Supraventricular Ectopic Beats Research Articles

Late, but Before Schedule-A Bigeminal Rhythm with Blocked Premature Junctional Beats

Premature supraventricular ectopic beats are common findings in ambulatory ECG monitoring. Blocked ectopic beats may occur if the premature beat coincides with the refractory period of the downstream conductive tissues. We report of an uncommon, symptomatic bigeminal rhythm which resulted in an abrupt decrease of the heart rate because of blocked P waves. The blocked P waves appeared uncommonly late in the cardiac cycle because of a very His-near activation site. For anatomic reasons treatment was difficult and the patient received a pacemaker.

Deep Learning Based Patient-Specific Classification of Arrhythmia on ECG signal.

The classification of the heartbeat type is an essential function in the automatical electrocardiogram (ECG) analysis algorithm. The guideline of the ANSI/AAMI EC57 defined five types of heartbeat: non-ectopic or paced beat (N), supraventricular ectopic beat (S), ventricular ectopic beat (V), fusion of a ventricular and normal beat (F), pace beat or fusion of a paced and a normal or beat that cannot be classified (Q). In the work, a deep neural network based method was proposed to classify these five types of heartbeat. After removing the noise from ECG signals by a low-pass filter, the two-lead heartbeat segments with 2-s length were generated on the filtered signals, and classified by an adaptive ResNet model. The proposed method was evaluated on the MIT-BIH Arrhythmia Database with the patient-specific pattern. The overall accuracy was 98.6% and sensitivity of N, S, V, F were 99.4%, 85.4%, 96.6%, 90.6% respectively. Experimental results show that the proposed method achieved a good performance, and would be useful in the clinic practice.

A Real-Time Arrhythmia Heartbeats Classification Algorithm Using Parallel Delta Modulations and Rotated Linear-Kernel Support Vector Machines.

Real-time wearable electrocardiogram monitoring sensor is one of the best candidates in assisting cardiovascular disease diagnosis. In this paper, we present a novel real-time machine learning system for Arrhythmia classification. The system is based on the parallel Delta modulation and QRS/PT wave detection algorithms. We propose a patient dependent rotated linear-kernel support vector machine classifier that combines the global and local classifiers, with three types of feature vectors extracted directly from the Delta modulated bit-streams. The performance of the proposed system is evaluated using the MIT-BIH Arrhythmia database. According to the AAMI standard, two binary classifications are performed and evaluated, which are supraventricular ectopic beat (SVEB) versus the rest four classes, and ventricular ectopic beat (VEB) versus the rest. For SVEB classification, the preferred SkP-32 method's F1 score, sensitivity, specificity, and positive predictivity value are 0.83, 79.3%, 99.6%, and 88.2%, respectively, and for VEB classification, the numbers are 0.92%, 92.8%, 99.4%, and 91.6%, respectively. The results show that the performance of our proposed approach is comparable to that of published research. The proposed low-complexity algorithm has the potential to be implemented as an on-sensor machine learning solution.

Association between excessive supraventricular ectopy and subclinical cerebrovascular disease: a population-based study.

The association between an increased supraventricular ectopic beat (SVEB) and subclinical cerebrovascular disease remains unclear. Given the emerging concept that an increased SVEB is a marker of atrial cardiomyopathy or atherosclerosis burden, we sought to determine whether excessive supraventricular ectopic activity (ESVEA) is associated with a higher burden of subclinical cerebrovascular disease in the middle-aged to older cohort with neither apparent stroke nor atrial fibrillation. We conducted a cross-sectional population-based study of 462 men (mean age, 68.1years) who underwent 24-h Holter electrocardiography and brain magnetic resonance imaging. ESVEA was defined as the presence of >10 SVEBs/h. Subclinical cerebrovascular diseases were defined as silent brain infarct (SBI), white matter hyperintensity (WMH) and intracranial atherosclerotic stenosis (ICAS). The association of ESVEA with the presence of subclinical cerebrovascular diseases was adjusted for potential confounding covariates. A total of 88 (19.0%) participants had ESVEA and 81 (17.5%), 91 (19.7%) and 109 (23.6%) had SBI, WMH and ICAS, respectively. In multivariable-adjusted Poisson regression with robust error variance, ESVEA was associated with the presence of WMH (relative risk, 1.58; 95% confidence interval, 1.06-2.36) and ICAS (relative risk, 1.49; 95% confidence interval, 1.02-2.18), but not with that of SBI (relative risk, 1.32; 95% confidence interval, 0.86-2.01). These associations were consistent when the graded distributions of subclinical cerebrovascular diseases were applied as outcomes in ordinal logistic regression. The ESVEA was independently associated with higher burdens of WMH and ICAS. This suggests that increased SVEBs might improve risk stratification of individuals at high risk of subclinical cerebrovascular disease and consequently apparent ischaemic stroke.

Key technologies in digital breast tomosynthesis system:theory, design, and optimization

To develop a digital breast tomosynthesis (DBT) imaging system with optimizes imaging chain. Based on 3D tomography and DBT imaging scanning, we analyzed the methods for projection data correction, geometric correction, projection enhancement, filter modulation, and image reconstruction, and established a hardware testing platform. In the experiment, the standard ACR phantom and high-resolution phantom were used to evaluate the system stability and noise level. The patient projection data of commercial equipment was used to test the effect of the imaging algorithm. In the high-resolution phantom study, the line pairs were clear without confusing artifacts in the images reconstructed with the geometric correction parameters. In ACR phantom study, the calcified foci, cysts, and fibrous structures were more clearly defined in the reconstructed images after filtering and modulation. The patient data study showed a high contrast between tissues, and the lesions were more clearly displayed in the reconstructed image. This DBT imaging system can be used for mammary tomography with an image quality comparable to that of commercial DBT systems to facilitate imaging diagnosis of breast diseases.

Polyscore of Non-invasive Cardiac Risk Factors.

Non-invasive risk stratification of cardiac patients has been the subject of numerous studies. Most of these investigations either researched unique risk predictors or compared the predictive power of different predictors. Fewer studies suggested a combination of a small number of non-invasive indices to increase the accuracy of high-risk group selection. To advance non-invasive risk assessment of cardiac patients, we propose a combination score (termed the Polyscore) of seven different cardiac risk stratifiers that predominantly quantify autonomic cardiovascular control and regulation, namely the slope of heart rate turbulence, deceleration capacity of heart rate, non-invasively assessed baroreflex sensitivity, resting respiration frequency, expiration triggered sinus arrhythmia, post-ectopic potentiation of systolic blood pressure, and frequency of supraventricular and ventricular ectopic beats. These risk stratification tests have previously been researched and their dichotomies defining abnormal results have been derived from previous reports. The Polyscore combination was defined as the number of positive tests among these seven risk predictors, giving a numerical scale which ranges from 0 (all tests normal) to 7 (all tests abnormal). The Polyscore was tested in a population of 941 contemporarily treated survivors of acute myocardial infarction (median age 61 years, 182 females) of whom 72 (7.65%) died during a 5-year follow-up. In these patients, all the risk predictors combined in the Polyscore were assessed during in-hospital 30-min simultaneous non-invasive recordings of high-frequency orthogonal electrocardiogram, continuous blood pressure and respiration. Compared to Polyscore 0 stratum, the hazard ratios of mortality during follow-up increased almost exponentially in strata 1 through 7 (vs. stratus 0, the hazard ratios were 1.37, 1.96, 7.03, 15.0, 35.7, 48.2, and 114, in strata 1 to 7, respectively; p < 0.0001). This allowed selecting low-risk (Polyscore ≤ 2), intermediate risk (Polyscore 3 or 4) and high-risk (Polyscore ≥ 5) sub-groups of the population that differed greatly in the Kaplan–Meier probabilities of mortality during follow-up. Since the Polyscore was derived from recordings of only 30-min duration, it can be reasonably applied in different clinical situations including population-wide screening. We can therefore conclude that the Polyscore is a reasonable method for cardiac risk stratification that is ready for prospective validation in future independent studies.

Automated Heartbeat Classification Exploiting Convolutional Neural Network With Channel-Wise Attention

Long-term Electrocardiogram (ECG) analysis has become a common means of diagnosing cardiovascular diseases. In order to reduce the workload of cardiologists and accelerate diagnosis, an automated patient-specific heartbeat classification method based on a customized convolutional neural network (CNN) is proposed in this paper. The parallel convolutional layers with kernels of different receptive fields in the network are responsible for extracting multi-spatial deep features of the heartbeats, and the channel-wise attention module is adopted to selectively emphasize the informative features, which are beneficial to distinguish different classes of beats. To facilitate the extraction and emphasis of the important features, each heartbeat is segmented and stacked to form the multi-channel network input according to the basic temporal characteristics of the main components (P wave, QRS complex, and T wave) in the ECG. Besides, to further improve the network generalization and achieve better performance on various ECG of new patients, a method of intra-record sample clustering is proposed to select the representative heartbeats to construct the training set. The proposed method classifies heartbeats into five classes (normal beat (N), supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), fusion beat (F), and unclassifiable beat (Q)). Validated on the MIT-BIH arrhythmia database, our approach demonstrates performance superior to several state-of-the-art methods. In addition to an average accuracy and specificity of over 99%, this method achieves a sensitivity of 95.4% and a positive predictivity of 97.1% for VEB class, and a sensitivity of 81.1% and a positive predictivity of 90.0% for SVEB class. With high classification performance and pathological heartbeat detection accuracy, the proposed method is promising for clinical device applications.

Automated Heartbeat Classification Using 3-D Inputs Based on Convolutional Neural Network With Multi-Fields of View

A high-performance method of automated heartbeat classification based on Convolutional Neural Network (CNN) is proposed in this paper. To make full use of the electrocardiogram information acquired from different parts of the human body, we present a novel 3-D data structure as the input of the CNN. The 3-D structure consists of multiple feature maps, each of which indicates the information collected from one lead and contains morphological characteristic, RR-interval, and beat-to-beat correlation feature. Besides, atrous spatial pyramid pooling (ASPP) module which uses filters with different resolutions is adopted to extract deep features in multi-fields of view. Validated on the MIT-BIH arrhythmia database, the proposed method yields an overall accuracy of 91.44% in the inter-patient practice. In particular, this method achieves 89.05% and 95.15% in the sensitivities of the supraventricular ectopic beat (SVEB) and ventricular ectopic beat (VEB) classes, respectively. With the high performance in detecting these two pathological classes, this method has potential clinical application.

Automated heartbeat classification and detection of arrhythmia using optimal orthogonal wavelet filters

Abstract Electrocardiogram (ECG) is commonly used to analyze heartbeats. Arrhythmia is a disturbance of the heartbeat that can potentially be lethal. Arrhythmia can be detected by identifying an individual abnormal heartbeat, which can occur in isolation or sequentially. Heartbeats can be classified into five types: non-ectopic (N), supra ventricular ectopic (S), ventricular ectopic (V), fusion (F) and unknown beats (Q). Automated classification of the incidence and pattern of abnormal heartbeats enables arrhythmia detection, triage and life-threatening arrhythmia. Therefore, it is vital to develop a tool for the classification of these classes. ECG signals are contaminated by noise rendering difficulty and challenging to discriminate between different types of heartbeats. In this work, we used noisy as well as denoised (clean) ECG signals to classify heartbeats. Using stop-band energy (SBE) minimized dyadic orthogonal filter bank, wavelet decomposition of the ECG signals was performed. After this, fuzzy entropy, Renyi entropy and fractal dimension features were extracted for easier and accurate classification into the five classes. These features were then fed to classifiers, achieving maximum accuracy (MAAC) of 98%, maximum sensitivity (MASE) of 85.33% and maximum specificity (MASP) of 98.22% for noisy data, and MAAC of 98.1%, MASE of 85.63% and MASP of 98.27% for clean data, with KNN classifier. Our developed system can be used in intensive care units to assist the clinicians to aid in their diagnosis.

Feature Enrichment Based Convolutional Neural Network for Heartbeat Classification From Electrocardiogram

Correct heartbeat classification from electrocardiogram (ECG) signals is fundamental to the diagnosis of arrhythmia. The recent advancement in deep convolutional neural network (CNN) has renewed the interest in applying deep learning techniques to improve the accuracy of heartbeat classification. So far, the results are not very exciting. Most of the existing methods are based on ECG morphological information, which makes deep learning difficult to extract discriminative features for classification. Towards an opposite direction of feature extraction or selection, this paper proceeds along a recent proposed direction named feature enrichment (FE). To exploit the advantage of deep learning, we develop a FE-CNN classifier by enriching the ECG signals into time-frequency images by discrete short-time Fourier transform and then using the images as the input to CNN. Experiments on MIT-BIH arrhythmia database show FE-CNN obtains sensitivity (Sen) of 75.6%, positive predictive rate (Ppr) of 90.1%, and F1 score of 0.82 for the detection of supraventricular ectopic (S) beats. Sen, Ppr, and F1 score are 92.8%, 94.5%, and 0.94, respectively, for ventricular ectopic (V) beat detection. The result demonstrates our method outperforms state-of-the-art algorithms including other CNN based methods, without any hand-crafted features, especially F1 score for S beat detection from 0.75 to 0.82. This FE-CNN classifier is simple, effective, and easy to be applied to other types of vital signs.

Contribution of Holter ECG to the diagnosis of palpitations in Brazzaville (Congo)

To determine the prevalence and the nature of the rhythmic disorders during palpitations. It was about a cross-sectional study, descriptive, conducted to Brazzaville between January 2012 and December 2016. The study related to a consecutive series of 530 patients having carried out 24 h Holter ECG for assessment of palpitations. The sociodemographic parameters of the patients were collected, and the principal indexed rhythmic anomalies. The Lown classification made it possible to evaluate the degree of gravity of the ventricular ectopic beats (VEB) into benign and complex or malignant. There were 225 men (42.5%) and 305 women (57.5%), old on average of 48.7 ± 13.2 years, without difference between the two sexes (49.7 ± 14.6 vs 50.9 ± 13.7 years; P = 0.311). The Holter ECG, prescribed by a cardiologist in 476 cases (89.8%) and by a general practitioner in 54 cases (10.2%), was normal in 360 cases (68%) and pathological in 170 cases (32%). The mean average heart rate (HR) was 76.8 ± 10.7 bpm, the mean minimum HR was 56.5 ± 9.4 bpm, and the mean maximum HR was 116.3 ± 13.1 bpm. The principal recorded anomalies consisted into VEB ( n = 136), supraventricular ectopic beats ( n = 27), paroxysmal atrial fibrillation ( n = 9), non-sustained ventricular tachycardia ( n = 4), sustained ventricular tachycardia and nodal tachycardia in two cases each one. The VEB were isolated ( n = 125), couplets ( n = 38), triplets ( n = 14), and bigeminy ( n = 65). One noted salvos of VEB in 11 cases (8.1%). The VEB were benign in 125 cases (92%), and complex or malignant in 11 cases (8%). This study underlines the interest of 24 h Holter ECG in the diagnosis of palpitations. If the anomalies frequently in question seem benign, others more serious are to be feared in spite of their relative scarcity. Such is the case of atrial fibrillation and the malignant ventricular arrhythmias.

Contribution of Holter ECG in the etiologic diagnosis of the ischemic stroke in Brazzaville (Congo)

To determine the prevalence of the rhythmic disorders during ischemic stroke, and to identify the predictive factors of paroxysmal atrial fibrillation (PAF). It was about a cross-sectional study, descriptive and analytical, conducted to Brazzaville between January 2012 and December 2016. It is related to a consecutive series of 267 patients victims of a transient ischemic attack ( n = 17) or ischemic stroke ( n = 250), documented by cerebral tomodensitometry or brain MRI. All these patients profited from a recording 24 h Holter ECG, carried out within the framework of etiologic research. The principal recorded rhythmic anomalies were indexed, and the logistic regression allowed the identification of the predictive factors of PAF. They were 164 men (61.4%) and 103 women (38.6%), old on average of 60.2 ± 12.1 years. The main cardiovascular risk factors were hypertension (80.1%), diabetes (13.5%), and tobacco use (6.7%). The 24 h Holter ECG, normal in 216 cases (81%), was pathological in 51 cases (19%). The principal recorded anomalies consisted into ventricular ectopic beats ( n = 32), PAF ( n = 7), supraventricular ectopic beats ( n = 5), non-sustained ventricular tachycardia ( n = 4), sustained ventricular tachycardia ( n = 2), and type 2 atrioventricular block ( n = 1). The frequency of PAF was 2.6%. In bivariate analysis, it was not noted correlation between PAF and sex ( P = 0.55), hypertension ( P = 0.42), diabetes ( P = 0.64), and tobacco use ( P = 0.61). In multivariate analysis, only the age was the predictive factor of PAF during ischemic stroke ( P = 0.0134). It comes out from this preliminary study that the emboligenous arrhythmias are relatively rare during ischemic stroke in Brazzaville. PAF, though little attends, remains primarily correlated at the age. Its systematic research at the old subjects contributes to improve the assumption of responsibility.

Yield and consistency of arrhythmia detection with patch electrocardiographic monitoring: The Multi-Ethnic Study of Atherosclerosis

BackgroundPatch electrocardiographic (ECG) monitors permit extended noninvasive ambulatory monitoring. To guide use of these devices, information is needed about their performance. We sought to determine in a large general population sample the acceptability of patch ECG monitors, the yield of arrhythmia detection, and the consistency of findings in participants monitored twice. MethodsIn the Multi-Ethnic Study of Atherosclerosis, 1122 participants completed one or two monitoring episodes using the Zio Patch XT, a single-channel ECG patch monitor capable of recording for 14 days. Recordings were analyzed for atrial fibrillation (AF), atrial flutter, atrioventricular block, pauses, and supraventricular and ventricular ectopy. ResultsThe mean(SD) age at the time of monitoring was 75(8) years, 52% were men, and 15% had a prior history of clinically-recognized AF/flutter. The median monitoring duration was 13.8 days. Among 804 participants with no prior clinical history of AF/flutter and at least 12 days of monitoring on a single device, AF/flutter was detected in 32 (4.0%); in 38% of these, AF/flutter was first detected during days 3 through 12 of monitoring. In participants monitored twice, findings from the two devices showed excellent agreement for supraventricular and ventricular ectopic beats per hour, but only fair agreement for high-grade atrioventricular block and pauses of >3 s duration. ConclusionsIn a general population of older individuals, new diagnoses of AF/flutter were made in 4.0% of participants without a prior history. A single monitoring episode accurately estimated rates of supraventricular and ventricular ectopy.

Patient-specific ECG classification by deeper CNN from generic to dedicated

Abstract This paper presents a new mechanism which is more effective for wearable devices to classify patient-specific electrocardiogram (ECG) heartbeats. In our method, a Generic Convolutional Neural Network (GCNN) is trained first using a large number of heartbeats without distinguishing patients. Based on the GCNN, fine-tuning technique is applied to modify the GCNN to a Tuned Dedicated CNN (TDCNN) for the corresponding individual. Notably, only the GCNN instead of common training data is required to be stored into wearable devices. Moreover, only fine-tuning with several seconds rather than dozens of minutes is needed before the TDCNN is used to monitor the long-term ECG signals in clinical. To accelerate the ECG classification, only the original ECG heartbeat is input to the CNN without other extended information from the neighbor heartbeats or FFT representation. A deeper CNN architecture with small-scale convolutional kernels is adopted to improve the speed and accuracy for classification. With deeper CNN, hierarchical features can be extracted to help improve the accuracy of ECG classification. The state-of-the-art performance on efficiency and accuracy for ECG classification over MIT-BIH dataset is achieved by the proposed method. The effectiveness and superiority for detecting ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB) events are demonstrated. The proposed mechanism of fine-tuning the GCNN to TDCNN improves the efficiency for training patient-specific CNN classifier. Because of the computational efficiency of fine-tuning, ECG diagnosis and heart monitoring can be easily implemented with popular wearable devices in practice.

Arrhythmia Recognition and Classification Using ECG Morphology and Segment Feature Analysis.

In this work, arrhythmia appearing with the presence of abnormal heart electrical activity is efficiently recognized and classified. A novel method is proposed for accurate recognition and classification of cardiac arrhythmias. Firstly, P-QRS-T waves is segmented from ECG waveform; secondly, morphological features are extracted from P-QRS-T waves, and ECG segment features are extracted from the selected ECG segment by using PCA and dynamic time warping(DTW); finally, SVM is applied to the features and automatic diagnosis results is presented. ECG data set used is derived from the MIT-BIH in which ECG signals are divided into the four classes: normal beats(N), supraventricular ectopic beats (SVEBs), ventricular ectopic beats (VEBs) and fusion of ventricular and normal (F). Our proposed method can distinguish N, SVEBs, VEBs and F with an accuracy of 97.80 percent. The sensitivities for the classes N, SVEBs, VEBs and F are 99.27, 87.47, 94.71, and 73.88 percent and the positive predictivities are 98.48, 95.25, 95.22 and 86.09 percent respectively. The detection sensitivity of SVEBs and VEBs has a better performance by combining proposed features than by using the ECG morphology or ECG segment features separately. The proposed method is compared with four selected peer algorithms and delivers solid results.

A novel application of deep learning for single-lead ECG classification

Detecting and classifying cardiac arrhythmias is critical to the diagnosis of patients with cardiac abnormalities. In this paper, a novel approach based on deep learning methodology is proposed for the classification of single-lead electrocardiogram (ECG) signals. We demonstrate the application of the Restricted Boltzmann Machine (RBM) and deep belief networks (DBN) for ECG classification following detection of ventricular and supraventricular heartbeats using single-lead ECG. The effectiveness of this proposed algorithm is illustrated using real ECG signals from the widely-used MIT-BIH database. Simulation results demonstrate that with a suitable choice of parameters, RBM and DBN can achieve high average recognition accuracies of ventricular ectopic beats (93.63%) and of supraventricular ectopic beats (95.57%) at a low sampling rate of 114 Hz. Experimental results indicate that classifiers built into this deep learning-based framework achieved state-of-the art performance models at lower sampling rates and simple features when compared to traditional methods. Further, employing features extracted at a sampling rate of 114 Hz when combined with deep learning provided enough discriminatory power for the classification task. This performance is comparable to that of traditional methods and uses a much lower sampling rate and simpler features. Thus, our proposed deep neural network algorithm demonstrates that deep learning-based methods offer accurate ECG classification and could potentially be extended to other physiological signal classifications, such as those in arterial blood pressure (ABP), nerve conduction (EMG), and heart rate variability (HRV) studies.

A Rare Cause of Supraventricular Ectopic Beats and Angina in a Young Patient

Abstract Introduction: We present the case of a young man with multiple atherosclerotic risk factors and a rare cause of angina and supraventricular ectopic beats. Case presentation: A 35-year-old man with one-year history of stable angina pectoris and supraventricular ectopic beats, without any medication, presented to the emergency room complaining of anterior chest pain that occurs at moderate physical exertion. The rest electrocardiogram, transthoracic echocardiography, and chest X-ray were normal; the exertion stress test was also normal, except for supraventricular ectopic beats (trigeminal rhythm). Due to the intermediate pre-test probability of coronary artery disease, he was evaluated using coronary computed tomography angiography. An anomalous origin of the right coronary artery from the left coronary sinus, with an inter-arterial course and without any atheroma plaques, was observed. During hospitalization the evolution was stable, without complications. The patient was further referred to a cardiac surgery clinic to evaluate the possibility of surgical treatment of this anomaly. Conclusions: Coronary artery anomalies are very rare; however, they present multiple implications in current practice. The most severe complication of this condition is represented by sudden death in young patients due to malignant ventricular arrhythmias. Imaging diagnostic techniques allow for a rapid, noninvasive diagnosis of this rare cause of angina.

Heartbeat classification with low computational cost using Hjorth parameters

A method for electrocardiogram (ECG) feature extraction is presented for automatic classification of heartbeats, using values of RR intervals, amplitude and Hjorth parameters. Hjorth parameters have been used in a variety of research areas, but their application to ECG signal processing is still little explored. This paper also introduces a new approach to heartbeat segmentation, which avoids mixing information from adjacent beats and improves classification performance. The proposed model is validated in the Massachusetts Institute of Technology - Beth Israel Hospital (MIT-BIH) Arrhythmia database and presents an overall accuracy of 90.4%, better than other state-of-the-art methods. There is an improvement over other models in positive predictivity for class S (66.6%) of supraventricular ectopic beats, and sensitivity for class N (93.0%). Results obtained indicate that the techniques used in this study can be successfully applied to the problem of automatic heartbeat classification. In addition, this new approach has low computational cost, which allows its later implementation in hardware devices with limited resources.

Effects of Prolonged Spaceflight on Atrial Size, Atrial Electrophysiology, and Risk of Atrial Fibrillation.

The prevalence of atrial fibrillation (AF) in active astronauts is ≈5%, similar to the general population but at a younger age. Risk factors for AF include left atrial enlargement, increased number of premature atrial complexes, and certain parameters on signal-averaged electrocardiography, such as P-wave duration, root mean square voltage for the terminal 20 ms of the signal-averaged P wave, and P-wave amplitude. We aimed to evaluate changes in atrial structure, supraventricular beats, and atrial electrophysiology to determine whether spaceflight could increase the risk of AF. Thirteen astronauts underwent cardiac magnetic resonance imaging to assess atrial structure and function before and after 6 months in space and high-resolution Holter monitoring for multiple 48-hour time periods before flight, during flight, and on landing day. Left atrial volume transiently increased after 6 months in space (12±18 mL; P=0.03) without changing atrial function. Right atrial size remained unchanged. No changes in supraventricular beats were noted. One astronaut had a large increase in supraventricular ectopic beats but none developed AF. Filtered P-wave duration did not change over time, but root mean square voltage for the terminal 20 ms decreased on all fight days except landing day. No changes in P-wave amplitude were seen in leads II or V1 except landing day for lead V1. Six months of spaceflight may be sufficient to cause transient changes in left atrial structure and atrial electrophysiology that increase the risk of AF. However, there was no definite evidence of increased supraventricular arrhythmias and no identified episodes of AF.

Convolutional Neural Networks for Electrocardiogram Classification

In this paper, we propose a transfer learning approach for Arrhythmia Detection and Classification in Cross ECG Databases. This approach relies on a deep convolutional neural network (CNN) pretrained on an auxiliary domain (called ImageNet) with very large labelled images coupled with an additional network composed of fully connected layers. As the pretrained CNN accepts only RGB images as the input, we apply continuous wavelet transform (CWT) to the ECG signals under analysis to generate an over-complete time–frequency representation. Then, we feed the resulting image-like representations as inputs into the pretrained CNN to generate the CNN features. Next, we train the additional fully connected network on the ECG labeled data represented by the CNN features in a supervised way by minimizing cross-entropy error with dropout regularization. The experiments reported in the MIT-BIH arrhythmia, the INCART and the SVDB databases show that the proposed method can achieve better results for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB) compared to state-of-the-art methods.