Volume 13, Issue 1 (2013)
MJEE 2013, 13(1): 1-7 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Riasi A, mohebbi M. Prediction of ventricular fibrillation using complexity analysis of T Wave from surface electrocardiogram. MJEE 2013; 13 (1) :1-7
URL: http://mjee.modares.ac.ir/article-17-4801-en.html
URL: http://mjee.modares.ac.ir/article-17-4801-en.html
1- M.Sc. Student, K. N. Toosi University of Technology, Biomedical Engineering group, Tehran, Iran,
2- Assistant Professor, K. N. Toosi University of Technology, Biomedical Engineering group, Tehran, Iran,
2- Assistant Professor, K. N. Toosi University of Technology, Biomedical Engineering group, Tehran, Iran,
Abstract: (5250 Views)
Ventricular Fibrillation (VF) is the major cause of triggering sudden cardiac death (SCD). Efficient prediction of ventricular fibrillation is very important for clinical purpose, as this is the most serious cardiac rhythm disturbance and can be life threatening. A reliable predictor of an imminent episode of VF, could be incorporated in an implantable cardioverter defibrillator (ICD) would be capable of delivering preventive therapy. The aim of this study is to investigate the possibility of predicting VF from surface electrocardiogram (ECG) signal by beat to beat tracing of the signal and using a dynamic thresholding method. As VF arises from the lower pumping chambers of the heart (ventricles), it is expected to find some changes in the ventricular activity part of the ECG signal before its occurrence. In this paper, we focused on the T-wave of ECG signal which shows the repolarization of ventricles and tried to present an online predictor by finding an entropy-based pattern in T-waves of ECG signal that can effectively maps the irregularity of this wave before VF. We have also used an Empirical Mode Decomposition (EMD) method to reduce the high frequency noises of T-waves before predictive index extraction in each beat. We found that proposed predictive pattern can be considered as a useful index for probability occurrence of VF. It reached the sensitivity of 89% and specificity of 95% in online VF prediction method. Presented method is simple, computationally fast and has high prediction quality and hence is well suited for real time implementation.
Keywords: Keywords-Ventricular Fibrillation, Prediction index, Approximate Entropy, Empirical Mode Decomposition
Received: 2015/12/9 | Accepted: 2013/03/21 | Published: 2017/02/5
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |