Classification of acute myocardial ischemia by artificial neural network using echocardiographic strain waveforms

Authors:
Eileen M. McMahon;Josef Korinek;Shiro Yoshifuku;Partho P. Sengupta;Armando Manduca;Marek Belohlavek
Affiliations:
Mayo Clinic College of Medicine, 13400 East Shea Boulevard, Scottsdale, AZ 85259, USA;Mayo Clinic College of Medicine, 200 First Street SW, Rochester, MN 55905, USA;Mayo Clinic College of Medicine, 200 First Street SW, Rochester, MN 55905, USA;Mayo Clinic College of Medicine, 13400 East Shea Boulevard, Scottsdale, AZ 85259, USA;Mayo Clinic College of Medicine, 200 First Street SW, Rochester, MN 55905, USA;Mayo Clinic College of Medicine, 13400 East Shea Boulevard, Scottsdale, AZ 85259, USA
Venue:
Computers in Biology and Medicine
Year:
2008

Citing 6
Cited 1

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
On the momentum term in gradient descent learning algorithms

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
A fuzzy clustering neural network architecture for classification of ECG arrhythmias

Computers in Biology and Medicine
An ischemia detection method based on artificial neural networks

Artificial Intelligence in Medicine
Stability of steepest descent with momentum for quadratic functions

IEEE Transactions on Neural Networks

Effects of principle component analysis on assessment of coronary artery diseases using support vector machine

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Echocardiographic strain waveforms are highly variable, so their interpretation is experience-dependent and subjective. We tested whether an artificial neural network (ANN) can distinguish between strain waveforms obtained at baseline and during experimentally induced acute ischemia. An open-chest model of coronary occlusion and acute ischemia was used in 14 adult pigs. Strain waveforms were obtained using a GE Vivid 7 ultrasound system. An ANN design was implemented in MATLAB^(R), and backpropagation and ''leave-one-out'' processes were used to train and test it. Specificity of 86% and sensitivity of 87% suggest that ANNs could aid in diagnostic prescreening of echocardiographic strain waveforms.