Effect of ECG episodes on parameters extraction for paroxysmal atrial fibrillation classification

Abstract

Atrial fibrillation is a type of atria arrhythmia which can cause the formation of blood clot in the heart. The blood clot may enlarge or moving to the brain and cause stroke. Therefore, this study monitors the performance of ECG episodes for paroxysmal atrial fibrillation classification. Episode of 2 seconds to 8 seconds were used to observe the performance of electrocardiograph (ECG) signal processing of atrial fibrillation patient classification. Methods of features extraction were based on the concept of describing short-term behaviour of complex physical and biological system, namely second order system (SOS), and with modified algorithm (hybrid with fast-Fourier transform, FFT). Features extracted from the ECG signal of atrial fibrillation patient were defined using three parameters, i.e. natural frequency, forcing input and damping coefficient. A total of twelve parameters were observed. Comparisons of performance between length of ECG episodes were explored for SOS, FFT-SOS and SOS-FFT algorithms. The episode of 4 seconds using SOS algorithm provides the highest accuracy (98 %) during the classification of ECG signal.

ASIC Design of Natural Frequency of ECG Signal for Atrial Fibrillation Detection Module using High-Level Synthesis Approach

“…A previous study has shown the viability of second order system to classify ECG signal between normal sinus rhythm of healthy human and atrial fibrillation patient [15,16]. Therefore this study illustrates the high-level design method to develop atrial fibrillation (AF) digital signal processing applicationspecific module in hardware design.…”

“…This study used algorithm of natural frequency of ECG signal which was derived from second-order system. The selected algorithm was chosen based on previous study to characterize and classify atrial fibrillation and normal sinus rhythm [15,16].…”

Machine Learning Approaches in Atrial Fibrillation Detection

“…The determination of an ECG signal length for the detection of AF using ML can depend on several factors, such as the objectives of the study, and the practical considerations of the machine learning algorithm. The authors of [9] tested various signal lengths for paroxysmal atrial fibrillation classification and got the best results with a 4 s window using the Second-Order System (SOS) algorithm. Another study by [10] employed both 2 s and 5 s windows using Convolutional Neural Network (CNN) and found that the 2 s segments achieved a higher specificity while 5 s segments showed a slightly better overall accuracy and sensitivity.…”

Design and Implementation of an Ultralow-Energy FFT ASIC for Processing ECG in Cardiac Pacemakers

“…The advancements of digital signal sampling and the emergence of discrete Fourier Transform (DFT) enables biomedical researchers to analyze the frequency components of physiological signals and detect concealed properties to identify physical anomalies. Such methods have been particularly effective in analyzing physiological signals such as the electrocardiogram (ECG) [3], [4], [5]. A practical application of the above-mentioned signal analysis can be found inside an implantable cardiac pacemaker, which is a device tasked with continuous monitoring of ECG signals to detect heart rhythm abnormalities [6].…”