Related Experiment Video
Updated: Aug 22, 2026
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
An artificial neural network ensemble to predict disposition and length of stay in children presenting with
Paul Walsh1, Padraig Cunningham, Stephen J Rothenberg
1Department of Emergency Medicine, Kern Medical Center, Bakersfield, CA 93305, USA. yousentwhohome@netscape.net
Insights
Artificial neural network ensembles accurately predict disposition for infants and toddlers with bronchiolitis. However, predicting length of hospital stay using these models remains less precise.
Area of Science:
- Artificial Intelligence
- Machine Learning
- Pediatric Medicine
Background:
- Bronchiolitis is a common viral respiratory infection in infants and toddlers.
- Artificial neural networks (ANNs) excel at complex pattern recognition.
- Ensembles of ANNs often surpass individual network performance.
Purpose of the Study:
- To develop and evaluate ANN ensembles for predicting patient disposition.
- To forecast the length of stay for pediatric patients with bronchiolitis in the Emergency Department.
Main Methods:
- A database of 119 bronchiolitis cases was used for training, validation, and testing.
- EasyNN 7.0 software was utilized on a Pentium PC.
- Fivefold cross-validation and statistical comparisons (kappa, Kaplan-Meier) were employed.
Main Results:
- ANN ensembles achieved 81% accuracy in predicting patient disposition.
- Performance was comparable to logistic regression and superior to baseline methods.
- Length of stay prediction accuracy was 65%, with no significant difference between observed and predicted values.
Conclusions:
- ANN ensembles demonstrate efficacy in predicting disposition for pediatric bronchiolitis cases.
- Predicting the length of hospital stay for these patients requires further refinement.
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.
