High Accuracy of Automatic Detection of Atrial Fibrillation Using Wavelet Transform of Heart Rate Intervals

Abstract

Permanent and paroxysmal AF is a risk factor for the occurrence and the recurrence of stroke, which can occur as its first manifestation. However, its automatic identification is still unsatisfactory. In this study, a new mathematical approach was evaluated to automate AF identification. A derivation set of 30 24-hour Holter recordings, 15 with chronic AF (CAF) and 15 with sinus rhythm (SR), allowed the authors to establish specific RR variability characteristics using wavelet and fractal analysis. Then, a validation set of 50 subjects was studied using these criteria, 19 with CAF, 16 with SR, and 15 with paroxysmal AF (PAF); and each QRS was classified as true or false sinus or AF beat. In the SR group, specificity reached 99.9%; in the CAF group, sensitivity reached 99.2%; in the PAF group, sensitivity reached 96.1%, and specificity 92.6%. However, classification on a patient basis provided a sensitivity of 100%. This new approach showed a high sensitivity and a high specificity for automatic AF detection, and could be used in screening for AF in large populations at risk.

Value of Routine Holter Monitoring for the Detection of Paroxysmal Atrial Fibrillation in Patients With Cerebral Ischemic Events

“…Recently, promising results were shown with a computer-derived analysis of heart rate intervals, 15 but few patients were studied, and the setting was not that of CIE patients.…”

Automatic Real Time Detection of Atrial Fibrillation

“…6,17,22,24,26,27 Since there is no uniform depolarization of the atria during AF and consequently no discernible P-waves in the ECG, their absence has been utilized in the detection of AF. However, locating the P-wave fiducial point is very difficult because the low amplitude of the P-wave makes it susceptible to corruption by noise.…”

“…6,24,26,27 Notable exceptions include Duverney et al, 6 Sarkar et al 24 and Tateno and Glass. 26,27 Duverney et al 6 used wavelet transform of the RR time series while the latter used the Kolmogorov-Smirnov test to compare the density histogram of the test RR (and DRR) segment with previously compiled standard density histograms of RR (and DRR) segments during AF. Sarkar et al 24 used the Lorenz distribution of a time series of RR intervals for AF and tachycardia detection for its use in a chronic implantable monitor.…”

“…9,10 Although the accuracy of the study by Duverney et al was high, their results were based on a small database. 6 The main drawback of these algorithms is that they are dependent on the robustness of the training data. For example, if the characteristics of AF are different from those learned in the training data, the accuracy of AF detection is compromised.…”

High accuracy in automatic detection of atrial fibrillation for Holter monitoring

“…The absence of P waves is the most significant marker of AF; however, since locating the P wave fiducial point is often difficult when extensive noise is present, the results relied on this hallmark are moderate to high (73.0% to 91.0%, 71.0% to 80.0%, respectively) (Fukunami et al, 1991;Opolski et al, 1997;Budeus et al, 2003). The methods based on RR intervals are, therefore, preferable, with a higher sensitivity and specificity compared to the former method (93.7% vs. 80.7%, 93.0% vs. 75.7% on average, respectively) (Moody and Mark, 1983;Tateno and Glass, 2001;Duverney et al, 2002;Dash et al, 2009). However, it is important to note that regular RR intervals occur in the presence of an atrioventricular (AV) block or ventricular or AV junctional tachycardia when AF is present (Levy et al, 1998).…”