Supraventricular Ectopic Beats Research Articles

A COMPLEX CASE OF EARLY ONSET ATRIAL FIBRILLATION IN AN ENDURANCE ATHLETE: THE IMPORTANCE OF FAMILY HISTORY

Abstract Introduction Early onset atrial fibrillation (AF) in an endurance athlete represents a challenge for the cardiologist, especially in apparent absence of an overt structural heart disease. Different genetic variants have been associated with early onset AF but indications to genetic testing are still under definition. Case A 54–year–old man (BMI 19 kg/sqm), previous competitive athlete (Nordic running and walking) presented to the Emergency Department with sudden onset palpitations and dyspnea due to high penetrance AF (145 bpm). Family history (FH) was positive for cerebrovascular accidents in both parents and for early onset (<60 years) AF in the father. The man had a recent history of borderline hypertension, of effort related syncope of and of infundibular, isolated, premature ventricular complexes during a maximal exercise stress test (otherwise negative for ischemia) which ultimately led to the denial of competitive sport eligibility. Sinus rhythm (SR) was acutely restored with flecainide and the patient was discharged with low dose nadolol. Cardiac US showed normal left ventricular (LV) dimensions and thicknesses (10 mm), with regular LVEF (60%) and global longitudinal strain (–18%), mildly dilated left atrium (LAVI 36 ml/sqm) and bi–leaflet mitral valve prolapse without significant mitral regurgitation, mitro–anular disjunction nor Pickelhaube sign; 24h Holter ECG showed SR with rare supraventricular (SV) ectopic beats and a 4 beats SV run. Due to the recurrence of short episodes of palpitations, rhythm control with flecainide and antithrombotic prophylaxis were started and AF ablation was planned. Genetic testing for early onset AF identified a nonsense variant (c.84665delG; p.Gly28222fs*2) in TTN gene, classified as likely pathogenic (C4), so far not reported in scientific literature. Also, despite a moderate–low cardiovascular risk as assessed by SCORE2, mostly due to the FH and the desire to engage in high intensity exercise, coronary CT was prescribed, which showed a critical coronary disease leading to stenting on left anterior descending artery and intermediate branch. Cardiac MRI was planned. Conclusions Early onset AF in endurance athletes should not be underrated and a thorough examination including a detailed family history should be performed. TTN is the single gene most frequently associated with early onset AF in absence of an overt structural heart disease, but the subsequent clinical evolution is still largely unknown.

Классификация сигналов ЭКГ на основе цифровой обработки сигналов, технического выбора функций и радиочастотного классификатора

Determining the optimal integration between features and classifiers has a significant effect on the performance of automatic heartbeat diagnostic systems. This importance stands out when dealing with critical applications that contain limited resources devices and require accurate and fast heartbeat classifiers to help the doctor make an accurate and quick diagnosis of heart diseases. Aiming at this task, this paper introduces a novel approach for choosing the optimal features of the ECG signal to be used with the Random Forest (RF) classifier following the inter-patient method for ECG signals division and obeying the instructions of the "Association for the Advancement of Medical Instrumentation (AAMI)." The features were chosen based on the concept of "Mutual Information Ranking (MIR)." The presented framework is comprehensive in terms of performing all the necessary processes efficiently, starting from ECG digital signal processing, segmentation, feature extraction, feature selection, and ending with ECG classification. The results of the experiments demonstrate that features corresponding to the normalized QRS width and the normalized RR intervals are the most influential features in the heartbeat classification. All tests were conducted using real ECG signals taken from the "MIT-BIH" Arrhythmia Database (MIT-BIH-ARR-DB). The suggested scheme attained the following F1-scores: 91.02%, 73.17%, and 98.04% in the classification of the Ventricular Ectopic Beats (V or VEB), Supraventricular Ectopic Beats (S or SVEB), and Normal Beats (N or NB), respectively. The overall accuracy was 96.26%. Despite its relative simplicity and reliance on few features, the proposed approach outperforms most of the reported state-of-the-art.

Risk of Cardiac Arrhythmias in Patients with Late-Onset Pompe Disease—Results from a Long Follow-Up in a Group of 12 Patients and Review of Literature

Background. Pompe disease is a rare, severe, autosomal recessive genetic disorder caused by GAA gene mutations, which cause α-1,4-glucosidase enzyme deficiency. There are two forms of Pompe disease based on the age of onset, the infantile and the adult form (LOPD). Cardiac involvement, previously recognized only in infantile cases, is now also reported in adults. Cardiomyopathy remains an exceptional finding while heart rhythm disorders appear to be more frequent. Methods. We retrospectively evaluated cardiac involvement in 12 patients with late-onset Pompe disease (LOPD) followed for an overall period of 143 years (mean 12.7 ± 7.7) using ECG, Holter ECG, and echocardiography. Results. The mean age of patients (M8:F4) at the first visit was 40.7 ± 16.1 (range 14–63) and 53.7 ± 16.9 (range 21–76) at last visit. Conduction delay was present in three patients; one patient developed ascending aorta ectasia but had a history of hypertension, and one patient showed right heart enlargement on echocardiography, probably due to pulmonary hypertension. No patient died during the FU, nor developed cardiomyopathy. Ectopic supraventricular beats and repeated episodes of ablation-resistant atrial fibrillation were observed in only one patient (8.3%) who required PMK implantation. Conclusions. Benefitting from the long follow-up, this study allows us to state that primary myocardial involvement is rare in patients with LOPD, while rhythm disorders are more frequent and require monitoring to avoid the risk of possible life-threatening complications.

Cross-database and cross-channel electrocardiogram arrhythmia heartbeat classification based on unsupervised domain adaptation

The classification of electrocardiogram (ECG) plays a crucial role in the development of an automatic cardiovascular diagnostic system. However, the considerable variances in ECG signals between individuals pose a significant challenge. Changes in data distribution limit cross-domain utilization of a model. In this study, we propose a solution to classify ECG in an unlabeled dataset by leveraging knowledge obtained from labeled source domain. We present a domain-adaptive deep network based on cross-domain feature discrepancy optimization. Our method comprises three stages: pre-training, cluster-centroid computing, and adaptation. In pre-training, we employ a Distributionally Robust Optimization (DRO) technique to deal with the vanishing worst-case training loss. To enhance the richness of the features, we concatenate three temporal features with the deep learning features. The cluster computing stage involves computing centroids of distinctly separable clusters for the source using true labels, and for the target using confident predictions. We propose a novel technique for selecting confident predictions in the target domain. In the adaptation stage, we minimize compacting loss within the same cluster, separating loss across different clusters, inter-domain cluster discrepancy loss, and running combined loss to produce a domain-robust model. Experiments conducted in both cross-domain and cross-channel paradigms show the efficacy of the proposed method. Our method achieves superior performance compared to other state-of-the-art approaches in detecting ventricular ectopic beats (V), supraventricular ectopic beats (S), and fusion beats (F). Our method achieves an average improvement of 11.78% in overall accuracy over the non-domain-adaptive baseline method on the three test datasets.

Inter-patient ECG arrhythmia heartbeat classification network based on multiscale convolution and FCBA

Cardiac arrhythmias that can lead to sudden cardiac death are common. Electrocardiograms (ECGs) offer valuable information about cardiac status and play a crucial role in evaluating patients with arrhythmia in clinical diagnosis. The development of machine learning technologies has made the computer-aided diagnosis of cardiac arrhythmias possible, which can improve the efficiency and quality of medical treatment. In this study, a new method for the automatic classification of heartbeats is developed. This paper presents a novel approach to detect arrhythmias in the inter-patient paradigm using a convolutional neural network (CNN) that integrates multiscale convolutional blocks, frequency convolutional block attention (FCBA) modules, and RR interval features. The proposed method also includes oversampling for the heartbeats of the minority class and the addition of random noise to increase training samples and alleviate the problem of data imbalance. We used the MIT-BIH-AR arrhythmia database , which is a globally recognized ECG database, to evaluate the classification performance of the proposed model in this paper. Based on the experiments, the sensitivities of the normal beats (N), supraventricular ectopic beats (SVEB), and ventricular ectopic beats (VEB) were 96.9%, 89.3%, and 93.3%, respectively. In the inter-patient heartbeat classification paradigm, the overall accuracy of the proposed method is 95.60% in classifying heartbeats. The study shows that the proposed scheme outperforms other published schemes in terms of classification results.

Arrhythmia Detection Based on New Multi-Model Technique for ECG Inter-Patient Classification

This paper presents a novel model for arrhythmia detection based on a cascading technique that utilizes a combination of the One-Sided Selection (OSS) method, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithms, this model denoted by (OWSK) model to classify four types of electrocardiogram (ECG) heartbeats following inter-patient scheme. The OWSK model consists of three stages. The first stage involves resampling using the One-Sided Selection (OSS) method to solve the imbalance problem and reduce data by removing noisy, borderline, and redundant samples. The second stage involves using Wavelet Transformation (WT) and Power Spectral Density (PSD) to extract the most relevant frequency domain features. The third stage involves a cascading process by constructing the classifier from SVM trained on the whole dataset to classify normal and abnormal beats. Then, KNN (K-Nearest Neighbors) is trained on only the three irregular minority classes to classify the three types of arrhythmias for the detection of ventricular ectopic beats, supraventricular ectopic beats, and fusion beats (V, S, and F). The performance of the proposed model is evaluated in terms of different metrics, including accuracy, recall, precision, and F1 score. The results show the superiority of the proposed model in medical diagnosis compared to the latest works, where it achieves 90%, 90%, 93%, and 91% for accuracy, recall, precision, and F1 score under the inter-patient paradigm and 98%, 98%, 98%, and 98% under the intra-patient paradigm.

Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning

This article presents a resource-efficient adaptive sampling methodology for classifying electrocardiogram (ECG) signals into different heart rhythms. We present our methodology in two folds: ( i ) the design of a novel real-time adaptive neural network architecture capable of classifying ECG signals with different sampling rates and ( ii ) a runtime implementation of sampling rate control using deep reinforcement learning (DRL). By using essential morphological details contained in the heartbeat waveform, the DRL agent can control the sampling rate and effectively reduce energy consumption at runtime. To evaluate our adaptive classifier, we use the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifier is designed to recognize three major types of arrhythmias, which are supraventricular ectopic beats (SVEB), ventricular ectopic beats (VEB), and normal beats (N). The performance of the arrhythmia classification reaches an accuracy of 97.2% for SVEB and 97.6% for VEB beats. Moreover, the designed system is 7.3× more energy-efficient compared to the baseline architecture, where the adaptive sampling rate is not utilized. The proposed methodology can provide reliable and accurate real-time ECG signal analysis with performances comparable to state-of-the-art methods. Given its time-efficient, low-complexity, and low-memory-usage characteristics, the proposed methodology is also suitable for practical ECG applications, in our case for arrhythmia classification, using resource-constrained devices, especially wearable healthcare devices and implanted medical devices.

Classification of Heartbeats Using Convolutional Neural Networks

Abstract: When there is a suspicion of a heart attack, an electrocardiogram (ECG) is a crucial test. It measures the electrical activity of the heart, which is manifested through small electric impulses when the heart beats. The subsequent process of analyzing ECG patterns is time-consuming but vital in determining the likelihood of cardiovascular disease by medical professionals. This project utilizes ECG image data to automate the interpretation of ECG recordings, aiming to assist clinicians in detecting life-threatening Myocardial Infarction. By taking an ECG image as input, the system classifies and attempts to categorize the final result into five classes: Non-Ectopic Beats, Supraventricular Ectopic Beats, Ventricular Ectopic Beats, Fusion Beats, and Unknown Beats.

C23 ELECTROCARDIOGRAPHIC PREDICTORS OF PRIMARY VENTRICULAR FIBRILLATION DURING A FIRST ACUTE MYOCARDIAL INFARCTION

Abstract Introduction Few small studies evaluated electrocardiographic (ECG) predictors of ventricular fibrillation (VF) before reperfusion during a first acute myocardial infarction (AMI). None accounted for the time between symptom onset and ECG. Objectives To evaluate the ECG predictors of primary VF in the PREDESTINATION (PRimary vEntricular fibrillation and suDden dEath during a firST myocardIal iNfArcTION) population. Patients and methods: PREDESTINATION is an ongoing, prospective, multicenter, case–control study (1:2 match for sex and age) enrolling patients aged 18–80 with a first AMI, whether complicated (cases) or not (controls) by primary VF before reperfusion. For the present analysis, we matched 1:1 for age, sex, infarct site, and symptom–ECG time, the ECGs of cases before VF and those of controls revascularized at least 60 minutes after symptom onset. ECG traces were digitized in pdf and enlarged by 400%. Three blind analyzes were performed: on the entire population, on only anterior and only non–anterior AMI. Results PREDESTINATION currently includes 1478 patients (mean 59 years, 83% male), 533 of whom are cases. Among the cases, only 59 (58 ± 11 years, 10% females, 64% with anterior AMI, mean symptoms–ECG time 78±60 minutes, mean ECG–VF time 23±15 minutes) had a pre–VF ECG of adequate quality. Both in the general population (118 ECGs) and in anterior AMIs subgroup (76 ECGs), the presence of ventricular (VEB) or supraventricular ectopic beats (SVEB) was associated with an increased risk of developing VF (maximum OR 8.35 for VEBs in anterior AMIs). In the subgroup of anterior AMIs, the Tpeak–Tend interval in non–infarction leads, both corrected for the RR interval (Bazett) and for the QT interval (TpTe/QT) was significantly longer in cases compared to controls. A TpTe/QT ≥0.33 in non–infarction leads was associated with an OR of 4.6 (p=0.02) of developing VF. Conclusions the present analysis, aimed at identifying ECG predictors of primary VF, is the first to perform a rigorous case–control matching including symptom–ECG time. In addition to ectopic beats, a well–known marker and promoter of electrical instability, we identified, only for anterior AMIs, a single additional predictor (TpTe/QT), which correlates with an increased dispersion of repolarization and consequently of ventricular refractoriness.

Ensemble classifier fostered detection of arrhythmia using ECG data.

Electrocardiogram (ECG) is a non-invasive medical tool that divulges the rhythm and function of the human heart. This is broadly employed in heart disease detection including arrhythmia. Arrhythmia is a general term for abnormal heart rhythms that can be identified and classified into many categories. Automatic ECG analysis is provided by arrhythmia categorization in cardiac patient monitoring systems. It aids cardiologists to diagnose the ECG signal. In this work, an Ensemble classifier is proposed for accurate arrhythmia detection using ECG Signal. Input data are taken from the MIT-BIH arrhythmia dataset. Then the input data was pre-processed using Python in Jupyter Notebook which run the code in an isolated manner and was able to keep code, formula, comments, and images. Then, Residual Exemplars Local Binary Pattern is applied for extracting statistical features. The extracted features are given to ensemble classifiers, like Support vector machines (SVM), Naive Bayes (NB), and random forest (RF) for classifying the arrhythmia as normal (N), supraventricular ectopic beat (S), ventricular ectopic beat (V), fusion beat (F), and unknown beat (Q). The proposed AD-Ensemble SVM-NB-RF method is implemented in Python. The proposed AD-Ensemble SVM-NB-RF method is 44.57%, 52.41%, and 29.49% higher accuracy; 2.01%, 3.33%, and 3.19% higher area under the curve (AUC); and 21.52%, 23.05%, and 12.68% better F-Measure compared with existing models, like multi-model depending on the ensemble of deep learning for ECG heartbeats arrhythmia categorization (AD-Ensemble CNN-LSTM-RRHOS), ECG signal categorization utilizing VGGNet: a neural network based classification method (AD-Ensemble CNN-LSTM) and higher performance arrhythmic heartbeat categorization utilizing ensemble learning along PSD based feature extraction method (AD-Ensemble MLP-NB-RF).

Imbalanced Ectopic Beat Classification Using a Low-Memory-Usage CNN LMUEBCNet and Correlation-Based ECG Signal Oversampling

Objective: This study presents a low-memory-usage ectopic beat classification convolutional neural network (CNN) (LMUEBCNet) and a correlation-based oversampling (Corr-OS) method for ectopic beat data augmentation. Methods: A LMUEBCNet classifier consists of four VGG-based convolution layers and two fully connected layers with the continuous wavelet transform (CWT) spectrogram of a QRS complex (0.712 s) segment as the input of the LMUEBCNet. A Corr-OS method augmented a synthetic beat using the top K correlation heartbeat of all mixed subjects for balancing the training set. This study validates data via a 10-fold cross-validation in the following three scenarios: training/testing with native data (CV1), training/testing with augmented data (CV2), and training with augmented data but testing with native data (CV3). Experiments: The PhysioNet MIT-BIH arrhythmia ECG database was used for verifying the proposed algorithm. This database consists of a total of 109,443 heartbeats categorized into five classes according to AAMI EC57: non-ectopic beats (N), supraventricular ectopic beats (S), ventricular ectopic beats (V), a fusion of ventricular and normal beats (F), and unknown beats (Q), with 90,586/2781/7236/803/8039 heartbeats, respectively. Three pre-trained CNNs: AlexNet/ResNet18/VGG19 were utilized in this study to compare the ectopic beat classification performance of the LMUEBCNet. The effectiveness of using Corr-OS data augmentation was determined by comparing (1) with/without using the Corr-OS method and (2) the Next-OS data augmentation method. Next-OS augmented the synthetic beat using the next heartbeat of one subject. Results: The proposed LMUEBCNet can achieve a 99.4% classification accuracy under the CV2 and CV3 cross-validation scenarios. The accuracy of the proposed LMUEBCNet is 0.4–0.5% less than the performance obtained from AlexNet/ResNet18/VGG19 under the same data augmentation and cross-validation scenario, but the parameter usage is only 10% or less than that of the AlexNet/ResNet18/VGG19 method. The proposed Corr-OS method can improve ectopic beat classification accuracy by 0.3%. Conclusion: This study developed a LMUEBCNet that can achieve a high ectopic beat classification accuracy with efficient parameter usage and utilized the Corr-OS method for balancing datasets to improve the classification performance.

Association of non-sustained atrial tachycardia and its duration in 24-h Holter monitoring with embolic stroke of unknown source.

Although supraventricular ectopic beats (SVE), including premature atrial contractions (PACs) and non-sustained atrial tachycardia (NSAT), are frequent in the general population, some study results indicate that they are pathologic. SVE may predict undiagnosed atrial fibrillation or be associated with the embolic pattern of ischemic stroke. The aim of this study was to identify the indicators most associated with embolic stroke among the parameters that suggest the burden of SVE. A total of 1920 consecutive acute ischemic stroke (AIS) patients were enrolled from two university hospitals. We defined embolic stroke of unknown source (ESUS) and small vessel occlusion (SVO) etiologies using stricter criteria than the existing conventional criteria. We enrolled 426 (SVO: 310 vs. ESUS: 116) patients who met the inclusion criteria. In the 24-h Holter monitoring parameters, total number of PACs and PAC-to-total beat ratio were not significantly different between the two groups. However, NSATs were more frequent, and the duration of the longest NSAT was longer in the ESUS group. Multivariate logistic regression revealed that high brain natriuretic peptide levels, presence of NSAT, history of previous stroke, and the longest NSAT duration significantly correlated with the ESUS etiology. The presence of NSAT and its duration are more important indicators of embolic stroke than the frequency of PACs is. Therefore, considering secondary prevention in AIS patients with ESUS, 24-h Holter monitoring parameters, such as the presence of NSAT and its duration, could be considered as potential sources of cardio-embolism.

Two-stage detection method of supraventricular and ventricular ectopic beats based on sequential artificial features and heartbeats

Early detection of Supraventricular ectopic beats (SVEBs) and Ventricular ectopic beats (VEBs) is particularly important for preventing dangerous heart diseases. Researchers proposed many automatic detection methods. However, most of these methods do not utilize the contextual information of artificial features among neighbor heartbeats. Our method consists of two stages. The first stage aims to classify all heartbeats into the ectopic class and non-ectopic class. The ectopic class includes SVEBs and VEBs. The ectopic class includes other heartbeats. Firstly, we extracted Sequential Artificial Features (SAFs) from every 20 neighbor heartbeats, including RR intervals, skewness, existence flags of P-waves and T-waves. Secondly, we developed a framework to implement classification by using SAFs and heartbeats. This framework integrates four independent networks, three of them are used to implement the same classification but have different classification performances, the remaining one is used to fuse outputs of the other three networks. In the second stage, we designed a network to further classify ectopic heartbeats into SVEBs and VEBs. We validated the proposed method on the MIT-BIH Arrhythmia Database with the inter-patient model. For the ectopic class and non-ectopic class, the F1-score reaches 90.82 and 98.96 respectively. For SVEBs and VEBs, the F1-score reaches 80.46 and 95.10 respectively. Experimental results demonstrated that our method and SAFs are effective for SVEBs and VEBs classification.

An automated patient-specific ECG beat classification using LSTM-based recurrent neural networks

Customized electrocardiogram analysis is inevitable in the cardiac functionality assessment of every single individual patient. In this paper, we firmly introduce a novel framework for patient-specific electrocardiogram (ECG) beat classification characterized by the long-short term memory (LSTM) based recurrent neural networks (RNNs). A novel architecture is developed by governing two LSTM models connected in parallel, and each of them operates on the single-channel ECG input. The proposed model customizes the classification process and imbibes the trait of patient-specific analysis by training the model with the first 5-min segment of heartbeats of the respective patient’s ECG record and tests the same for the rest of the ECG record. The proposed framework undergoes five stages viz; pre-processing, QRS complex detection, segmentation, feature extraction, and LSTM-based RNNs for classification. The efficiency of the proposed framework is deeply examined by the support of various metrics viz; accuracy (Acc), sensitivity (Sen), specificity (Spe), positive predictivity (Ppr), F1 score, and G score and the performance of the proposed method is compared to that of some popular state-of-the-art techniques. The proposed framework is exposed to a highly popular and reliable MIT-BIH arrhythmia database for training and testing purposes. The obtained results are found promising and yield superior classification performance in recognizing ventricular ectopic beats (VEB) and supra-ventricular ectopic beats (SVEB). In addition, the proposed framework is recognized as simple, lightweight yet efficient which in turn makes it suitable for continuous monitoring applications in clinical settings for automated ECG analysis to assist the cardiologist.

Automatic classification of arrhythmias using multi-branch convolutional neural networks based on channel-based attention and bidirectional LSTM

Cardiac arrhythmia is an abnormal rhythm of the heartbeat and can be life-threatening Electrocardiogram (ECG) is a technology that uses an electrocardiograph machine to record a graph of the changes in electrical activity produced by the heart at each cardiac cycle. ECG can generally be used to check whether the examinee has arrhythmia, ion channel disease, cardiomyopathy, electrolyte disorder and other diseases. To reduce the workload of doctors and improve the accuracy of ECG signal recognition, a novel and lightweight automatic ECG classification method based on Convolutional Neural Network (CNN) is proposed. The multi-branch network with different receptive fields is used to extract the multi-spatial deep features of heartbeats. The Channel Attention Module (CAM) and Bidirectional Long Short-Term Memory neural network (BLSTM) module are used to filter redundant ECG features. CAM and BLSTM are beneficial for distinguishing different categories of heartbeats. In the experiments, a four-fold cross-validation technique is used to improve the generalization capability of the network, and it shows good performance on the testing set. This method divides heartbeats into five categories according to the American Advancement of Medical Instrumentation (AAMI) criteria, which is validated in the MIT-BIH arrhythmia database. The sensitivity of this method to Ventricular Ectopic Beat (VEB) is 98.5% and the F1 score is 98.2%. The precision of the Supraventricular Ectopic Beat (SVEB) is 91.1%, and the corresponding F1 score is 90.8%. The proposed method has high classification performance and a lightweight feature. In a word, it has broad application prospects in clinical medicine and health testing.

Intra-Individual Comparison of Sinus and Ectopic Beats Probing the Ventricular Gradient’s Activation Dependence

Wilson assumed that the ventricular gradient (VG) is independent of the ventricular activation order. This paradigm has often been refuted and was never convincingly corroborated. We sought to validate Wilson's concept by intra-individual comparison of the VG of sinus beats and ectopic beats, thus assessing the effects of both altered ventricular conduction (caused by the ectopic focus) and restitution (caused by ectopic prematurity). We studied standard diagnostic ECGs of 118 patients with accidental extrasystoles: normally conducted supraventricular ectopic beats (SN, N = 6) and aberrantly conducted supraventricular ectopic beats (SA, N = 20) or ventricular ectopic beats (V, N = 92). In each patient, we computed the VG vectors of the predominant beat, VGp→, of the ectopic beat, VGe→, and of the VG difference vector, ΔVGep→, and compared their sizes. VGe→ of the SA and V ectopic beats were significantly larger than VGp→ (53.7 ± 25.0 vs. 47.8 ± 24.6 mV∙ms, respectively; p < 0.001). ΔVGep→ were three times larger than the difference of VGe→ and VGp→ (19.94 ± 9.76 vs. 5.94 mV∙ms, respectively), demonstrating differences in the VGp→ and VGe→ spatial directions. The amount of ectopic prematurity was not correlated with ΔVGep→, although the larger VG difference vectors were observed for the more premature (<80%) extrasystoles. Electrical restitution properties and electrotonic interactions likely explain our findings. We conclude that the concept of a conduction-independent VG should be tested at equal heart rates and without including premature extrasystoles.

A Tiny Matched Filter-Based CNN for Inter-Patient ECG Classification and Arrhythmia Detection at the Edge.

Automated electrocardiogram (ECG) classification using machine learning (ML) is extensively utilized for arrhythmia detection. Contemporary ML algorithms are typically deployed on the cloud, which may not always meet the availability and privacy requirements of ECG monitoring. Edge inference is an emerging alternative that overcomes the concerns of cloud inference; however, it poses new challenges due to the demanding computational requirements of modern ML algorithms and the tight constraints of edge devices. In this work, we propose a tiny convolutional neural network (CNN) classifier for real-time monitoring of ECG at the edge with the aid of the matched filter (MF) theory. The MIT-BIH dataset with inter-patient division is used for model training and testing. The model generalization capability is validated on the INCART, QT, and PTB diagnostic databases, and the model performance in the presence of noise is experimentally analyzed. The proposed classifier can achieve average accuracy, sensitivity, and F1 scores of 98.18%, 91.90%, and 92.17%, respectively. The sensitivity of detecting supraventricular and ventricular ectopic beats (SVEB and VEB) is 85.3% and 96.34%, respectively. The model is 15 KB in size, with an average inference time of less than 1 ms. The proposed model achieves superior classification and real-time performance results compared to the state-of-the-art ECG classifiers while minimizing the model complexity. The proposed classifier can be readily deployed on a wide range of resource-constrained edge devices for arrhythmia monitoring, which can save millions of cardiovascular disease patients.

WavelNet: A novel convolutional neural network architecture for arrhythmia classification from electrocardiograms

Background and objectiveAutomated detection of arrhythmias from electrocardiograms (ECGs) can be of considerable assistance to medical professionals in providing efficient treatment for patients with cardiovascular diseases. In recent times, convolutional neural network (CNN)-based arrhythmia classification models have been introduced, but their decision-making processes remain unclear and their performances are not reproducible. This paper proposes an accurate, interpretable, and reproducible end-to-end arrhythmia classification model based on a novel CNN architecture named WavelNet, which is interpretable and optimal for dealing with ECGs. MethodsInspired by SincNet, which is capable of band-pass filtering-based spectral analysis, WavelNet was devised to achieve wavelet transform-based spectral analysis. WavelNet was trained using a subject-oriented five-class ECG arrhythmia dataset generated from the MIT-BIH Arrhythmia Database while following a benchmark scheme. By adopting various mother wavelets, multiple WavelNet-based arrhythmia classification models were implemented. To investigate whether our wavelet transform-based approach outperforms original end-to-end and band-pass filtering-based approaches, our proposed models were compared with vanilla CNN- and SincNet-based models. Model implementation and evaluation processes were repeated ten times in a Google Colab Pro+ environment. Furthermore, our most successful model was compared with state-of-the-art arrhythmia classification models for performance evaluation. ResultsThe proposed WavelNet-based models showed excellent performance on classifying non-ectopic, supraventricular ectopic, and ventricular ectopic beats because of their ability to perform adaptive spectral analysis while preserving temporal ECG information compared with vanilla CNN- and SincNet-based models. In particular, a Symlet 4 wavelet-adopting WavelNet-based model achieved the best performance with nearly 90% overall accuracy as well as the highest levels of sensitivity in classifying each arrhythmia class: 91.4%, 49.3%, and 91.4% for non-ectopic, supraventricular ectopic, and ventricular ectopic beat classifications, respectively. These results were comparable to those of state-of-the-art models. In addition, the results are reproducible, which differentiates our study from previous studies. ConclusionsOur proposed WavelNet-based arrhythmia classification model achieved remarkable performance based on a reasonable decision-making process, in comparison with other models. As its noteworthy performance is clinically reasonable and reproducible, our proposed model can contribute toward implementing a real-world precision healthcare system for patients with cardiovascular diseases.

Enhanced electrocardiogram machine learning-based classification with emphasis on fusion and unknown heartbeat classes.

Building an electrocardiogram (ECG) heartbeat classification model is essential for early arrhythmia detection. This research aims to build a reliable model that can classify heartbeats into five heartbeat types: normal beat (N), supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), fusion beat (F), and unknown beat (Q), with a focus on enhancing the predictions of the uncommon Q and F heartbeats. The base dataset used is the MIT-BIH SupraVentricular Database, which was used to train and compare the performance of five machine learning models: logistic regression, Random Forest (RF), K-nearest neighbor, linear support vector machine, and linear discriminant analysis. In addition to using the synthetic minority oversampling technique, data extracted from multiple databases for the F and Q classes were combined with the original base dataset. These methods resulted in significant improvement in the recall for the rare F and Q classes when compared to the literature. The RF algorithm produced the best performance with an accuracy of 97% and recall values equal to 97%, 93%, 95%, 95%, and 30% for N, SVEB, VEB, F, and Q, respectively.

Interpatient Heartbeat Classification Using Modified Residual Attention Network With Two-Phase Training and Assistant Decision

State-of-the-art studies on automatic heartbeat classification have made efforts to improve supraventricular ectopic beat (SVEB) detection, but resulted in a low positive predictive value (PPV) of SVEB and poor performance of other categories under the interpatient paradigm. This article proposes a novel algorithm for heartbeat classification by the means of deep learning combined with feature extraction, which enhances the performance and can be applied to an automatic electrocardiogram (ECG) analysis. It is an improved residual attention network (IraNet) that combines attention module, residual inception block, and bidirectional long short-term memory (BiLSTM) layer to process single heartbeat segments directly. A two-phase training method is presented to change the weights in a planned way to deal with the imbalance of distinguishable features. An assistant decision for the deep learning-based model enhances the PPV of SVEB effectively. Under the interpatient paradigm on the Massachusetts Institute of Technology and Beth Israel Hosipital (MIT-BIH) arrhythmia database, the overall accuracy (Acc) of four classes achieves 0.9548. For SVEB class, the PPV is significantly improved to 0.7557 with the sensitivity (Sen) and an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> score of 0.7392 and 0.7474, respectively. For ventricular ectopic beat (VEB) class, the Sen, PPV, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> score achieve 0.9575, 0.8500, and 0.9005, respectively, and the numbers are 0.9663, 0.9873, and 0.9767 for normal beat class. For fusion beat class, the numbers are 0.7964, 0.3597, and 0.4954, respectively. The proposed algorithm gets competitive results with the state-of-the-art studies, and there is a notable improvement in the detection of SVEB