Detection of cardiac arrhythmias using a damped exponential modeling algorithm

Author

Chen, Szi-Wen ; Clarkson, Peter M.

Author_Institution

Biomed. Eng. Center, Ohio State Univ., Columbus, OH, USA

Volume

3

fYear

1996

fDate

7-10 May 1996

Firstpage

1775

Abstract

We describe a new approach for the discrimination among ventricular fibrillation (VF), ventricular tachycardia (VT) and superventricular tachycardia (SVT) based on a damped exponential (DE) modeling algorithm. Two features, dubbed energy fractional factor (EFF) and predominant frequency (PF), were derived from the DE model. Classification task is achieved by performing a two-stage process using the EFF and PF indicators. Tests conducted using 91 episodes drawn from the MIT-BIH database produced total predictive accuracy of (SVT,VF,VT)=(95%,96%,98%)

Keywords

electrocardiography; medical signal processing; pattern classification; signal detection; MIT-BIH database; cardiac arrhythmias detection; damped exponential modeling algorithm; energy fractional factor; predictive accuracy; predominant frequency; superventricular tachycardia; tests; ventricular fibrillation; ventricular tachycardia; Accuracy; Biomedical engineering; Cardiac disease; Covariance matrix; Electrocardiography; Fibrillation; Frequency estimation; Parameter estimation; Spatial databases; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.544210

Filename

544210