital, University of Michigan, Ann Arbor, MI, USA Center for Healthcare Outcomes and Policy, University of Michigan, Ann Arbor, MI, USA
John R. Charpie
Affiliation:
Department of Pediatrics, Division of Cardiology, C.S. Mott Children’s Hospital, University of Michigan, Ann Arbor, MI, USA
Michael G. Gaies
Affiliation:
Department of Pediatrics, Division of Cardiology, C.S. Mott Children’s Hospital, University of Michigan, Ann Arbor, MI, USA Center for Healthcare Outcomes and Policy, University of Michigan, Ann Arbor, MI, USA
Gabe E. Owens*
Affiliation:
Department of Pediatrics, Division of Cardiology, C.S. Mott Children’s Hospital, University of Michigan, Ann Arbor, MI, USA
*
Author for correspondence: G. Owens, MD, PhD, C.S. Mott Children’s Hospital, 1540 E Hospital Drive, Ann Arbor, MI48109, USA. Tel: (734) 936-8997; Fax: 734-936-9470. E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

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.

Keywords

Airway extubationartificial respirationquality of healthcareclinical decision-makingmachine learning
Type
Original Article
Information
Cardiology in the Young , Volume 32 , Issue 10 , October 2022 , pp. 1649 - 1656
Check for updates
Copyright
© The Author(s), 2021. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Farias, JA, Retta, A, Alía, I, et al. A comparison of two methods to perform a breathing trial before extubation in pediatric intensive care patients. Intensive Care Med 2001; 27: 1649–1654.CrossRefGoogle ScholarPubMed
Kurachek, SC, Newth, CJ, Quasney, MW, et al. Extubation failure in pediatric intensive care: a multiple-center study of risk factors and outcomes. Crit Care Med 2003; 31: 2657–2664.CrossRefGoogle ScholarPubMed
Rothaar, RC, Epstein, SK. Extubation failure: magnitude of the problem, impact on outcomes, and prevention. Curr Opin Crit Care 2003; 9: 59–66.CrossRefGoogle Scholar
Epstein, SK, Ciubotaru, RL, Wong, JB. Effect of failed extubation on the outcome of mechanical ventilation. Chest 1997; 112: 186–192.CrossRefGoogle ScholarPubMed
Randolph, AG, Wypij, D, Venkataraman, ST, et al. Effect of mechanical ventilator weaning protocols on respiratory outcomes in infants and children: a randomized controlled trial. JAMA 2002; 288: 2561–2568.CrossRefGoogle ScholarPubMed
Ferguson, LP, Walsh, BK, Munhall, D, et al. A spontaneous breathing trial with pressure support overestimates readiness for extubation in children. Pediatr Crit Care Med 2011, 12, , e330–335.CrossRefGoogle ScholarPubMed
Newth, CJL, Venkataraman, S, Willson, DF, et al. Weaning and extubation readiness in pediatric patients. Pediatr Crit Care Med 2009; 10: 1–11.CrossRefGoogle ScholarPubMed
Ferreira, FV, Sugo, EK, Aragon, DC, et al. Spontaneous breathing trial for prediction of extubation success in pediatric patients following congenital heart surgery: a randomized, controlled trial. Pediatr Crit Care Med 2019; 20: 940–946.CrossRefGoogle Scholar
Abu-Sultaneh, S, Hole, AJ, Tori, AJ, et al. An interprofessional quality improvement initiative to standardize pediatric extubation readiness assessment. Pediatr Crit Care Med 2017, 18, , e463–e471.CrossRefGoogle Scholar
Banerjee, M, Reynolds, E, Andersson, HB, et al. Tree-based analysis. Circ Cardiovasc Qual Outcomes 2019; 12: e004879.CrossRefGoogle ScholarPubMed
Gaies, M, Cooper, DS, Tabbutt, S, et al. Collaborative quality improvement in the cardiac intensive care unit: development of the Paediatric Cardiac Critical Care Consortium (PC4). Cardiol Young 2015; 25: 951–957.CrossRefGoogle Scholar
Gaies, M, Donohue, JE, Willis, GM, et al. Data integrity of the Pediatric Cardiac Critical Care Consortium (PC4) clinical registry. Cardiol Young 2016; 26: 1090–1096.CrossRefGoogle ScholarPubMed
T3 Data Aggregation & Visualization [Internet]. Etiometry. Retrieved October 29, 2018, from http://www.etiometry.com/our-platform/t3-visualization/ Google Scholar
Gaies, M, Tabbutt, S, Schwartz, SM, et al. Clinical epidemiology of extubation failure in the pediatric cardiac ICU: a report from the pediatric cardiac critical care consortium. Pediatr Crit Care Med 2015; 16: 837–845.CrossRefGoogle ScholarPubMed
Breiman, L, Friedman, J, Olshen, R, et al. Classification and Regression Trees. Wadsworth, Belmont, CA, 1984.Google Scholar
Hastie, T, Tibshirani, R, Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, New York, 2001.CrossRefGoogle Scholar
Breiman, L. Random forests. Mach Learn 2001; 45: 5–32.CrossRefGoogle Scholar
Freund, Y, Schapire, R. Experiments with a new boosting algorithm. In Proceedings of the Thirteenth International Conference on Machine Learning. Morgan Kaufmann, San Francisco, CA, 1996: 148–156.Google Scholar
Ishwaran, H, Kogalur, U. Fast Unified Random Forests for Survival, Regression, and Classification (RF-SRC) [Internet], 2020. https://cran.r-project.org/package=randomForestSRC Google Scholar
Therneau, T, Atkinson, B, Ripley, B. Rpart: Recursive Partitioning and Regression Trees. R Package Version 4.1-3, 2013. http://CRAN.R-project.org/package=rpart Google Scholar
Bischl, B, Lang, M, Schiffner, J, et al. mlr: machine learning in R. J Mach Learn Res 2016; 17: 1–5.Google Scholar
Alfaro, E, Gamez, M, Garcia, N. adabag: an R package for classification with boosting and bagging. J Stat Softw 2013, 54:1–35.CrossRefGoogle Scholar
Norrie, J. The challenge of implementing AI models in the ICU. Lancet Respir Med 2018; 6: 886–888.CrossRefGoogle ScholarPubMed
Hu, SB, Wong, DJL, Correa, A, et al. Prediction of clinical deterioration in hospitalized adult patients with hematologic malignancies using a neural network model. PloS One 2016; 11: e0161401.CrossRefGoogle ScholarPubMed
Jalali, A, Bender, D, Rehman, M, et al. Advanced analytics for outcome prediction in intensive care units. Annu Int Conf IEEE Eng Med Biol Soc 2016; 2016: 2520–2524.Google ScholarPubMed
Jalali, A, Licht, DJ, Nataraj, C. Application of decision tree in the prediction of periventricular leukomalacia (PVL) occurrence in neonates after heart surgery. Annu Int Conf IEEE Eng Med Biol Soc 2012; 2012: 5931–5934.Google ScholarPubMed
Goodman, KE, Lessler, J, Cosgrove, SE, et al. A clinical decision tree to predict whether a bacteremic patient is infected with an extended-spectrum β-lactamase-producing organism, 2016; 63: 896–903.Google Scholar
Fairchild, KD. Predictive monitoring for early detection of sepsis in neonatal ICU patients. Curr Opin Pediatr 2013; 25: 172–179.CrossRefGoogle ScholarPubMed
Olive, MK, Owens, GE. Current monitoring and innovative predictive modeling to improve care in the pediatric cardiac intensive care unit. Transl Pediatr 2018; 7: 120–128.CrossRefGoogle ScholarPubMed