Automatic Detection of Short-Term Atrial Fibrillation Segments Based on Frequency Slice Wavelet Transform and Machine Learning Techniques.

Yaru Yue,Ying Xing,Chengdong Chen,Pengkun Liu,Xiaoguang Zhou

doi:10.3390/s21165302

Abstract

Atrial fibrillation (AF) is the most frequently encountered cardiac arrhythmia and is often associated with other cardiovascular and cerebrovascular diseases, such as ischemic heart disease, chronic heart failure, and stroke. Automatic detection of AF by analyzing electrocardiogram (ECG) signals has an important application value. Using the contaminated and actual ECG signals, it is not enough to only analyze the atrial activity of disappeared P wave and appeared F wave in the TQ segment. Moreover, the best analysis method is to combine nonlinear features analyzing ventricular activity based on the detection of R peak. In this paper, to utilize the information of the P-QRS-T waveform generated by atrial and ventricular activity, frequency slice wavelet transform (FSWT) is adopted to conduct time-frequency analysis on short-term ECG segments from the MIT-BIH Atrial Fibrillation Database. The two-dimensional time-frequency matrices are obtained. Furthermore, an average sliding window is used to convert the two-dimensional time-frequency matrices to the one-dimensional feature vectors, which are classified using five machine learning (ML) techniques. The experimental results show that the classification performance of the Gaussian-kernel support vector machine (GKSVM) based on the Bayesian optimizer is better. The accuracy of the training set and validation set are 100% and 93.4%. The accuracy, sensitivity, and specificity of the test set without training are 98.15%, 96.43%, and 100%, respectively. Compared with previous research results, our proposed FSWT-GKSVM model shows stability and robustness, and it could achieve the purpose of automatic detection of AF.

Highlights

Introduction published maps and institutional affilThe mortality rate of cardiovascular diseases (CVDs) has been extremely high [1,2,3].about 422.7 million people in the world suffered from CVDs of different degrees and types, and about 17.92 million patients died due to CVDs in 2015 [1]
Compared with previous research results, our proposed frequency slice wavelet transform (FSWT)-Gaussian-kernel support vector machine (GKSVM) model shows stability and robustness, and it could achieve the purpose of automatic detection of atrial fibrillation (AF)
On the 3 s time-scale, the original ECG signals and denoised ECG signals were, respectively, used as training sets, and support vector machine (SVM), k-nearest neighbor (KNN), bagged tree algorithms were used for training

Summary

Introduction

The mortality rate of cardiovascular diseases (CVDs) has been extremely high [1,2,3]. About 422.7 million people in the world suffered from CVDs of different degrees and types, and about 17.92 million patients died due to CVDs in 2015 [1]. Atrial fibrillation (AF) is a major CVD, affecting over 33.5 million individuals worldwide [4]. The heart rate is as high as 100–160 beats/min when AF attacks. AF has strong associations with other CVDs, such as myocardial infarction (MI) and chronic heart failure (CHF) [6]. Stroke patients with the highest mortality rate are more likely to suffer from AF, which is up to 5 times more likely than the general population [7]. Automatic detection is very helpful for the early treatment of AF and prevention of related complications

Methods

Results

Conclusion