Existing arrhythmia classification methods usually use manual selection of electrocardiogram (ECG) signal features, so that the feature selection is subjective, and the feature extraction is complex, leaving the classification accuracy usually affected. Based on this situation, a new method of arrhythmia automatic classification based on discriminative deep belief networks (DDBNs) is proposed. The morphological features of heart beat signals are automatically extracted from the constructed generative restricted Boltzmann machine (GRBM), then the discriminative restricted Boltzmann machine (DRBM) with feature learning and classification ability is introduced, and arrhythmia classification is performed according to the extracted morphological features and RR interval features. In order to further improve the classification performance of DDBNs, DDBNs are converted to deep neural network (DNN) using the Softmax regression layer for supervised classification in this paper, and the network is fine-tuned by backpropagation. Finally, the Massachusetts Institute of Technology and Beth Israel Hospital Arrhythmia Database (MIT-BIH AR) is used for experimental verification. For training sets and test sets with consistent data sources, the overall classification accuracy of the method is up to 99.84% ± 0.04%. For training sets and test sets with inconsistent data sources, a small number of training sets are extended by the active learning (AL) method, and the overall classification accuracy of the method is up to 99.31% ± 0.23%. The experimental results show the effectiveness of the method in arrhythmia automatic feature extraction and classification. It provides a new solution for the automatic extraction of ECG signal features and classification for deep learning.
Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.
ObjectiveTo compare the therapeutic effect of dual-chamber pacing (DDD) and ventricular single-chamber pacing (VVI) on arrhythmia via systematic evaluation. MethodsWith the method of Cochrane system evaluation, we searched Medline, Embase, CNKI, PubMed and Wanfang database (the searching time was up to June 30, 2016) for randomized controlled trials comparing DDD with VVI treatingcardiac arrhythmias. Meta analysis was performed using RevMan5.3 software. ResultsWe collected 12 randomized controlled trials of DDD and VVI pacing treating cardiac arrhythmia including 1 704 patients, but the quality of the studies were not good. The results of Meta analysis showed that:compared with VVI pacing mode, DDD pacing mode reduced the risk of atrial fibrillation[RR=0.36, 95%CI (0.22, 0.59), P < 0.000 1]; besides, it reduced the left atrial diameter[SMD=-0.43, 95%CI (-0.68, -0.17), P=0.001], the left ventricular end diastolic dimension[SMD=-0.33, 95%CI (-0.61, -0.05), P=0.02] and increased the left ventricular ejection fraction[SMD=1.03, 95%CI (0.49, 1.57), P=0.000 2]. ConclusionsComparing DDD with VVI on the treatment of cardiac arrhythmia in patients with cardiac arrhythmia, DDD pacing can reduce the incidence of atrial fibrillation and thrombosis, enhance heart function and improve blood supply. But because of the low quality of the included studies, the curative effect cannot be confirmed, and more randomized controlled trials with high quality needs to be carried out in the future.
Objective To evaluate the feasibility of imaging the rat cardiac conduction system (CCS) using transaortic antegrade perfusion of Alexa Fluor 633-labeled antibodies targeting hyperpolarization-activated cyclic nucleotide-gated cation channel 4 (HCN4) and connexin (Cx). The study also sought to optimize antibody dosage, perfusion duration, and assess the photostability of the dye. Methods Ex vivo rat heart model with transaortic antegrade perfusion was established using 33 male SPF-grade Sprague-Dawley (SD) rats. Primary and secondary antibody solutions were sequentially perfused in an antegrade manner. After perfusion for predetermined durations, the atrioventricular junction was observed, and the fluorescence intensity of the corresponding area was recorded. Five dose-gradient groups (n=3 rats/group), five perfusion time-gradient groups (n=3 rats/group), and ten continuous LED light exposure time-gradient groups (using 3 rats prepared with a fixed dose and time) were established to observe and record regional fluorescence intensity. Standard immunofluorescence staining was performed on both paraffin and frozen sections for comparative histological analysis. Results A region of aggregated red fluorescent signal was observed in the atrioventricular junction. Following semi-quantitative fluorescence intensity analysis of HCN4/Cx43 and validation through comparative histology, this structure was identified as the atrioventricular node (AVN) region. The AVN-to-background fluorescence intensity ratio showed no statistically significant differences among groups with increasing antibody dosage (P>0.05). The ratio increased with longer antibody perfusion times. Furthermore, no statistically significant differences in the ratio were observed among groups with extended light exposure (P>0.05). Conclusion Transaortic antegrade perfusion of fluorescently labeled antibodies can successfully image the AVN within the CCS of ex vivo rat hearts. Increasing the antibody dosage does not significantly improve the AVN imaging effect. Longer antibody perfusion time results in better imaging quality of the AVN. The fluorescent dye maintains sufficient visualization of the AVN even after prolonged (8 h) exposure to light.
Objective To evaluate the efficacy and safety of Shen Song Yang Xin Capsule for cardiac arrhythmia. Methods Randomized controlled trials (RCTs) were searched from the following electronic databases: WanFang, CNKI, CBM, VIP, PubMed, and The Cochrane Library. Quality assessment and data extraction were conducted by two reviewers independently. Disagreement was resolved through discussion. All data were analyzed by using RevMan 5.0 software. Results Thirteen studies involving 1896 participants were included. The results of meta-analyses showed that compared with the control group, a) efficacy: Shen Song Yang Xin Capsule was superior to mexiletine (OR=2.96, 95%CI 1.79 to 4.87), and propafenone (OR=2.41, 95%CI 1.60 to 3.62), but was not superior to miodarone (OR=1.25, 95%CI 0.88 to 1.71); b) safety: Shen Song Yang Xin Capsule was superior to propafenone and miodarone in reducing the incidence of cardiac arrhythmia (OR=0.06, 95%CI 0.01 to 0.35; OR=0.05, 95%CI 0.02 to 0.17), but no significant difference was found between the two groups in incidence of gastrointestinal adverse reactions. Conclusion Based on the current studies, Shen Song Yang Xin Capsule is not inferior to the commonly-used anti-arrhythmic medicine at present. It has lower incidence of cardiac arrhythmia, and has no significant difference in the incidence of gastrointestinal adverse reactions compared with western drugs. For the quality restrictions of the included studies, more double blind RCTs with high quality are required to further assess the effects.
Electrocardiogram (ECG) signal is an important basis for the diagnosis of arrhythmia and myocardial infarction. In order to further improve the classification effect of arrhythmia and myocardial infarction, an ECG classification algorithm based on Convolutional vision Transformer (CvT) and multimodal image fusion was proposed. Through Gramian summation angular field (GASF), Gramian difference angular field (GADF) and recurrence plot (RP), the one-dimensional ECG signal was converted into three different modes of two-dimensional images, and fused into a multimodal fusion image containing more features. The CvT-13 model could take into account local and global information when processing the fused image, thus effectively improving the classification performance. On the MIT-BIH arrhythmia dataset and the PTB myocardial infarction dataset, the algorithm achieved a combined accuracy of 99.9% for the classification of five arrhythmias and 99.8% for the classification of myocardial infarction. The experiments show that the high-precision computer-assisted intelligent classification method is superior and can effectively improve the diagnostic efficiency of arrhythmia as well as myocardial infarction and other cardiac diseases.
Objective To investigate the risky factors of ventricular arrhythmias following open heart surgery in patients with giant left ventricle, and offer the basis in order to prevent it’s occurrence. Methods The clinical materials of 176 patients who had undergone the open heart surgery were analyzed retrospectively. There were 44 patients who had ventricular arrhythmia (ventricular arrhythmia group), 132 patients who had no ventricular arrhythmia as contrast (control group). The preoperative clinical data, indexes of types of cardiopathy, ultrasonic cardiogram, electrocardiogram and cardiopulmonary bypass (CPB) etc. were choosed, and tested by using χ2 test,t test and logistic regression to analyse the high endangered factors for incidence of ventricular arrhythmia after open heart surgery. Results Age≥55 years (OR=3.469), left ventricular enddiastolic diameter(LVEDD)≥80 mm (OR=3.927), left ventricular ejection fraction（LVEF）≤55% (OR=2.967), CPB time≥120min(OR=5.170) and aortic clamping time≥80min(OR=4.501) were the independent risk factors of ventricular arrhythmia. Conclusion Ventricular arrhythmia is a severe complication for the patients with giant left ventricle after open heart surgery, and influence the prognosis of the patients. Patient’s age, size of the left ventricle, cardiac function, CPB time and clamping time could influence the incidence of ventricular arrhythmias.
The cardiac conduction system (CCS) is a set of specialized myocardial pathways that spontaneously generate and conduct impulses transmitting throughout the heart, and causing the coordinated contractions of all parts of the heart. A comprehensive understanding of the anatomical characteristics of the CCS in the heart is the basis of studying cardiac electrophysiology and treating conduction-related diseases. It is also the key of avoiding damage to the CCS during open heart surgery. How to identify and locate the CCS has always been a hot topic in researches. Here, we review the histological imaging methods of the CCS and the specific molecular markers, as well as the exploration for localization and visualization of the CCS. We especially put emphasis on the clinical application prospects and the future development directions of non-destructive imaging technology and real-time localization methods of the CCS that have emerged in recent years.
As an important medical electronic equipment for the cardioversion of malignant arrhythmia such as ventricular fibrillation and ventricular tachycardia, cardiac external defibrillators have been widely used in the clinics. However, the resuscitation success rate for these patients is still unsatisfied. In this paper, the recent advances of cardiac external defibrillation technologies is reviewed. The potential mechanism of defibrillation, the development of novel defibrillation waveform, the factors that may affect defibrillation outcome, the interaction between defibrillation waveform and ventricular fibrillation waveform, and the individualized patient-specific external defibrillation protocol are analyzed and summarized. We hope that this review can provide helpful reference for the optimization of external defibrillator design and the individualization of clinical application.
Arrhythmia is a kind of common cardiac electrical activity abnormalities. Heartbeats classification based on electrocardiogram (ECG) is of great significance for clinical diagnosis of arrhythmia. This paper proposes a feature extraction method based on manifold learning, neighborhood preserving embedding (NPE) algorithm, to achieve the automatic classification of arrhythmia heartbeats. With classification system, we obtained low dimensional manifold structure features of high dimensional ECG signals by NPE algorithm, then we inputted the feature vectors into support vector machine (SVM) classifier for heartbeats diagnosis. Based on MIT-BIH arrhythmia database, we clustered 14 classes of arrhythmia heartbeats in the experiment, which yielded a high overall classification accuracy of 98.51%. Experimental result showed that the proposed method was an effective classification method for arrhythmia heartbeats.