Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2013:2:1000118.
doi: 10.4172/2167-0897.1000118.

Can Machine Learning Methods Predict Extubation Outcome in Premature Infants as well as Clinicians?

Martina Mueller  1 , Jonas S Almeida  2 , Romesh Stanislaus  3 , Carol L Wagner  4
Affiliations

Can Machine Learning Methods Predict Extubation Outcome in Premature Infants as well as Clinicians?

Martina Mueller et al. J Neonatal Biol. 2013.

Abstract

Rationale: Though treatment of the prematurely born infant breathing with assistance of a mechanical ventilator has much advanced in the past decades, predicting extubation outcome at a given point in time remains challenging. Numerous studies have been conducted to identify predictors for extubation outcome; however, the rate of infants failing extubation attempts has not declined.

Objective: To develop a decision-support tool for the prediction of extubation outcome in premature infants using a set of machine learning algorithms.

Methods: A dataset assembled from 486 premature infants on mechanical ventilation was used to develop predictive models using machine learning algorithms such as artificial neural networks (ANN), support vector machine (SVM), naïve Bayesian classifier (NBC), boosted decision trees (BDT), and multivariable logistic regression (MLR). Performance of all models was evaluated using area under the curve (AUC).

Results: For some of the models (ANN, MLR and NBC) results were satisfactory (AUC: 0.63-0.76); however, two algorithms (SVM and BDT) showed poor performance with AUCs of ~0.5.

Conclusion: Clinician's predictions still outperform machine learning due to the complexity of the data and contextual information that may not be captured in clinical data used as input for the development of the machine learning algorithms. Inclusion of preprocessing steps in future studies may improve the performance of prediction models.

Keywords: Premature infant; extubation; machine learning; mechanical ventilation; prediction.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Distribution of birth weight categories by extubation outcome
Figure 2
Figure 2
ROC curves for validation for ANN, MLR and NBC (full set)
See this image and copyright information in PMC

References

    1. Halliday HL. What interventions facilitate weaning from the ventilator? A review of the evidence from systematic reviews. Paediatr Respir Rev. 2004;5(Suppl A):S347–S352. - PubMed
    1. Bancalari E, Claure N. Weaning Infants from Mechanical Ventilation. Neonatology. 2008;94:197–202. doi: 10.1159/000143722. - PubMed
    1. Greenough A, Prendergast M. Difficult extubation in low birthweight infants. Arch Dis Child Fetal Neonatal Ed. 2008;93:F242–F245. doi:10.1136/adc.2007.121335. - PubMed
    1. Barrington KJ. Extubation failure in the very preterm infant. J Pediatr (Rio J) 2009;85(5):375–377. doi:10.2223/JPED.1937. - PubMed
    1. Gupta S, Sinha SK, Tin W, Donn SM. A Randomized Controlled Trial of Post-extubation Bubble Continuous Positive Airway Pressure Versus Infant Flow Driver Continuous Positive Airway Pressure in Preterm Infants with Respiratory Distress Syndrome. J Pediatr. 2009;154:645–50. Doi:10.1016/j.jpeds.2008.12.034. - PubMed

LinkOut - more resources