CFP last date
20 May 2024
Reseach Article

Automatic Discrimination between NSR, VT and VF

by Nidhi G Sharma, A N Cheeran, Prerana N Gawale
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 93 - Number 16
Year of Publication: 2014
Authors: Nidhi G Sharma, A N Cheeran, Prerana N Gawale
10.5120/16297-6037

Nidhi G Sharma, A N Cheeran, Prerana N Gawale . Automatic Discrimination between NSR, VT and VF. International Journal of Computer Applications. 93, 16 ( May 2014), 9-12. DOI=10.5120/16297-6037

@article{ 10.5120/16297-6037,
author = { Nidhi G Sharma, A N Cheeran, Prerana N Gawale },
title = { Automatic Discrimination between NSR, VT and VF },
journal = { International Journal of Computer Applications },
issue_date = { May 2014 },
volume = { 93 },
number = { 16 },
month = { May },
year = { 2014 },
issn = { 0975-8887 },
pages = { 9-12 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume93/number16/16297-6037/ },
doi = { 10.5120/16297-6037 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:15:52.813556+05:30
%A Nidhi G Sharma
%A A N Cheeran
%A Prerana N Gawale
%T Automatic Discrimination between NSR, VT and VF
%J International Journal of Computer Applications
%@ 0975-8887
%V 93
%N 16
%P 9-12
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Ventricular Tachycardia (VT) and Ventricular Fibrillation(VF) are life-threatening arrhythmias and accurate discrimination between them is a hard task for the cardiologists. This paper aims to automatically discriminate between Normal Sinus Rhythm (NSR), VT and VF to help make a timely decision of delivering an electroshock to the patient to save his life. To do this discriminative information is extracted from the trajectories traced by NSR, VT and VF signals in the state space. Time delay method is used to represent the signal in state space which is then converted into image. Onto this image, several masks are applied which classify the signal by counting the number of pixels flagged. The algorithm is tested on signals from MIT-BIH databases and is developed on Python 2. 7. Experiments carried out give an accuracy rate of 97%. Also the developed algorithm is computationally less complex and hence can be implemented in real-time applications.

References
  1. Othman M A. , et al. , (2012), "Characterization of Ventricular Tachycardia and Fibrillation Using Semantic Mining. " Computer & Information Science 5, no. 5.
  2. Sarvestani R. , et al. , (2009),"VT and VF classification using trajectory analysis. " Nonlinear Analysis: Theory, Methods & Applications71. 12: e55-e61.
  3. Mane R. , et al. , (2013),"Cardiac Arrhythmia Detection By ECG Feature Extraction. " International Journal of Engineering Research and Applications 3, no. 2: 327-332.
  4. Anton A. , et al. , (2007) "Detecting ventricular fibrillation by time-delay methods. " IEEE Trans. Biomed. Eng. 54 (1) 174_177.
  5. Rocha, T. , et al. , (2008),"Phase space reconstruction approach for ventricular arrhythmias characterization. " In Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE, pp. 5470-5473. IEEE.
  6. CU Database, Massachusetts Institute of Technology, [online] available : http://www. physionet. org/physiobank/database/cudb
  7. The MIT-BIH Normal Sinus Rhythm Database, [online] available : http://www. physionet. org/physiobank/database/nsrdb
  8. The MIT-BIH Malignant Ventricular Arrhythmia Database, [online] available : http://www. physionet. org/physiobank/database/vfdb
Index Terms

Computer Science
Information Sciences

Keywords

Normal Sinus Rhythm Python State space Ventricular Fibrillation Ventricular Tachycardia