Detection of atrial fibrillation episodes using SVM

Maryam Mohebbi; Hassan Ghassemian

doi:10.1109/IEMBS.2008.4649119

Detection of atrial fibrillation episodes using SVM

Annu Int Conf IEEE Eng Med Biol Soc. 2008:2008:177-80. doi: 10.1109/IEMBS.2008.4649119.

Authors

Maryam Mohebbi¹, Hassan Ghassemian

Affiliation

¹ Department of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran.

PMID: 19162622
DOI: 10.1109/IEMBS.2008.4649119

Abstract

This paper explains an atrial fibrillation (AF) detection algorithm, which consists of a linear discriminant analysis (LDA) based feature reduction scheme and a support vector machine (SVM) based classifier. Initially nine features were extracted from the input episodes each containing 32 RR intervals by linear and nonlinear methods. Next, to improve the learning efficiency of the classifier and to reduce the learning time, these features are reduced to 4 features by LDA. The performance of the proposed method in discriminating AF episodes was evaluated using MIT-BIH arrhythmia database. The obtained sensitivity, specificity and positive predictivity were 99.07%, 100% and 100%, respectively.

MeSH terms

Algorithms*
Artificial Intelligence*
Atrial Fibrillation / diagnosis*
Diagnosis, Computer-Assisted / methods*
Electrocardiography / methods*
Humans
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity