You are here

Automated Detection of Atrial Fibrillation using R-R intervals and multivariate based classification

Authors: 

Alan Kennedy, Dewar Finlay, Daniel Guldenring, Raymond Bond, James McLaughlin, Kieran Moran

Publication Type: 
Refereed Original Article
Abstract: 
Automated detection of AF from the electrocardiogram (ECG) still remains a challenge. In this study we investigated two multivariate based classification techniques, Random Forests (RF) and k-nearest neighbor (k − nn), for improved automated detection of AF from the ECG. We have compiled a new database from ECG data taken from existing sources. R-R intervals were then analyzed using four previously described R-R irregularity measurements: (1) The coefficient of sample entropy (CoSEn) (2) The coefficient of variance (CV) (3) Root mean square of the successive differences (RMSSD) and (4) median absolute deviation (MAD). Using outputs from all four R-R irregularity measurements RF and k − nn models were trained. RF classification improved AF detection over CoSEn with overall specificity of 80.1% vs. 98.3% and positive predictive value of 51.8% vs. 92.1% with a reduction in sensitivity, 97.6% vs. 92.8%. k − nn also improved specificity and PPV over CoSEn however the sensitivity of this approach was considerably reduced (68.0%).
Digital Object Identifer (DOI): 
10.1016/j.jelectrocard.2016.07.033
Publication Status: 
Published
Date Accepted for Publication: 
Monday, 1 August, 2016
Publication Date: 
12/08/2016
Journal: 
Journal of Electrocardiology
Volume: 
49
Issue: 
6
Pages: 
871
Research Group: 
Institution: 
Dublin City University (DCU)
Open access repository: 
Yes