An Attention Based Neural Architecture for Arrhythmia Detection and Classification from ECG Signals

Arrhythmia is ubiquitous worldwide and cardiologists tend to provide solutions from the recent advancements in medicine.Detecting arrhythmia from ECG signals is considered a standard approach and hence,automating this process would aid the diagnosis by providing fast,costefficient,and accurate solutions at scale.This is executed by extracting the definite properties from the individual patterns collected from Electrocardiography(ECG)signals causing arrhythmia.In this era of applied intelligence,automated detection and diagnostic solutions are widely used for their spontaneous and robust solutions.In this research,our contributions are two-fold.Firstly,the Dual-Tree Complex Wavelet Transform(DT-CWT)method is implied to overhaul shift-invariance and aids signal reconstruction to extract significant features.Next,A neural attention mechanism is implied to capture temporal patterns from the extracted features of the ECG signal to discriminate distinct classes of arrhythmia and is trained end-to-end with the finest parameters.To ensure that the model’s generalizability,a set of five traintest variants are implied.The proposed model attains the highest accuracy of 98.5%for classifying 8 variants of arrhythmia on the MIT-BIH dataset.To test the resilience of the model,the unseen(test)samples are increased by 5x and the deviation in accuracy score and MSE was 0.12%and 0.1%respectively.Further,to assess the diagnostic model performance,AUC-ROC curves are plotted.At every test level,the proposed model is capable of generalizing new samples and leverages the advantage to develop a real-world application.As a note,this research is the first attempt to provide neural attention in arrhythmia classification using MIT-BIH ECG signals data with state-of-the-art performance.

Multi-Lead ECG Classification via an Information-Based Attention Convolutional Neural Network

A novel structure based on channel-wise attention mechanism is presented in this paper.With the proposed structure embedded,an efficient classification model that accepts multi-lead electrocardiogram(ECG)as input is constructed.One-dimensional convolutional neural networks(CNNs)have proven to be effective in pervasive classification tasks,enabling the automatic extraction of features while classifying targets.We implement the residual connection and design a structure which can learn the weights from the information contained in different channels in the input feature map during the training process.An indicator named mean square deviation is introduced to monitor the performance of a particular model segment in the classification task on the two out of five ECG classes.The data in the MIT-BIH arrhythmia database is used and a series of control experiments is conducted.Utilizing both leads of the ECG signals as input to the neural network classifier can achieve better classification results than those from using single channel inputs in different application scenarios.Models embedded with the channel-wise attention structure always achieve better scores on sensitivity and precision than the plain Resnet models.The proposed model exceeds most of the state-of-the-art models in ventricular ectopic beats(VEB)classification performance and achieves competitive scores for supraventricular ectopic beats(SVEB).Adopting more lead ECG signals as input can increase the dimensions of the input feature maps,helping to improve both the performance and generalization of the network model.Due to its end-to-end characteristics,and the extensible intrinsic for multi-lead heart diseases diagnosing,the proposed model can be used for the realtime ECG tracking of ECG waveforms for Holter or wearable devices.

Research on ECG classification based on transfer learning

Concerning current deep learning-based electrocardiograph(ECG) classification methods, there exists domain discrepancy between the data distributions of the training set and the test set in the inter-patient paradigm. To reduce the negative effect of domain discrepancy on the classification accuracy of ECG signals, this paper incorporates transfer learning into the ECG classification, which aims at applying the knowledge learned from the training set to the test set. Specifically, this paper first develops a deep domain adaptation network(DAN) for ECG classification based on the convolutional neural network(CNN). Then, the network is pre-trained with training set data obtained from the famous Massachusetts Institute of Technology-Beth Israel Hospital(MIT-BIH) ECG arrhythmia database. On this basis, by minimizing the multi-kernel maximum mean discrepancy(MK-MMD) between the data distributions of the training set and the test set, the pre-trained network is adjusted to learn transferable feature representations. Finally, with the low-density separation of unlabeled target data, the feature representations are more transferable. The extensive experimental results show that the proposed domain adaptation method has reached a 7.58% improvement in overall classification accuracy on the test set, and achieves competitive performance with other state-of-the-arts.

ECG Heartbeat Classification Under Dataset Shift

Electrocardiogram(ECG)is widely used to detect arrhythmia.Atrial fibrillation,atrioventricular block,premature beats,etc.can all be diagnosed by ECG.When the distribution of training data and test data is inconsistent,the accuracy of the model will be affected.This phenomenon is called dataset shift.In the real-world heartbeat classification system,the heartbeat of the training set and test set often comes from patients of different ages and genders,so there are differences in the distribution of data sets.The main challenge in applying machine learning algorithms to clinical AI systems is dataset shift.Test-time adaptation(TTA)aims to adapt a pre-trained model from the source domain(SD)to the target domain(TD)without using any SD data or TD labels,thereby reducing model performance degradation due to domain differences.We propose a method based on multimodal image fusion and continual test-time adaptation(FCTA)for accurate and efficient heartbeat classification.First,the original ECG data is converted into a three-channel color image through a multimodal image fusion framework.The impact of class imbalance on network performance is overcome using a batch weight loss function,and then the pretrained source model is adapted to the TD using a continual test-time adaptation(CTA)method.Although our method is very simple,compared with other domain adaptation methods,it can significantly improve model performance on the test set and reduce the impact caused by the difference in domain distribution.

Arrhythmia Detection by Using Chaos Theory with Machine Learning Algorithms

Heart monitoring improves life quality.Electrocardiograms(ECGs or EKGs)detect heart irregularities.Machine learning algorithms can create a few ECG diagnosis processing methods.The first method uses raw ECG and time-series data.The second method classifies the ECG by patient experience.The third technique translates ECG impulses into Q waves,R waves and S waves(QRS)features using richer information.Because ECG signals vary naturally between humans and activities,we will combine the three feature selection methods to improve classification accuracy and diagnosis.Classifications using all three approaches have not been examined till now.Several researchers found that Machine Learning(ML)techniques can improve ECG classification.This study will compare popular machine learning techniques to evaluate ECG features.Four algorithms—Support Vector Machine(SVM),Decision Tree,Naive Bayes,and Neural Network—compare categorization results.SVM plus prior knowledge has the highest accuracy(99%)of the four ML methods.QRS characteristics failed to identify signals without chaos theory.With 99.8%classification accuracy,the Decision Tree technique outperformed all previous experiments.

ECG beat classification using particle swarm optimization and support vector machine

In this paper, we propose a novel ECG arrhythmia classification method using power spectral-based features and support vector machine （SVM） classifier. The method extracts electrocardiogram＇s spectral and three timing inter- val features. Non-parametric power spectral density （PSD） estimation methods are used to extract spectral features. The proposed approach optimizes the relevant parameters of SVM classifier through an intelligent algorithm using parti- cle swarm optimization （PSO）. These parameters are： Gaus- sian radial basis function （GRBF） kernel parameter o- and C penalty parameter of SVM classifier. ECG records from the MIT-BIH arrhythmia database are selected as test data. It is observed that the proposed power spectral-based hybrid par- ticle swarm optimization-support vector machine （SVMPSO） classification method offers significantly improved perfor- mance over the SVM which has constant and manually ex- tracted parameter.

A Novel Defibrillator-Specific Coprocessor Capable of Running Entropy and CNN Integration Algorithms

It is difficult for the existing Automated External Defibrillator (AED) on-board microprocessors to accurately classify electrocardiographic signals (ECGs) mixed with Cardiopulmonary Resuscitation artifacts in real-time. In order to improve recognition speed and accuracy of electrocardiographic signals containing Cardiopulmonary Resuscitation artifacts, a new special coprocessor system-on-chip (SoC) for defibrillators was designed. In this study, a microprocessor was designed based on the RISC-V architecture to achieve hardware acceleration for ECGs classification;Besides, an Approximate Entropy (ApEn) and Convolutional neural networks (CNNs) integrated algorithm capable of running on it was designed. The algorithm differs from traditional electrocardiographic (ECG) classification algorithms. It can be used to perform ECG classification while chest compressions are applied. The proposed co-processor can be used to accelerate computation rate of ApEn by 34 times compared with pure software computation. It can also be used to accelerate the speed of CNNs ECG recognition by 33 times. The combined algorithm was used to classify ECGs with CPR artifacts. It achieved a precision of 96%, which was significantly superior to that of simple CNNs. The coprocessor can be used to significantly improve the recognition efficiency and accuracy of ECGs containing CPR artifacts. It is suitable for automatic external defibrillator and other medical devices in which one-dimensional physiological signals.