Arrhythmia Classification Research Articles

Semantic-aware alignment and label propagation for cross-domain arrhythmia classification

Cross-domain arrhythmia classification (CAC) aims to transfer the model trained on a label-sufficient source domain to a label-scarce target domain. To the best of our knowledge, almost all existing CAC models focus on the unsupervised setting, where no labeled target samples are available. However, in most practical scenes, acquiring limited annotated target samples is feasible, which can provide reliable target semantic information for model learning directly. Consequently, we first propose a more realistic semi-supervised CAC setting, where only the source samples and extremely limited target samples are annotated. Most previous CAC models realize cross-domain learning by aligning the feature distributions of source and target domains coarsely and globally, where the semantic invariance within each class is not taken into consideration during the domain alignment process. Additionally, the semantic information contained in the feature space is not fully utilized for target pseudo label mining. To address the above two issues, a unified framework containing the semantic-aware feature alignment (SAFA) and prototype-based label propagation (PBLP) modules is proposed. In the proposed framework, SAFA and PBLP are complementary to each other. Specifically, SAFA provides more robust prototypes for PBLP by performing semantic-aware feature alignment, and PBLP offers more reliable target pseudo labels for more effective semantic-aware feature alignment learning. Comprehensive qualitative and quantitative experimental results on different benchmarks verify the effectiveness of the proposed method.

A training pipeline of an arrhythmia classifier for atrial fibrillation detection using Photoplethysmography signal.

Photoplethysmography (PPG) signal is potentially suitable in atrial fibrillation (AF) detection for its convenience in use and similarity in physiological origin to electrocardiogram (ECG). There are a few preceding studies that have shown the possibility of using the peak-to-peak interval of the PPG signal (PPIp) in AF detection. However, as a generalized model, the accuracy of an AF detector should be pursued on the one hand; on the other hand, its generalizability should be paid attention to in view of the individual differences in PPG manifestation of even the same arrhythmia and the existence of sub-types. Moreover, a binary classifier for atrial fibrillation and normal sinus rhythm is not convincing enough for the similarity between AF and ectopic beats. In this study, we project the atrial fibrillation detection as a multiple-class classification and try to propose a training pipeline that is advantageous both to the accuracy and generalizability of the classifier by designing and determining the configurable options of the pipeline, in terms of input format, deep learning model (with hyperparameter optimization), and scheme of transfer learning. With a rigorous comparison of the possible combinations of the configurable components in the pipeline, we confirmed that first-order difference of heartbeat sequence as the input format, a 2-layer CNN-1-layer Transformer hybridR model as the learning model and the whole model fine-tuning as the implementing scheme of transfer learning is the best combination for the pipeline (F1 value: 0.80, overall accuracy: 0.87)R.

Arrhythmia Classification Based on Bi-Directional Long Short-Term Memory and Multi-Task Group Method

Early and accurate classification of arrhythmia helps the experts to select the treatment for the patient to increase the recovery rate. The deep learning method of convolution neural network (CNN) is used for classification, and this has an overfitting problem. In this research, the multi-task group bi-directional long short term memory (MTGBi-LSTM) method is proposed to increases the performance of arrhythmia classification. The multi-task learning technique learns two ECG signals in shared representation for effective learning. The global and intra LSTM method selects the relevant feature and easily escapes from local optima. The MTGBi-LSTM model learns the unique features in shared representation that helps to overcome overfitting problem and increases the learning rate of the model. The MTGBi-LSTM model in arrhythmia classification is evaluated on MIT-BIH dataset. The MTGBi-LSTM model has 96.48% accuracy, 97.73% sensitivity, existing AFibNet has 96.36% accuracy, and 93.65% sensitivity for arrhythmia classification in CPSC 2018 dataset.

Dipper Throated Algorithm for Feature Selection and Classification in Electrocardiogram

Arrhythmia has been classified using a variety of methods. Because of the dynamic nature of electrocardiogram (ECG) data, traditional handcrafted approaches are difficult to execute, making the machine learning (ML) solutions more appealing. Patients with cardiac arrhythmias can benefit from competent monitoring to save their lives. Cardiac arrhythmia classification and prediction have greatly improved in recent years. Arrhythmias are a category of conditions in which the heart's electrical activity is abnormally rapid or sluggish. Every year, it is one of the main reasons of mortality for both men and women, worldwide. For the classification of arrhythmias, this work proposes a novel technique based on optimized feature selection and optimized K-nearest neighbors (KNN) classifier. The proposed method makes advantage of the UCI repository, which has a 279-attribute high-dimensional cardiac arrhythmia dataset. The proposed approach is based on dividing cardiac arrhythmia patients into 16 groups based on the electrocardiography dataset’s features. The purpose is to design an efficient intelligent system employing the dipper throated optimization method to categorize cardiac arrhythmia patients. This method of comprehensive arrhythmia classification outperforms earlier methods presented in the literature. The achieved classification accuracy using the proposed approach is 99.8%.

Analysis on effect of resampling techniques on cardiac arrhythmia classification using convolutional neural networks

Analysis on effect of resampling techniques on cardiac arrhythmia classification using convolutional neural networks

Classification Of Arrhythmia by Using Deep Learning With 2-D Ecg Spectral Image Representation

Classification Of Arrhythmia by Using Deep Learning With 2-D Ecg Spectral Image Representation

Classification of ECG arrhythmia using significant wavelet-based input features

This paper proposes an automated approach to classify ECG arrhythmia using wavelet transform and neural network. Wavelet-based optimal ECG feature sets are prepared followed by regression plots in curve fitting. These feature sets are further used for pattern recognition to distinguish in between normal or abnormal arrhythmia classes using multi-layer perceptron neural network (MLP NN). To evaluate performances of the designed classifier accuracy, selectivity and sensitivity parameters are measured. The average accuracy of the classifier is 99.05% which is comparatively higher than the existing methods with dependence on less input features.

A Novel Hybrid Model Based on Convolutional Neural Network With Particle Swarm Optimization Algorithm for Classification of Cardiac Arrhythmias

A Novel Hybrid Model Based on Convolutional Neural Network With Particle Swarm Optimization Algorithm for Classification of Cardiac Arrhythmias

Stacked LSTM and Kernel-PCA-based Ensemble Learning for Cardiac Arrhythmia Classification

Stacked LSTM and Kernel-PCA-based Ensemble Learning for Cardiac Arrhythmia Classification

MaeFE: Masked Autoencoders Family of Electrocardiogram for Self-Supervised Pretraining and Transfer Learning

Electrocardiogram (ECG) is a universal diagnostic tool for heart disease, which can provide data for deep learning. The scarcity of labeled data is a major challenge for medical artificial intelligence diagnosis. Acquiring labeled medical data is time-consuming and high-cost because medical specialists are needed. As a kind of generative self-supervised learning method, a masked autoencoder (MAE) is capable to solve these problems. MAE family of ECG (MaeFE) is proposed in this article. Considering the temporal and spatial features of ECG, MaeFE contains three customized masking modes, including masked time autoencoder (MTAE), masked lead autoencoder (MLAE), and masked lead and time autoencoder (MLTAE). MTAE and MLAE pay greater attention to temporal features and spatial features, respectively. MLTAE is a multihead architecture that combines MTAE and MLAE. In the pretraining stage, ECG signals from the pretrain dataset are divided into patches and partially masked. The encoder transfers unmasked patches to tokens and the decoder reconstructs masked ones. In downstream tasks, the pretrained encoder is utilized as a classifier, which is arrhythmia classification performed in the downstream dataset. The process is the so-called transfer learning. MaeFE outperforms the state-of-the-art self-supervised learning methods, SimCLR, MoCo, CLOCS, and MaskUNet in downstream tasks. MTAE has the best comprehensive performance. Compared to contrastive learning models, MTAE achieves at least a 5.18%, 11.80%, and 3.23% increase in accuracy (Acc), Macro-F1, and area under the curve (AUC), respectively, using the linear probe. It also outperforms other models at 8.99% in Acc, 20.18% in Macro-F1, and 7.13% in AUC using fine-tuning. As another downstream task, experiments on the multilabel classification of arrhythmia are also conducted, which reflects the excellent generalization performance of MaeFE. Depending on experimental results, MaeFE turns out to be efficient and robust in downstream tasks. Overcoming the scarcity of labeled data, MaeFE is better than other self-supervised learning methods and achieves satisfying performance. Consequently, the algorithm in this article is on track of playing a major role in practical applications.

Cardiac Arrhythmia Disease Classifier Model Based on a Fuzzy Fusion Approach

Cardiac diseases are one of the greatest global health challenges. Due to the high annual mortality rates, cardiac diseases have attracted the attention of numerous researchers in recent years. This article proposes a hybrid fuzzy fusion classification model for cardiac arrhythmia diseases. The fusion model is utilized to optimally select the highest-ranked features generated by a variety of well-known feature-selection algorithms. An ensemble of classifiers is then applied to the fusion’s results. The proposed model classifies the arrhythmia dataset from the University of California, Irvine into normal/abnormal classes as well as 16 classes of arrhythmia. Initially, at the preprocessing steps, for the miss-valued attributes, we used the average value in the linear attributes group by the same class and the most frequent value for nominal attributes. However, in order to ensure the model optimality, we eliminated all attributes which have zero or constant values that might bias the results of utilized classifiers. The preprocessing step led to 161 out of 279 attributes (features). Thereafter, a fuzzy-based feature-selection fusion method is applied to fuse high-ranked features obtained from different heuristic feature-selection algorithms. In short, our study comprises three main blocks: (1) sensing data and preprocessing; (2) feature queuing, selection, and extraction; and (3) the predictive model. Our proposed method improves classification performance in terms of accuracy, F1 measure, recall, and precision when compared to state-of-the-art techniques. It achieves 98.5% accuracy for binary class mode and 98.9% accuracy for categorized class mode.

Feature Selection Using Selective Opposition Based Artificial Rabbits Optimization for Arrhythmia Classification on Internet of Medical Things Environment

Feature Selection Using Selective Opposition Based Artificial Rabbits Optimization for Arrhythmia Classification on Internet of Medical Things Environment

Recurrent Ascendancy Feature Subset Training Model using Deep CNN Model for ECG based Arrhythmia Classification

Recurrent Ascendancy Feature Subset Training Model using Deep CNN Model for ECG based Arrhythmia Classification

Heartbeat Dynamics: A Novel Efficient Interpretable Feature for Arrhythmias Classification

Heartbeat Dynamics: A Novel Efficient Interpretable Feature for Arrhythmias Classification

Domain knowledge enhanced deep learning for electrocardiogram arrhythmia classification

Domain knowledge enhanced deep learning for electrocardiogram arrhythmia classification

Cardiac Arrhythmia, CHF, and NSR Classification With NCA-Based Feature Fusion and SVM Classifier

An arrhythmia is an irregular heartbeat that causes abnormal heart rhythms. Manual analysis of electrocardiogram (ECG) signals is not sufficient to quickly detect cardiac arrhythmias. This study proposes a deep learning approach based on a convolutional neural network (CNN) architecture for the classification of cardiac arrhythmias (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR). First, the ECG signal is converted into a 2D image using time-frequency conversion. The scalogram is constructed using a continuous wavelet transform to extract dynamic features. With CNN, each ECG signal is broken down into heartbeats, and then each heartbeat is converted into a 2D grayscale image of the heartbeat. Morphological feature extraction was performed by segmenting the QRS complex and detecting P and T waves. A third approach to feature extraction is dual-tree complex wavelet transform (DT-CWT). In addition, all extracted features are combined using neighborhood component analysis (NCA), and features are selected to classify using a support vector machine (SVM) classifier.

Impact of Mineralocorticoid Receptor Gene NR3C2 on the Prediction of Functional Classification of Left Ventricular Remodeling and Arrhythmia after Acute Myocardial Infarction.

Background: The NR3C2 gene encodes the mineralocorticoid receptor, which is present on cardiomyocytes. Prior studies reported an association between the presence of NR3C2 single-nucleotide polymorphisms (SNPs) and an increased cortisol production during a stress response such as acute myocardial infarction (AMI), which may lead to adverse cardiac remodeling. Objective: To study the impact of the NR3C2 rs2070950, rs4635799 and rs5522 gene polymorphisms on left ventricular (LV) remodeling, rhythm and conduction disorders in AMI patients. Methods: A cohort of 301 AMI patients who underwent revascularization was included. SNPs of the NR3C2 gene (rs2070950, rs4635799 and rs5522) were evaluated. A total of 127 AMI patients underwent transthoracic echocardiography follow-up after 72 h and 6 months. Results: The rs2070950 GG genotype and rs4635799 TT genotype were most common in patients who had LV end-diastolic volume increase < 20% and the same or increased LV ejection fraction, indicating a possible protective effect of these SNPs. The rs5522 TT genotype was associated with a higher frequency of arrhythmias, while the presence of at least one rs5522 C allele was associated with a lower risk of arrhythmias. Conclusion: SNPs of the NR3C2 gene appear to correlate with better ventricular remodeling and a reduced rate of arrhythmias post-AMI, possibly by limiting the deleterious effects of cortisol on cardiomyocytes.

Clinical Characteristics of Cardiac Arrhythmias in Pediatric Age Group

Background: The Symptomatic manifestation of pediatric arrhythmias varies according to the age. Patients with disturbances in cardiac rhythm have several complaints, but also could be totally asymptomatic. This study aimed to assess clinical characteristics of Tachy and Brady arrhythmia in neonates, infant, children and adolescents of various age groups.&#x0D; Methods: This cross-sectional study included 253 patients of pediatric age below 18 years old presented with different types of tachyarrhythmia or bradyarrhythmia. All patients were subjected to clinical general examination of patient, vital data collection, local cardiac examination, 12 leads electrocardiography, ambulatory ECG Holter monitoring, exercise ECG stress testing if indicated and transthoracic echocardiography. &#x0D; Results: There was a significant relation between age of presentation of the study patients and classification of arrhythmia (P &lt; 0.001). Palpitations was the most common presentations of arrhythmia in our study patients (32%) followed by dyspnea in 17.8 % of the patients. 20.6 % of the study patients with arrhythmias were asymptomatic. Congenital heart anomalies were in 43 % of the patients.&#x0D; Conclusion: Pediatric arrhythmia can be totally asymptomatic and discovered accidentally. Congenital cardiac anomalies and cardiac arrhythmias are closely correlated. Holter monitoring and exercise ECG testing can help in diagnosing pediatric arrhythmia. Untreated or persistent arrhythmia causes LV myopathy and dilatation. Antiarrhythmic drugs can have their harmful effect on the growing child.

Robust Arrhythmia Classification Based on QRS Detection and a Compact 1D-CNN for Wearable ECG Devices.

Embedded arrhythmia classification is the first step towards heart diseases prevention in wearable applications. In this paper, a robust arrhythmia classification algorithm, NEO-CCNN, for wearables that can be implemented on a simple microcontroller is proposed. The NEO-CCNN algorithm not only detects QRS complex but also accurately locates R-peak with the help of the proposed adaptive time-dependent thresholding technique, improving the accuracy and sensitivity in arrhythmia classification. An optimized compact 1D-CNN network (CCNN) with 9,701 parameters is used for classification. A QRS complex augmentation method is introduced in the training process to cater for R-peak location error (RLE). A nested k1k2-fold cross-validation method is utilized to evaluate the robustness of the proposed algorithm. Simulation results show that the proposed algorithm has the ability to detect more than 99.79% of R peaks with an RLE of 7.94 ms for the MIT-BIH database. Implemented on the STM32F407 microcontroller, NEO-CNN attains a classification accuracy of 97.83% and sensitivity of 96.46% using only 8s window size.

Classification of heart rhythm disturbances based on BSPM measurements

The multitude of measurement data obtained from BSPM (Body Surface Potential Mapping) requires automatic detection and classification methods to detect disturbances. The article describes the method of classification of heart rate disorders based on the characteristics of signals from sensors. For the research, a coefficient was created that allows the classification of cardiac arrhythmias in the BSPM measurements. In addition, BSPM signals were simulated using a system constructed for testing an innovative measuring vest with 102 measuring electrodes.