Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Automated detection of atrial Fibrillation using R-R intervals and multivariate based classification.

Kennedy, Alan and Finlay, Dewar D. and Guldenring, Daniel and Bond, Raymond R. and McLaughlin, James and Moran, Kieran (2016) Automated detection of atrial Fibrillation using R-R intervals and multivariate based classification. Journal of Electrocardiology, 49 (6). pp. 871-876. ISSN 0022-0736

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


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%).

Item Type:Article (Published)
Uncontrolled Keywords:Atrial fibrillation; R-R intervals; Algorithms
Subjects:Medical Sciences > Health
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Science and Health > School of Health and Human Performance
Official URL:
Copyright Information:© 2016 Elsevier
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:European Union’s Horizon 2020 Framework Programme for Research & Innovation Action under Grant no. 643491.
ID Code:21933
Deposited On:18 Aug 2017 09:53 by Thomas Murtagh. Last Modified 11 Oct 2017 12:04

Download statistics

Archive Staff Only: edit this record