Atrial fibrillation detection by DFA and SDCST methods

2021 ◽  
Vol 16 (3) ◽  
pp. 189-196
Author(s):  
Regis Nunes Vargas ◽  
Antônio Cláudio Paschoarelli Veiga ◽  
Raquel Romes Linhares

Many cardiac disorders were diagnosed by analyzing an electrocardiogram signal, in particular, atrial fibrillation. We join the SDCST method with the Detrended Fluctuation Analysis (DFA) and the backpropagation net to identify atrial fibrillation in one hundred ECG signals obtained from Physionet Challenge 2017 database. The accuracy of the proposed classifier parameter is 97% for the training set and 95% for the test set.

Author(s):  
Jurij Matija Kališnik ◽  
Eva Hrovat ◽  
Alenka Hrastovec ◽  
Viktor Avbelj ◽  
Janez Žibert ◽  
...  

Objective Postoperative atrial fibrillation (POAF) is a frequent complication after heart surgery. It has been shown that cardiac autonomic derangement plays a significant role in the genesis of atrial fibrillation (AF) and that AF might also be promoted by altered repolarization. Thus, the aim of our study was to determine the levels of cardiac autonomic modulation and repolarization properties in patients developing POAF. Methods Seventy-nine patients scheduled for aortic and/or coronary artery bypass grafting surgery with cardiopulmonary bypass were enrolled prospectively. High-resolution 20-minute electrocardiogram recordings were obtained day before surgery to determine P, PR, QT, and QTc intervals, as well as linear (time and frequency domain) and nonlinear heart rate variability parameters (fractal dimension and detrended fluctuation analysis). QTc interval was calculated using Framingham correction. Results Twenty-nine patients developed POAF (AF group), and 50 did not (non-AF group). Groups were similar regarding demographics, surgery type, and perioperative characteristics, except for older age in the AF group. QT and QTc intervals (Framingham) were longer in the AF group [442 (44) vs 422 (28) milliseconds, P = 0.018; and 448 (44) vs 431 (24) milliseconds, P = 0.031 and P = 0.019, respectively]. Time domain heart rate variability parameter PNN50 (percentage of pairs of adjacent NN intervals differing >50 milliseconds) was higher [14% (21%) vs 8% (16%), P = 0.015], and nonlinear parameter detrended fluctuation analysis α2 was lower in the AF group [0.81 (0.21) vs 0.91 (0.20), P = 0.031]. Conclusions Profound cardiac autonomic derangement, suggestive of parasympathetic excessive modulation, exists preoperatively in patients inclined to POAF after cardiac surgery, whereby parameters PNN50 and α2 differentiated the AF from the non-AF group. Prolonged QTc intervals are associated with an increased risk of POAF.


Author(s):  
Javier Gómez-Gómez ◽  
Rafael Carmona-Cabezas ◽  
Ana B. Ariza-Villaverde ◽  
Eduardo Gutiérrez de Ravé ◽  
Francisco José Jiménez-Hornero

Sign in / Sign up

Export Citation Format

Share Document