Abstract
A highly accurate, automated algorithm would facilitate cost-effective screening for asymptomatic atrial fibrillation. This study analyzed a new algorithm and compared it to existing techniques. The incremental benefit of each step in refinement of the algorithm was measured, and the algorithm was compared to other methods using the Physionet atrial fibrillation and normal sinus rhythm databases. When analyzing segments of 21 RR intervals or less, the algorithm had a significantly higher area under the receiver operating characteristic curve (AUC) than the other algorithms tested. At analysis segment sizes of up to 101 RR intervals, the algorithm continued to have a higher AUC than any of the other methods tested, although the difference from the second best other algorithm was no longer significant, with an AUC of 0.9992 with a 95% confidence interval (CI) of 0.9986–0.9998, vs. 0.9986 (CI 0.9978–0.9994). With identical per-subject sensitivity, per-subject specificity of the current algorithm was superior to the other tested algorithms even at 101 RR intervals, with no false positives (CI 0.0–0.8%) vs. 5.3% false positives for the second best algorithm (CI 3.4–7.9%). The described algorithm shows great promise for automated screening for atrial fibrillation by reducing false positives requiring manual review, while maintaining high sensitivity.
Similar content being viewed by others
References
Bardy H, Klein. External atrial defibrillator and method for personal termination of atrial fibrillation. US Patent 7,085,601 Aug 1 2006.
Colilla, S., A. Crow, W. Petkun, D. E. Singer, T. Simon, and X. Liu. Estimates of current and future incidence and prevalence of atrial fibrillation in the U.S. Adult population. Am. J. Cardiol. 112(8):1142–1147, 2013.
Duverney, D., J. M. Gaspoz, V. Pichot, F. Roche, R. Brion, A. Antoniadis, and J. C. Barthélémy. High accuracy of automatic detection of atrial fibrillation using wavelet transform of heart rate intervals. Pacing Clin. Electrophysiol. 25(4 Pt 1):457–462, 2002.
Gage, B. F., A. D. Waterman, W. Shannon, M. Boechler, M. W. Rich, and M. J. Radford. Validation of clinical classification schemes for predicting stroke: results from the national registry of atrial fibrillation. JAMA 285(22):2864–2870, 2001.
Glass L, Tateno K. Method and system for detection of cardiac arrhythmia. US Patent 7,120,485 Oct 10 2006.
Goldberger, A. L., L. A. N. Amaral, L. Glass, J. M. Hausdorff, P Ch Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E. Stanley. PhysioBank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215-2, 2000.
Hanley, J. A., and B. J. McNeil. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36, 1982.
Larburu N, Lopetegi T, Romero I. Comparative study of algorithms for atrial fibrillation detection. Comput. Cardiol.:265–268, 2011.
Linker D. T. Long-term monitoring for detection of different heart rhythms. US Patent 8,326,407 Dec 4 2012.
Linker DT. Long-term monitoring for detection of atrial fibrillation. US Patent 7,630,756 Dec 8 2009.
Rho, R. W., and R. L. Page. Asymptomatic Atrial Fibrillation. Prog. Cardiovasc. Dis. 48(2):79–87, 2005.
Tateno, K., and L. Glass. Automatic detection of atrial fibrillation using the coefficient of variation and density histograms of RR and deltarr intervals. Med Biol Eng Comput 39(6):664–667, 2001.
Weisel J. Method of and apparatus for detecting atrial fibrillation. US Patent 7,020,514 Mar 28 2006.
Acknowledgments
This work was supported in part by the National Heart, Lung and Blood Institute at the National Institutes of Health [R41 HL 090106-01A1].
Conflict of Interest
David Linker holds patents on the methods of automated atrial fibrillation detection described, and is a founder and board member of, stockholder in, and consultant to Cardiac Insight, Inc., a manufacturer of a long-term ambulatory ECG monitor, which has licensed the patents.
Human and Animal Studies
This study used only historical, de-identified ambulatory monitor recordings that are publicly available, and is therefore exempt. No animals were used in this research.
Author information
Authors and Affiliations
Corresponding author
Additional information
Associate Editor Ajit P. Yoganathan oversaw the review of this article.
Rights and permissions
About this article
Cite this article
Linker, D.T. Accurate, Automated Detection of Atrial Fibrillation in Ambulatory Recordings. Cardiovasc Eng Tech 7, 182–189 (2016). https://doi.org/10.1007/s13239-016-0256-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13239-016-0256-z