An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis.

Paul Walsh, Padraig Cunningham, Stephen J. Rothenberg, Sinead O'Doherty, Hilary Hoey, Roisin Healy

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

BACKGROUND: Artificial neural networks apply complex non-linear functions to pattern recognition problems. An ensemble is a 'committee' of neural networks that usually outperforms single neural networks. Bronchiolitis is a common manifestation of viral lower respiratory tract infection in infants and toddlers. OBJECTIVE: To train artificial neural network ensembles to predict the disposition and length of stay in children presenting to the Emergency Department with bronchiolitis. METHODS: A specifically constructed database of 119 episodes of bronchiolitis was used to train, validate, and test a neural network ensemble. We used EasyNN 7.0 on a 200 Mhz pentium PC with a maths co-processor. The ensemble of neural networks constructed was subjected to fivefold validation. Comparison with actual and predicted dispositions was measured using the kappa statistic for disposition and the Kaplan-Meier estimations and log rank test for predictions of length of stay. RESULTS: The neural network ensembles correctly predicted disposition in 81% (range 75-90%) of test cases. When compared with actual disposition the neural network performed similarly to a logistic regression model and significantly better than various 'dumb machine' strategies with which we compared it. The prediction of length of stay was poorer, 65% (range 60-80%), but the difference between observed and predicted lengths of stay were not significantly different. CONCLUSION: Artificial neural network ensembles can predict disposition for infants and toddlers with bronchiolitis; however, the prediction of length of hospital stay is not as good.

Original languageEnglish (US)
Pages (from-to)259-264
Number of pages6
JournalEuropean journal of emergency medicine : official journal of the European Society for Emergency Medicine
Volume11
Issue number5
StatePublished - Oct 2004
Externally publishedYes

Fingerprint

Bronchiolitis
Length of Stay
Logistic Models
Respiratory Tract Infections
Hospital Emergency Service
Databases

ASJC Scopus subject areas

  • Emergency Medicine

Cite this

An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis. / Walsh, Paul; Cunningham, Padraig; Rothenberg, Stephen J.; O'Doherty, Sinead; Hoey, Hilary; Healy, Roisin.

In: European journal of emergency medicine : official journal of the European Society for Emergency Medicine, Vol. 11, No. 5, 10.2004, p. 259-264.

Research output: Contribution to journalArticle

Walsh, Paul ; Cunningham, Padraig ; Rothenberg, Stephen J. ; O'Doherty, Sinead ; Hoey, Hilary ; Healy, Roisin. / An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis. In: European journal of emergency medicine : official journal of the European Society for Emergency Medicine. 2004 ; Vol. 11, No. 5. pp. 259-264.
@article{07486d93d7004d4dbabc62ec835bbf9b,
title = "An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis.",
abstract = "BACKGROUND: Artificial neural networks apply complex non-linear functions to pattern recognition problems. An ensemble is a 'committee' of neural networks that usually outperforms single neural networks. Bronchiolitis is a common manifestation of viral lower respiratory tract infection in infants and toddlers. OBJECTIVE: To train artificial neural network ensembles to predict the disposition and length of stay in children presenting to the Emergency Department with bronchiolitis. METHODS: A specifically constructed database of 119 episodes of bronchiolitis was used to train, validate, and test a neural network ensemble. We used EasyNN 7.0 on a 200 Mhz pentium PC with a maths co-processor. The ensemble of neural networks constructed was subjected to fivefold validation. Comparison with actual and predicted dispositions was measured using the kappa statistic for disposition and the Kaplan-Meier estimations and log rank test for predictions of length of stay. RESULTS: The neural network ensembles correctly predicted disposition in 81{\%} (range 75-90{\%}) of test cases. When compared with actual disposition the neural network performed similarly to a logistic regression model and significantly better than various 'dumb machine' strategies with which we compared it. The prediction of length of stay was poorer, 65{\%} (range 60-80{\%}), but the difference between observed and predicted lengths of stay were not significantly different. CONCLUSION: Artificial neural network ensembles can predict disposition for infants and toddlers with bronchiolitis; however, the prediction of length of hospital stay is not as good.",
author = "Paul Walsh and Padraig Cunningham and Rothenberg, {Stephen J.} and Sinead O'Doherty and Hilary Hoey and Roisin Healy",
year = "2004",
month = "10",
language = "English (US)",
volume = "11",
pages = "259--264",
journal = "European Journal of Emergency Medicine",
issn = "0969-9546",
publisher = "Lippincott Williams and Wilkins",
number = "5",

}

TY - JOUR

T1 - An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis.

AU - Walsh, Paul

AU - Cunningham, Padraig

AU - Rothenberg, Stephen J.

AU - O'Doherty, Sinead

AU - Hoey, Hilary

AU - Healy, Roisin

PY - 2004/10

Y1 - 2004/10

N2 - BACKGROUND: Artificial neural networks apply complex non-linear functions to pattern recognition problems. An ensemble is a 'committee' of neural networks that usually outperforms single neural networks. Bronchiolitis is a common manifestation of viral lower respiratory tract infection in infants and toddlers. OBJECTIVE: To train artificial neural network ensembles to predict the disposition and length of stay in children presenting to the Emergency Department with bronchiolitis. METHODS: A specifically constructed database of 119 episodes of bronchiolitis was used to train, validate, and test a neural network ensemble. We used EasyNN 7.0 on a 200 Mhz pentium PC with a maths co-processor. The ensemble of neural networks constructed was subjected to fivefold validation. Comparison with actual and predicted dispositions was measured using the kappa statistic for disposition and the Kaplan-Meier estimations and log rank test for predictions of length of stay. RESULTS: The neural network ensembles correctly predicted disposition in 81% (range 75-90%) of test cases. When compared with actual disposition the neural network performed similarly to a logistic regression model and significantly better than various 'dumb machine' strategies with which we compared it. The prediction of length of stay was poorer, 65% (range 60-80%), but the difference between observed and predicted lengths of stay were not significantly different. CONCLUSION: Artificial neural network ensembles can predict disposition for infants and toddlers with bronchiolitis; however, the prediction of length of hospital stay is not as good.

AB - BACKGROUND: Artificial neural networks apply complex non-linear functions to pattern recognition problems. An ensemble is a 'committee' of neural networks that usually outperforms single neural networks. Bronchiolitis is a common manifestation of viral lower respiratory tract infection in infants and toddlers. OBJECTIVE: To train artificial neural network ensembles to predict the disposition and length of stay in children presenting to the Emergency Department with bronchiolitis. METHODS: A specifically constructed database of 119 episodes of bronchiolitis was used to train, validate, and test a neural network ensemble. We used EasyNN 7.0 on a 200 Mhz pentium PC with a maths co-processor. The ensemble of neural networks constructed was subjected to fivefold validation. Comparison with actual and predicted dispositions was measured using the kappa statistic for disposition and the Kaplan-Meier estimations and log rank test for predictions of length of stay. RESULTS: The neural network ensembles correctly predicted disposition in 81% (range 75-90%) of test cases. When compared with actual disposition the neural network performed similarly to a logistic regression model and significantly better than various 'dumb machine' strategies with which we compared it. The prediction of length of stay was poorer, 65% (range 60-80%), but the difference between observed and predicted lengths of stay were not significantly different. CONCLUSION: Artificial neural network ensembles can predict disposition for infants and toddlers with bronchiolitis; however, the prediction of length of hospital stay is not as good.

UR - http://www.scopus.com/inward/record.url?scp=16644380249&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=16644380249&partnerID=8YFLogxK

M3 - Article

VL - 11

SP - 259

EP - 264

JO - European Journal of Emergency Medicine

JF - European Journal of Emergency Medicine

SN - 0969-9546

IS - 5

ER -