Sample Entropy in Electrocardiogram During Atrial Fibrillation

Atrial fibrillation (AF) is an arrhythmia commonly encountered in clinical practice. There is a high risk of thromboembolism in patients with AF. Nonlinear analyses such as electroencephalogram (EEG), electrocardiogram (ECG), and respiratory movement have been used to quantify biological signals, and sample entropy (SampEn) has been employed as a statistical measure to evaluate complex systems. In this study, we examined the values of SampEn in ECG signals for patients with and without AF to measure the regularity and complexity.

ECG signals of lead II were recorded from 34 subjects without arrhythmia and 15 patients with chronic AF in a supine position. The ECG signals were converted into time-series data and SampEn was calculated.

The SampEn values for the group without arrhythmia were 0.252 ± 0.114 [time lag (τ) = 1] and 0.533 ± 0.163 (τ = 5), and those for the chronic AF group were 0.392 ± 0.158 (τ = 1) and 0.759 ± 0.246 (τ = 5). The values of SampEn were significantly higher in the group with chronic AF than in the group without arrhythmia (P < 0.01 for τ = 1, P < 0.004 for τ = 5). The constructed three-dimensional vectors were plotted in time-delayed three-dimensional space. We used time lags of τ = 5 and τ = 1. The shape of the loops of the three-dimensional space was better for τ = 5.

The values of SampEn from ECG for chronic AF patients were higher than for subjects without arrhythmia, suggesting greater complexity for the time-series from chronic AF patients. SampEn is considered a new index for evaluating complex systems in ECG.