Automated Method for Discrimination of Arrhythmias Using Time, Frequency, and Nonlinear Features of Electrocardiogram Signals

A novel method of swin transformer with time-frequency characteristics for ECG-based arrhythmia detection

Introduction

Arrhythmia is an important indication of underlying cardiovascular diseases (CVD) and is prevalent worldwide. Accurate diagnosis of arrhythmia is crucial for timely and effective treatment. Electrocardiogram (ECG) plays a key role in the diagnosis of arrhythmia. With the continuous development of deep learning and machine learning processes in the clinical field, ECG processing algorithms have significantly advanced the field with timely and accurate diagnosis of arrhythmia.

Methods

In this study, we combined the wavelet time-frequency maps with the novel Swin Transformer deep learning model for the automatic detection of cardiac arrhythmias. In specific practice, we used the MIT-BIH arrhythmia dataset, and to improve the signal quality, we removed the high-frequency noise, artifacts, electromyographic noise and respiratory motion effects in the ECG signals by the wavelet thresholding method; we used the complex Morlet wavelet for the feature extraction, and plotted wavelet time-frequency maps to visualise the time-frequency information of the ECG; we introduced the Swin Transformer model for classification and achieve high classification accuracy of ECG signals through hierarchical construction and self attention mechanism, and combines windowed multi-head self-attention (W-MSA) and shifted window-based multi-head self-attention (SW-MSA) to comprehensively utilise the local and global information.

Results

To enhance the confidence of the experimental results, we evaluated the performance using intra-patient and inter-patient paradigm analyses, and the model classification accuracies reached 99.34% and 98.37%, respectively, which are better than the currently available detection methods.

Discussion

The results reveal that our proposed method is superior to currently available methods for detecting arrhythmia ECG. This provides a new idea for ECG based arrhythmia diagnosis.

Improving the Accuracy of R-Peak Detection in a Wearable Armband Device for Daily Life Electrocardiogram Monitoring Using a Deep Convolutional Denoising Encoder-Decoder Network

Continuous long-term heart rate (HR) monitoring using wearable devices is desirable to aid in the diagnosis of many health-related conditions. Recently, we have developed an armband device that does not use obstructive leads, has dry electrodes which are convenient for long-term electrocardiogram (ECG) recording, and has been shown to be an effective alternate approach for continuous ECG monitoring. However, motion artifacts (MA) due to electromyogram (EMG) contractions are acknowledged as the major challenge of an armband. In this study, we used a deep convolutional neural network denoising encoder-decoder (CNNDED) to enhance the accuracy of R-peak detection in MA-corrupted ECG recordings obtained by an armband device. We collected simultaneous 24-hour ECG recordings using both the armband device and a Holter monitor on 10 subjects. Each 10-sec ECG segment was converted to a time-frequency representation and subsequently used as the input to CNNDED. During the training process, the model learned to accentuate the location of R peaks by amplifying their values in each ECG beat and suppressing the remaining waveforms. For the training output, the model used the R-peak location information from the simultaneously collected Holter ECG data, which were considered as the reference. The performance of CNNDED was evaluated on an independent test data set using the standard performance metrics. The mean relative error of the estimated HR with respect to the Holter data was 17.5 and 7.3 beats/min, pre- and post-CNNDED, respectively. The mean relative difference of the root mean square of successive difference values were 0.23 and 0.06 before and after applying CNNDED, respectively. Although further study is needed, the current preliminary results suggest that CNNDED can improve detection of R peaks even when they are completely buried in the presence of EMG artifacts.

A review of progress and an advanced method for shock advice algorithms in automated external defibrillators

Shock advice algorithm plays a vital role in the detection of sudden cardiac arrests on electrocardiogram signals and hence, brings about survival improvement by delivering prompt defibrillation. The last decade has witnessed a surge of research efforts in racing for efficient shock advice algorithms, in this context. On one hand, it has been reported that the classification performance of traditional threshold-based methods has not complied with the American Heart Association recommendations. On the other hand, the rise of machine learning and deep learning-based counterparts is paving the new ways for the development of intelligent shock advice algorithms. In this paper, we firstly provide a comprehensive survey on the development of shock advice algorithms for rhythm analysis in automated external defibrillators. Shock advice algorithms are categorized into three groups based on the classification methods in which the detection performance is significantly improved by the use of machine learning and/or deep learning techniques instead of threshold-based approaches. Indeed, in threshold-based shock advice algorithms, a parameter is calculated as a threshold to distinguish shockable rhythms from non-shockable ones. In contrast, machine learning-based methods combine multiple parameters of conventional threshold-based approaches as a set of features to recognize sudden cardiac arrest. Noticeably, those features are possibly extracted from stand-alone ECGs, alternative signals using various decomposition techniques, or fully augmented ECG segments. Moreover, these signals can be also used directly as the input channels of deep learning-based shock advice algorithm designs. Then, we propose an advanced shock advice algorithm using a support vector machine classifier and a feature set extracted from a fully augmented ECG segment with its shockable and non-shockable signals. The relatively high detection performance of the proposed shock advice algorithm implies a potential application for the automated external defibrillator in the practical clinic environment. Finally, we outline several interesting yet challenging research problems for further investigation.

Hybrid-Pattern Recognition Modeling with Arrhythmia Signal Processing for Ubiquitous Health Management

We established a web-based ubiquitous health management (UHM) system, "ECG4UHM", for processing ECG signals with AI-enabled models to recognize hybrid arrhythmia patterns, including atrial premature atrial complex (APC), atrial fibrillation (AFib), ventricular premature complex (VPC), and ventricular tachycardia (VT), versus normal sinus rhythm (NSR). The analytical model coupled machine learning methods, such as multiple layer perceptron (MLP), random forest (RF), support vector machine (SVM), and naive Bayes (NB), to process the hybrid patterns of four arrhythmia symptoms for AI computation. The data pre-processing used Hilbert-Huang transform (HHT) with empirical mode decomposition to calculate ECGs' intrinsic mode functions (IMFs). The area centroids of the IMFs' marginal Hilbert spectrum were suggested as the HHT-based features. We engaged the MATLAB^TM compiler and runtime server in the ECG4UHM to build the recognition modules for driving AI computation to identify the arrhythmia symptoms. The modeling extracted the crucial data sets from the MIT-BIH arrhythmia open database. The validated models, including the premature pattern (i.e., APC-VPC) and the fibril-rapid pattern (i.e., AFib-VT) against NSR, could reach the best area under the curve (AUC) of the receiver operating characteristic (ROC) of approximately 0.99. The models for all hybrid patterns, without VPC versus AFib and VT, achieved an average accuracy of approximately 90%. With the prediction test, the respective AUCs of the NSR and APC versus the AFib, VPC, and VT were 0.94 and 0.93 for the RF and SVM on average. The average accuracy and the AUC of the MLP, RF, and SVM models for APC-VT reached the value of 0.98. The self-developed system with AI computation modeling can be the backend of the intelligent social-health system that can recognize hybrid arrhythmia patterns in the UHM and home-isolated cares.

Automated Condition-Based Suppression of the CPR Artifact in ECG Data to Make a Reliable Shock Decision for AEDs during CPR

Cardiopulmonary resuscitation (CPR) corrupts the morphology of the electrocardiogram (ECG) signal, resulting in an inaccurate automated external defibrillator (AED) rhythm analysis. Consequently, most current AEDs prohibit CPR during the rhythm analysis period, thereby decreasing the survival rate. To overcome this limitation, we designed a condition-based filtering algorithm that consists of three stop-band filters which are turned either 'on' or 'off' depending on the ECG's spectral characteristics. Typically, removing the artifact's higher frequency peaks in addition to the highest frequency peak eliminates most of the ECG's morphological disturbance on the non-shockable rhythms. However, the shockable rhythms usually have dynamics in the frequency range of (3-6) Hz, which in certain cases coincide with CPR compression's harmonic frequencies, hence, removing them may lead to destruction of the shockable signal's dynamics. The proposed algorithm achieves CPR artifact removal without compromising the integrity of the shockable rhythm by considering three different spectral factors. The dataset from the PhysioNet archive was used to develop this condition-based approach. To quantify the performance of the approach on a separate dataset, three performance metrics were computed: the correlation coefficient, signal-to-noise ratio (SNR), and accuracy of Defibtech's shock decision algorithm. This dataset, containing 14 s ECG segments of different types of rhythms from 458 subjects, belongs to Defibtech commercial AED's validation set. The CPR artifact data from 52 different resuscitators were added to artifact-free ECG data to create 23,816 CPR-contaminated data segments. From this, 82% of the filtered shockable and 70% of the filtered non-shockable ECG data were highly correlated (>0.7) with the artifact-free ECG; this value was only 13 and 12% for CPR-contaminated shockable and non-shockable, respectively, without our filtering approach. The SNR improvement was 4.5 ± 2.5 dB, averaging over the entire dataset. Defibtech's rhythm analysis algorithm was applied to the filtered data. We found a sensitivity improvement from 67.7 to 91.3% and 62.7 to 78% for VF and rapid VT, respectively, and specificity improved from 96.2 to 96.5% and 91.5 to 92.7% for normal sinus rhythm (NSR) and other non-shockables, respectively.

Artificial Intelligence-Enabled ECG Algorithm Based on Improved Residual Network for Wearable ECG

Heart disease is the leading cause of death for men and women globally. The residual network (ResNet) evolution of electrocardiogram (ECG) technology has contributed to our understanding of cardiac physiology. We propose an artificial intelligence-enabled ECG algorithm based on an improved ResNet for a wearable ECG. The system hardware consists of a wearable ECG with conductive fabric electrodes, a wireless ECG acquisition module, a mobile terminal App, and a cloud diagnostic platform. The algorithm adopted in this study is based on an improved ResNet for the rapid classification of different types of arrhythmia. First, we visualize ECG data and convert one-dimensional ECG signals into two-dimensional images using Gramian angular fields. Then, we improve the ResNet-50 network model, add multistage shortcut branches to the network, and optimize the residual block. The ReLu activation function is replaced by a scaled exponential linear units (SELUs) activation function to improve the expression ability of the model. Finally, the images are input into the improved ResNet network for classification. The average recognition rate of this classification algorithm against seven types of arrhythmia signals (atrial fibrillation, atrial premature beat, ventricular premature beat, normal beat, ventricular tachycardia, atrial tachycardia, and sinus bradycardia) is 98.3%.

Deep Neural Network Approach for Continuous ECG-Based Automated External Defibrillator Shock Advisory System During Cardiopulmonary Resuscitation

Background Because chest compressions induce artifacts in the ECG, current automated external defibrillators instruct the user to stop cardiopulmonary resuscitation (CPR) while an automated rhythm analysis is performed. It has been shown that minimizing interruptions in CPR increases the chance of survival. Methods and Results The objective of this study was to apply a deep-learning algorithm using convolutional layers, residual networks, and bidirectional long short-term memory method to classify shockable versus nonshockable rhythms in the presence and absence of CPR artifact. Forty subjects' data from Physionet with 1131 shockable and 2741 nonshockable samples contaminated with 43 different CPR artifacts that were acquired from a commercial automated external defibrillator during asystole were used. We had separate data as train and test sets. Using our deep neural network model, the sensitivity and specificity of the shock versus no-shock decision for the entire data set over the 4-fold cross-validation sets were 95.21% and 86.03%, respectively. This result was based on the training and testing of the model using ECG data in both the presence and the absence of CPR artifact. For ECG without CPR artifact, the sensitivity was 99.04% and the specificity was 95.2%. A sensitivity of 94.21% and a specificity of 86.14% were obtained for ECG with CPR artifact. In addition to 4-fold cross-validation sets, we also examined leave-one-subject-out validation. The sensitivity and specificity for the case of leave-one-subject-out validation were 92.71% and 97.6%, respectively. Conclusions The proposed trained model can make shock versus nonshock decision in automated external defibrillators, regardless of CPR status. The results meet the American Heart Association's sensitivity requirement (>90%).

Insights Into the Spatiotemporal Patterns of Complexity of Ventricular Fibrillation by Multilead Analysis of Body Surface Potential Maps

Background

Ventricular fibrillation (VF) is the main cause of sudden cardiac death, but its mechanisms are still unclear. We propose a noninvasive approach to describe the progression of VF complexity from body surface potential maps (BSPMs).

Methods

We mapped 252 VF episodes (16 ± 10 s) with a 252-electrode vest in 110 patients (89 male, 47 ± 18 years): 50 terminated spontaneously, otherwise by electrical cardioversion (DCC). Changes in complexity were assessed between the onset (“VF start”) and the end (“VF end”) of VF by the nondipolar component index (NDI_BSPM), measuring the fraction of energy nonpreserved by an equivalent 3D dipole from BSPMs. Higher NDI reflected lower VF organization. We also examined other standard body surface markers of VF dynamics, including fibrillatory wave amplitude (A_BSPM), surface cycle length (BsCL_BSPM) and Shannon entropy (ShEn_BSPM). Differences between patients with and without structural heart diseases (SHD, 32 vs. NSHD, 78) were also tested at those stages. Electrocardiographic features were validated with simultaneous endocardium cycle length (CL) in a subset of 30 patients.

Results

All BSPM markers measure an increase in electrical complexity during VF (p < 0.0001), and more significantly in NSHD patients. Complexity is significantly higher at the end of sustained VF episodes requiring DCC. Intraepisode intracardiac CL shortening (VF start 197 ± 24 vs. VF end 169 ± 20 ms; p < 0.0001) correlates with an increase in NDI, and decline in surface CL, f-wave amplitude, and entropy (p < 0.0001). In SHD patients VF is initially more complex than in NSHD patients (NDI_BSPM, p = 0.0007; ShEn_BSPM, p < 0.0001), with moderately slower (BsCL_BSPM, p = 0.06), low-amplitude f-waves (A_BSPM, p < 0.0001). In this population, lower NDI (p = 0.004) and slower surface CL (p = 0.008) at early stage of VF predict self-termination. In the NSHD group, a more abrupt increase in VF complexity is quantified by all BSPM parameters during sustained VF (p < 0.0001), whereas arrhythmia evolution is stable during self-terminating episodes, hinting at additional mechanisms driving VF dynamics.

Conclusion

Multilead BSPM analysis underlines distinct degrees of VF complexity based on substrate characteristics.

Spectral Analysis and Mutual Information Estimation of Left and Right Intracardiac Electrograms during Ventricular Fibrillation

Ventricular fibrillation (VF) signals are characterized by highly volatile and erratic electrical impulses, the analysis of which is difficult given the complex behavior of the heart rhythms in the left (LV) and right ventricles (RV), as sometimes shown in intracardiac recorded Electrograms (EGM). However, there are few studies that analyze VF in humans according to the simultaneous behavior of heart signals in the two ventricles. The objective of this work was to perform a spectral and a non-linear analysis of the recordings of 22 patients with Congestive Heart Failure (CHF) and clinical indication for a cardiac resynchronization device, simultaneously obtained in LV and RV during induced VF in patients with a Biventricular Implantable Cardioverter Defibrillator (BICD) Contak Renewal IV^TM (Boston Sci.). The Fourier Transform was used to identify the spectral content of the first six seconds of signals recorded in the RV and LV simultaneously. In addition, measurements that were based on Information Theory were scrutinized, including Entropy and Mutual Information. The results showed that in most patients the spectral envelopes of the EGM sources of RV and LV were complex, different, and with several frequency peaks. In addition, the Dominant Frequency (DF) in the LV was higher than in the RV, while the Organization Index (OI) had the opposite trend. The entropy measurements were more regular in the RV than in the LV, thus supporting the spectral findings. We can conclude that basic stochastic processing techniques should be scrutinized with caution and from basic to elaborated techniques, but they can provide us with useful information on the biosignals from both ventricles during VF.

A Metaheuristic Optimization Approach for Parameter Estimation in Arrhythmia Classification from Unbalanced Data

The electrocardiogram records the heart's electrical activity and generates a significant amount of data. The analysis of these data helps us to detect diseases and disorders via heart bio-signal abnormality classification. In unbalanced-data contexts, where the classes are not equally represented, the optimization and configuration of the classification models are highly complex, reflecting on the use of computational resources. Moreover, the performance of electrocardiogram classification depends on the approach and parameter estimation to generate the model with high accuracy, sensitivity, and precision. Previous works have proposed hybrid approaches and only a few implemented parameter optimization. Instead, they generally applied an empirical tuning of parameters at a data level or an algorithm level. Hence, a scheme, including metrics of sensitivity in a higher precision and accuracy scale, deserves special attention. In this article, a metaheuristic optimization approach for parameter estimations in arrhythmia classification from unbalanced data is presented. We selected an unbalanced subset of those databases to classify eight types of arrhythmia. It is important to highlight that we combined undersampling based on the clustering method (data level) and feature selection method (algorithmic level) to tackle the unbalanced class problem. To explore parameter estimation and improve the classification for our model, we compared two metaheuristic approaches based on differential evolution and particle swarm optimization. The final results showed an accuracy of 99.95%, a F1 score of 99.88%, a sensitivity of 99.87%, a precision of 99.89%, and a specificity of 99.99%, which are high, even in the presence of unbalanced data.

Noise Detection in Electrocardiogram Signals for Intensive Care Unit Patients

Long term electrocardiogram (ECG) signals recorded in an intensive care unit (ICU) are often corrupted by severe motion and noise artifacts (MNA), which may lead to many false alarms including inaccurate detection of atrial fibrillation (AF). We developed an automated method to detect MNA from ECG recordings in the Medical Information Mart for Intensive Care (MIMIC) III database. Since AF detection is often based on identification of irregular RR intervals derived from the QRS complexes, the main design focus of our MNA detection algorithm was to identify corrupted QRS complexes of the ECG signals. The MNA in the MIMIC III database contain not only motion-induced noise, but also a plethora of non-ECG waveforms, which must also be automatically identified. Our algorithm is designed to first discriminate between ECG and non-ECG waveforms using both time and spectral-domain properties. For the segments of data containing ECG waveforms, a time-frequency spectrum and its sub-band decomposition approach were used to identify MNA, and high frequency noise ECG segments, respectively. The algorithm was tested on data from 35 subjects in normal sinus rhythm and 25 AF subjects. The proposed method is shown to accurately discriminate between segments that contained real ECG waveforms and those that did not, even though the latter were numerous in some subjects. In addition, we found a significant reduction (> 94%) in false positive detection of AF in normal subjects when our MNA detection algorithm was used. Without using it, we inaccurately detected AF owing to the MNA.

Detection of Ventricular Fibrillation Using the Image from Time-Frequency Representation and Combined Classifiers without Feature Extraction

Due the fact that the required therapy to treat Ventricular Fibrillation (V F) is aggressive (electric shock), the lack of a proper detection and recovering therapy could cause serious injuries to the patient or trigger a ventricular fibrillation, or even death. This work describes the development of an automatic diagnostic system for the detection of the occurrence of V F in real time by means of the time-frequency representation (T F R) image of the ECG. The main novelties are the use of the T F R image as input for a classification process, as well as the use of combined classifiers. The feature extraction stage is eliminated and, together with the use of specialized binary classifiers, this method improves the results of the classification. To verify the validity of the method, four different classifiers in different combinations are used: Regression Logistic with L2 Regularization (L 2 R L R), adaptive neural network (A N N C), Bagging (B A G G), and K-nearest neighbor (K N N). The Hierarchical Method (HM) and Voting Majority Method (VMM) combinations are used. ECG signals used for evaluation were obtained from the standard MIT-BIH and AHA databases. When the classifiers were combined, it was observed that the combination of B A G G , K N N , and A N N C using the Hierarchical Method (HM) gave the best results, with a sensitivity of 95.58 ± 0.41%, a 99.31 ± 0.08% specificity, a 98.6 ± 0.04% of overall accuracy, and a precision of 98.25 ± 0.29% for V F . Whereas a sensitivity of 94.02 ± 0.58%, a specificity of 99.31 ± 0.08%, an overall accuracy of 99.14 ± 0.43%, and a precision of 98.59 ± 0.09% was obtained for V T with a run time between 0.07 s and 0.12 s. Results show that the use of T F R image data to feed the combined classifiers yields a reduction in execution time with performance values above to those obtained by individual classifiers. This is of special utility for V F detection in real time.