Limits...
Prediction models in the design of neural network based ECG classifiers: a neural network and genetic programming approach.

Nugent CD, Lopez JA, Smith AE, Black ND - BMC Med Inform Decis Mak (2002)

Bottom Line: The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop.For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047).That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.

View Article: PubMed Central - HTML - PubMed

Affiliation: Medical Informatics Research Group, Faculty of Informatics, University of Ulster at Jordanstown, BT37 0QB, Northern Ireland. cd.nugent@ulst.ac.uk

ABSTRACT

Background: Classification of the electrocardiogram using Neural Networks has become a widely used method in recent years. The efficiency of these classifiers depends upon a number of factors including network training. Unfortunately, there is a shortage of evidence available to enable specific design choices to be made and as a consequence, many designs are made on the basis of trial and error. In this study we develop prediction models to indicate the point at which training should stop for Neural Network based Electrocardiogram classifiers in order to ensure maximum generalisation.

Methods: Two prediction models have been presented; one based on Neural Networks and the other on Genetic Programming. The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop. Training and testing of the models was based on the results from 44 previously developed bi-group Neural Network classifiers, discriminating between Anterior Myocardial Infarction and normal patients.

Results: Our results show that both approaches provide close fits to the training data; p = 0.627 and p = 0.304 for the Neural Network and Genetic Programming methods respectively. For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047).

Conclusions: The approaches provide reverse engineering solutions to the development of Neural Network based Electrocardiogram classifiers. That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.

Show MeSH

Related in: MedlinePlus

Comparison between actual and predicted values for the GP based prediction model for training data.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC65522&req=5

Figure 3: Comparison between actual and predicted values for the GP based prediction model for training data.

Mentions: Figures 2 and 3 indicate the prediction capabilities of both models following training. These graphs indicate the predicted epoch cycles from the NN and the GP models and actual points at which the BGNN attained maximum performance.


Prediction models in the design of neural network based ECG classifiers: a neural network and genetic programming approach.

Nugent CD, Lopez JA, Smith AE, Black ND - BMC Med Inform Decis Mak (2002)

Comparison between actual and predicted values for the GP based prediction model for training data.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC65522&req=5

Figure 3: Comparison between actual and predicted values for the GP based prediction model for training data.
Mentions: Figures 2 and 3 indicate the prediction capabilities of both models following training. These graphs indicate the predicted epoch cycles from the NN and the GP models and actual points at which the BGNN attained maximum performance.

Bottom Line: The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop.For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047).That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.

View Article: PubMed Central - HTML - PubMed

Affiliation: Medical Informatics Research Group, Faculty of Informatics, University of Ulster at Jordanstown, BT37 0QB, Northern Ireland. cd.nugent@ulst.ac.uk

ABSTRACT

Background: Classification of the electrocardiogram using Neural Networks has become a widely used method in recent years. The efficiency of these classifiers depends upon a number of factors including network training. Unfortunately, there is a shortage of evidence available to enable specific design choices to be made and as a consequence, many designs are made on the basis of trial and error. In this study we develop prediction models to indicate the point at which training should stop for Neural Network based Electrocardiogram classifiers in order to ensure maximum generalisation.

Methods: Two prediction models have been presented; one based on Neural Networks and the other on Genetic Programming. The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop. Training and testing of the models was based on the results from 44 previously developed bi-group Neural Network classifiers, discriminating between Anterior Myocardial Infarction and normal patients.

Results: Our results show that both approaches provide close fits to the training data; p = 0.627 and p = 0.304 for the Neural Network and Genetic Programming methods respectively. For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047).

Conclusions: The approaches provide reverse engineering solutions to the development of Neural Network based Electrocardiogram classifiers. That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.

Show MeSH
Related in: MedlinePlus