Ventricular Tachyarrhythmia Onset Prediction Based on HRV and Genetic Algorithm
Abstract: Predicting onset of
ventricular tachyarrhythmia provides opportunities to reduce casualties due to sudden
cardiac death. However, the prediction accuracy still needs improvement.
Therefore, we aim to propose a method that can predict the onset of
tachyarrhythmia events with improved accuracy based on heart rate variability
and Support Vector Machine classifier. Fifty percent of sample data from
standard database was used to train the classifier, and the remainder was used
to verify the performance. Five minutes RR intervals immediately prior to
tachyarrhythmia event from each sample data was cropped for ectopic beat
correction and then converted to heart rate. Extraction of time domain,
spectral, non-linear and bispectrum features were performed subsequently.
Furthermore, genetic algorithm was used tosimultaneously optimize the feature
subset and classifier parameters. With the optimization, prediction accuracy of
our proposed method able to outperform previous works with 77.94%, 80.88% and
79.41 % for sensitivity, specificity and accuracy respectively.
Keywords: Heart Rate
Variability, Arrhythmia Prediction, Ventricular Tachyarrhythmia (VTA), Genetic Algorithm,
Bispectrum features
Author: K. H. Boon
Journal Code: jptkomputergg160280
