Using an artificial neural network to detect activations during ventricular fibrillation

Melanie T. Young, Susan M. Blanchard, Mark W. White, Eric Johnson, William M. Smith, Raymond E. Ideker

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Ventricular fibrillation is a cardiac arrhythmia that can result in sudden death. Understanding and treatment of this disorder would be improved if patterns of electrical activation could be accurately identified and studied during fibrillation. A feedforward artificial neural network using backpropagation was trained with the Rule-Based Method and the Current Source Density Method to identify cardiac tissue activation during fibrillation. Another feedforward artificial neural network that used backpropagation was trained with data preprocessed by those methods and the Transmembrane Current Method. Staged training, a new method that uses different sets of training examples in different stages, was used to improve the ability of the artificial neural networks to detect activation. Both artificial neural networks were able to correctly classify more than 92% of new test examples. The performance of both artificial neural networks improved when staged training was used. Thus, artificial neural networks may be useful for identifying activation during ventricular fibrillation. (C) 2000 Academic Press.

Original languageEnglish (US)
Pages (from-to)43-58
Number of pages16
JournalComputers and Biomedical Research
Volume33
Issue number1
DOIs
StatePublished - Jan 1 2000

Fingerprint

Ventricular Fibrillation
Chemical activation
Neural networks
Backpropagation
Sudden Death
Cardiac Arrhythmias
Tissue

All Science Journal Classification (ASJC) codes

  • Medicine (miscellaneous)

Cite this

Using an artificial neural network to detect activations during ventricular fibrillation. / Young, Melanie T.; Blanchard, Susan M.; White, Mark W.; Johnson, Eric; Smith, William M.; Ideker, Raymond E.

In: Computers and Biomedical Research, Vol. 33, No. 1, 01.01.2000, p. 43-58.

Research output: Contribution to journalArticle

Young, Melanie T. ; Blanchard, Susan M. ; White, Mark W. ; Johnson, Eric ; Smith, William M. ; Ideker, Raymond E. / Using an artificial neural network to detect activations during ventricular fibrillation. In: Computers and Biomedical Research. 2000 ; Vol. 33, No. 1. pp. 43-58.
@article{992bf8142db449a98b0c10eabf55b4e5,
title = "Using an artificial neural network to detect activations during ventricular fibrillation",
abstract = "Ventricular fibrillation is a cardiac arrhythmia that can result in sudden death. Understanding and treatment of this disorder would be improved if patterns of electrical activation could be accurately identified and studied during fibrillation. A feedforward artificial neural network using backpropagation was trained with the Rule-Based Method and the Current Source Density Method to identify cardiac tissue activation during fibrillation. Another feedforward artificial neural network that used backpropagation was trained with data preprocessed by those methods and the Transmembrane Current Method. Staged training, a new method that uses different sets of training examples in different stages, was used to improve the ability of the artificial neural networks to detect activation. Both artificial neural networks were able to correctly classify more than 92{\%} of new test examples. The performance of both artificial neural networks improved when staged training was used. Thus, artificial neural networks may be useful for identifying activation during ventricular fibrillation. (C) 2000 Academic Press.",
author = "Young, {Melanie T.} and Blanchard, {Susan M.} and White, {Mark W.} and Eric Johnson and Smith, {William M.} and Ideker, {Raymond E.}",
year = "2000",
month = "1",
day = "1",
doi = "10.1006/cbmr.1999.1530",
language = "English (US)",
volume = "33",
pages = "43--58",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Using an artificial neural network to detect activations during ventricular fibrillation

AU - Young, Melanie T.

AU - Blanchard, Susan M.

AU - White, Mark W.

AU - Johnson, Eric

AU - Smith, William M.

AU - Ideker, Raymond E.

PY - 2000/1/1

Y1 - 2000/1/1

N2 - Ventricular fibrillation is a cardiac arrhythmia that can result in sudden death. Understanding and treatment of this disorder would be improved if patterns of electrical activation could be accurately identified and studied during fibrillation. A feedforward artificial neural network using backpropagation was trained with the Rule-Based Method and the Current Source Density Method to identify cardiac tissue activation during fibrillation. Another feedforward artificial neural network that used backpropagation was trained with data preprocessed by those methods and the Transmembrane Current Method. Staged training, a new method that uses different sets of training examples in different stages, was used to improve the ability of the artificial neural networks to detect activation. Both artificial neural networks were able to correctly classify more than 92% of new test examples. The performance of both artificial neural networks improved when staged training was used. Thus, artificial neural networks may be useful for identifying activation during ventricular fibrillation. (C) 2000 Academic Press.

AB - Ventricular fibrillation is a cardiac arrhythmia that can result in sudden death. Understanding and treatment of this disorder would be improved if patterns of electrical activation could be accurately identified and studied during fibrillation. A feedforward artificial neural network using backpropagation was trained with the Rule-Based Method and the Current Source Density Method to identify cardiac tissue activation during fibrillation. Another feedforward artificial neural network that used backpropagation was trained with data preprocessed by those methods and the Transmembrane Current Method. Staged training, a new method that uses different sets of training examples in different stages, was used to improve the ability of the artificial neural networks to detect activation. Both artificial neural networks were able to correctly classify more than 92% of new test examples. The performance of both artificial neural networks improved when staged training was used. Thus, artificial neural networks may be useful for identifying activation during ventricular fibrillation. (C) 2000 Academic Press.

UR - http://www.scopus.com/inward/record.url?scp=0034009183&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034009183&partnerID=8YFLogxK

U2 - 10.1006/cbmr.1999.1530

DO - 10.1006/cbmr.1999.1530

M3 - Article

VL - 33

SP - 43

EP - 58

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 1

ER -