Title: Atrial fibrillation detection using support vector machine and electrocardiographic descriptive statistics
Authors: Nuryani Nuryani; Bambang Harjito; Iwan Yahya; Maratus Solikhah; Rifai Chai; Anik Lestari
Addresses: Faculty of Mathematics and Natural Sciences, University of Sebelas Maret, Surakarta 57126, Indonesia ' Faculty of Mathematics and Natural Sciences, University of Sebelas Maret, Surakarta 57126, Indonesia ' Faculty of Mathematics and Natural Sciences, University of Sebelas Maret, Surakarta 57126, Indonesia ' Faculty of Mathematics and Natural Sciences, University of Sebelas Maret, Surakarta 57126, Indonesia ' Centre for Health Technologies, University of Technology, Sydney, Australia ' Faculty of Medicine, University of Sebelas Maret, Surakarta 57126, Indonesia
Abstract: This paper proposes a new technique for detecting atrial fibrillation (AF). The method employs electrocardiographic features and support vector machine (SVM). The features include descriptive statistics of electrocardiographic RR interval. The RR interval is the distance in time between two consecutive R-peaks of electrocardiogram. AF detections using SVM with different electrocardiographic features and different SVM free parameters are explored. Employing SVM with the optimal free parameters and all the proposed electrocardiographic features, we find an AF detection technique with a comparable performance. The best performance obtained by the technique is 98.47% and 97.84%, in terms of sensitivity and specificity.
Keywords: atrial fibrillation; support vector machine; electrocardiogram; RR interval.
DOI: 10.1504/IJBET.2017.085140
International Journal of Biomedical Engineering and Technology, 2017 Vol.24 No.3, pp.225 - 236
Received: 11 Feb 2016
Accepted: 16 May 2016
Published online: 13 Jul 2017 *