Paroxysmal atrial fibrillation recognition based on multi-scale wavelet α-entropy

Abstract

BackgroundThis study proposed an effective method based on the wavelet multi-scale α-entropy features of heart rate variability (HRV) for the recognition of paroxysmal atrial fibrillation (PAF). This new algorithm combines wavelet decomposition and non-linear analysis methods. The PAF signal, the signal distant from PAF, and the normal sinus signals can be identified and distinguished by extracting the characteristic parameters from HRV signals and analyzing their quantification indexes. The original ECG signals for QRS detection and HRV signal extraction are first processed. The features from the HRV signals are extracted as feature vectors using the wavelet multi-scale entropy. A support vector machine-based classifier is used for PAF prediction.ResultsThe performance of the proposed method in predicting PAF episodes is evaluated with 100 signals from the MIT-BIT PAF prediction database. With regard to the dynamics and uncertainty of PAF signals, our proposed method obtains the values of 92.18, 94.88, and 89.48% for the evaluation criteria of correct rate, sensitivity, and specificity, respectively.ConclusionsOur proposed method presents better results than the existing studies based on time domain, frequency domain, and non-linear methods. Thus, our method shows considerable potential for clinical monitoring and treatment.

A Classification and Prediction Hybrid Model Construction with the IQPSO-SVM Algorithm for Atrial Fibrillation Arrhythmia

“…Dozens of features are related to HRV, and different modes of feature training cause differences in model performance. In [ 42 , 43 ], 5 min ECG signals were used for model training. The short ECG sequence contained limited information.…”

Prediction of Paroxysmal Atrial Fibrillation From Complexity Analysis of the Sinus Rhythm ECG: A Retrospective Case/Control Pilot Study

“…Machine-learning methods for PAF detection use retrospective analysis of freely available clinical ECG recordings or clinical databases. These are often based on detection and classification of atrial premature beats and other ECG abnormalities (Thong et al, 2004), or from interval analysis of atrial or ventricular depolarisations (Ghodrati et al, 2008;Mohebbi and Ghassemian, 2012;Xin and Zhao, 2017;Aronis et al, 2018), with specificity and sensitivity ranging between 71-93% and 85-96%, respectively, but requiring recording periods up to 30 min. However, convolutional neural networks achieve accuracy of detection in the range 75-95% using shorter recording periods of detection (Hsieh et al, 2020;Nurmaini et al, 2020).…”

Perspectives on Sex- and Gender-Specific Prediction of New-Onset Atrial Fibrillation by Leveraging Big Data

“…Over the past years, there has been an exponential interest in using various big data sources to further improve the AF risk prediction beyond the traditional AF risk factors (23,24). Specifically, multiple studies have employed AI-enabled algorithms to evaluate new-onset AF prediction by leveraging various big data modalities including the clinical data, ECGs, EHRs, and wearable devices (23)(24)(25)(26)(27)(28)(29)(30)(31)(32)(33)(34)(35)(36)(37)(38)(39)(40)(41)(42). Some of these studies showed that AI-enabled AF prediction models performed similar to or better than established traditional AF prediction models (25,(27)(28)(29)(30).…”