Search

Although radio frequency ablation is the most effective treatment for atrial fibrillation (AF), there is still a high recurrence rate. The purpose of this paper was to initially assess the probability of the recurrence of AF based on the preoperative body surface potential mapping (BSPM) signals, in other words, to predict the efficiency of ablation and assist physicians in developing more effective treatment options. At present, deep learning methods based on convolutional neural networks (CNNs) do not require complex mathematical abstractions or manual interventions; thus, higher computation efficiency can be obtained in such research. However, the use of the fully connected multi-layer perceptron (MLP) algorithms has shown low classification performance. This paper proposes an improved CNN algorithm (CNN-SVM method) for the recurrence classification in AF patients by combining with the support vector machine (SVM) architecture. The algorithm is validated on the preoperative AF signals of 14 patients for classification. All postoperative patients are followed up for one year; ten of them remain in sinus rhythm, whereas the other four turn back to AF. The ECG data for these patients are obtained through the 128-Lead BSPM system. The results show that the proposed CNN-SVM method can automatically extract the characteristic information through the CNN network. The constructed model ultimately achieved an accuracy of 96%, a sensitivity of 88%, and a specificity of 96%. It is concluded that the CNN-SVM method solves the drawbacks of MLP only for separating linear data. It improves the overall performance of AF recurrence classification, thereby providing a valuable reference for doctors to develop personalized treatment plans.

Atrial fibrillation (AF) is a common clinical arrhythmia with a lifetime risk and has become an attractive topic of clinical research and health management. Although the 12-lead classical ECG configuration is adequate for the detection of AF, its configuration is suboptimal for constructing surface potential mapping or extracting other diagnostic features during AF. Body surface potential mapping (BSPM) has a broad application prospect in AF study, but the electrode wiring is complicated and the hardware cost is high. This paper proposes a method to improve the performance of leads selection algorithm from a 128-lead BSPM system with equidistantly spaced electrodes. 128-lead BSPM data obtained from 8 AF patients were used in the study. Leads selection was performed by a sequential selection based on an adapted Botteron’s approach and multiple linear regression. The result showed that the proposed method has significant improvement on the performance of the accurate reconstruction of dominant frequency on the patient-specific dataset. The proposed method may not only improve the performance on the spectrum characteristic but also effectively improve the performance of time domain criteria when the number of selected leads is above 12.

Atrial fibrillation (AF) is one of the most common arrhythmias. The automatic AF detection is of great clinical significance but at the same time it remains a big problem to researchers. In this study, a novel deep learning method to detect AF was proposed. For a 10 s length single lead electrocardiogram (ECG) signal, the continuous wavelet transform (CWT) was used to obtain the wavelet coefficient matrix, and then a convolutional neural network (CNN) with a specific architecture was trained to discriminate the rhythm of the signal. The ECG data in multiple databases were divided into 4 classes according to the rhythm annotation: normal sinus rhythm (NSR), atrial fibrillation (AF), other types of arrhythmia except AF (OTHER), and noise signal (NOISE). The method was evaluated using three different wavelet bases. The experiment showed promising results when using a Morlet wavelet, with an overall accuracy of 97.56%, an average sensitivity of 97.56%, an average specificity of 99.19%. Besides, the area under curve (AUC) value is 0.9983, which showed that the proposed method was effective for detecting AF.

Objective Atrial fibrillation inducibility has recently been shown to be associated with the increased clinical recurrence after ablation. Previous studies have identified unstable sinus rhythm before the occurrence of paroxysmal AF, yet earlier subtle changes, related to AF inducibility, are less be investigated. The purposed of this study is to predict AF inducibility, here we established a controllable canine model and prepared various sinus rhythms with different AF inducibility to study atrial electrophysiological changes. Methods The data were derived from acetylcholine induced acute canine AF models (n = 5, data samples = 90) through epicardial mapping system using 64 electrodes attached to the left and right atrial appendages. Signal preprocessing consists of three steps: noise reduction, removal of ventricular artifact and extraction of activation time (AT). Two classifiers based on activating rule and spatiotemporal features, visualized by network mapping, were established by binary logical regression analysis. Results The sensitivity, specificity and accuracy of activation analysis are 83.30%, 91.70% and 87.80% respectively, while those of spatiotemporal analysis are apparently increased to 97.60%, 93.80% and 95.56%. We observed that the atria (in sinus rhythm) with more disordered electrophysiological activity was more vulnerable to AF. Conclusion The high accuracies indicate the feasibility of AF inducibility prediction using sinus rhythm electrocardiogram, especially with the aid of superior spatiotemporal analysis. Significance To our knowledge, this is the first study that demonstrates the possibility of predicting AF inducibility using network mapping. With this study, accurate AF inducibility forecasting may help to evaluate the recurrence of AF after ablation.