An explainable artificial intelligence framework for trustworthy arrhythmia detection from heart rhythm data

An efficient ECG arrhythmia classification method based on Manta ray foraging optimization

An electrocardiogram (ECG) is a painless, noninvasive way to help diagnose numerous common heart problems. ECG plays an important role in diagnosing various Cardiac ailments. In recent years, Deep learning techniques have shown remarkable promise in achieving accurate and automated ECG arrhythmia classification. The primary goal of the system is to develop a robust and accurate system for the automated detection and classification of arrhythmias in electrocardiogram (ECG) data. By leveraging state-of-the-art techniques such as Convolutional Neural Networks (CNNs), we analyze pattern recognition within ECG signals to detect arrhythmias. Furthermore, we address the challenge of dataset scarcity by augmenting the data through nine different image cropping methods during the training phase. The implementation of techniques like Batch Normalization and data augmentation will further enhance the model's adaptability to diverse data sources, making it an invaluable tool for healthcare professionals. The CNN will be trained and tested using the ECG Dataset obtained from the MIT-BIH Database and from it, seven types of signals of arrhythmia will be classified. These seven signals are Premature Ventricular contractions (PVC), Paced beat (PAB), Right bundle branch block beat (RBB), Left bundle branch block beat (LBB), Atrial premature contraction (APC), Ventricular escape beat (VEB) and Normal beat. This system bridges the gap between advanced technology and healthcare, offering a transformative approach to ECG arrhythmia classification that has the potential to significantly improve patient outcomes and reduce the burden of manual diagnosis

The classification of electrocardiogram (ECG) signals is very important for the automatic diagnosis of heart disease. Traditionally, it is divided into two steps, including the step of feature extraction and the step of pattern classification. Owing to recent advances in artificial intelligence, it has been demonstrated that deep neural network, which trained on a huge amount of data, can carry out the task of feature extraction directly from the data and recognize cardiac arrhythmias better than professional cardiologists. This paper proposes an ECG arrhythmia classification method using two-dimensional (2D) deep convolutional neural network (CNN). The time domain signals of ECG, belonging to five heart beat types including normal beat (NOR), left bundle branch block beat (LBB), right bundle branch block beat (RBB), premature ventricular contraction beat (PVC), and atrial premature contraction beat (APC), were first transformed into time-frequency spectrograms by short-time Fourier transform. Subsequently, the spectrograms of the five arrhythmia types were utilized as input to the 2D-CNN such that the ECG arrhythmia types were identified and classified finally. Using ECG recordings from the MIT-BIH arrhythmia database as the training and testing data, the classification results show that the proposed 2D-CNN model can reach an averaged accuracy of 99.00%. On the other hand, in order to achieve optimal classification performances, the model parameter optimization was investigated. It was found when the learning rate is 0.001 and the batch size parameter is 2500, the classifier achieved the highest accuracy and the lowest loss. We also compared the proposed 2D-CNN model with a conventional one-dimensional CNN model. Comparison results show that the 1D-CNN classifier can achieve an averaged accuracy of 90.93%. Therefore, it is validated that the proposed CNN classifier using ECG spectrograms as input can achieve improved classification accuracy without additional manual pre-processing of the ECG signals.

BackgroundHeart disease diagnosis is a challenging task and it is important to explore useful information from the massive amount of electrocardiogram (ECG) records of patients. The high-precision diagnostic identification of ECG can save clinicians and cardiologists considerable time while helping reduce the possibility of misdiagnosis at the same time.Currently, some deep learning-based methods can effectively perform feature selection and classification prediction, reducing the consumption of manpower.MethodsIn this work, an end-to-end deep learning framework based on convolutional neural network (CNN) is proposed for ECG signal processing and arrhythmia classification. In the framework, a transformer network is embedded in CNN to capture the temporal information of ECG signals and a new link constraint is introduced to the loss function to enhance the classification ability of the embedding vector.ResultsTo evaluate the proposed method, extensive experiments based on real-world data were conducted. Experimental results show that the proposed model achieve better performance than most baselines. The experiment results also proved that the transformer network pays more attention to the temporal continuity of the data and captures the hidden deep features of the data well. The link constraint strengthens the constraint on the embedded features and effectively suppresses the effect of data imbalance on the results.ConclusionsIn this paper, an end-to-end model is used to process ECG signal and classify arrhythmia. The model combine CNN and Transformer network to extract temporal information in ECG signal and is capable of performing arrhythmia classification with acceptable accuracy. The model can help cardiologists perform assisted diagnosis of heart disease and improve the efficiency of healthcare delivery.

Cardiovascular diseases like arrhythmia are a significant health concern worldwide, affecting both elderly and young population due to lifestlye changes. Early diagnosis of cardiac arrhythmia using Electrocardiogram (ECG) by trained cardiologists is vital to prevent heart ailments and save lives. With the growth of wearable and standard ECG monitoring devices and a dearth of qualified cardiologists required to analyse the vast amounts of data collected, automated arrhythmia detection by Machine Learning (ML) and Deep Learning (DL) techniques have become very popular in recent years. In this study, we have reviewed the literature and described standard ML and DL studies in ECG arrhythmia classification. While ML techniques do demonstrate very good metrics, ML classifiers like SVM, knearest-neighbours, Decision Trees, etc. need preprocessing and hand-crafted feature extraction. DL methods which use networks like Convolutional Neural Networks (CNN), Long-Short-Term-Memory (LSTM) do not need any feature extraction as they automatically learn the features by themselves. Recent studies in DL have demonstrated very high performance metrics without the need for feature extraction. While some DL techniques do need noise filtering and determination of other features like the QRS complex, many of them can work with raw ECG signals and hence are ideally suited over their ML counterparts for real time ECG classification. DL networks can also be used as feature extractors and combined with ML classifiers. We thus conclude that state-of-the-art DL methods offer inherent advantages and flexibility over ML methods for automated arrhythmia classification. This review aggregates the niche features of leading ML and DL studies in this field which interested researchers can benefit from.

Effective compression and classification of ECG arrhythmia by singular value decomposition

Cardiovascular disease (CVD) has become one of the main diseases threatening human life and health. As an important tool for doctors to diagnose and analyze cardiovascular diseases, it is necessary to improve the accuracy of Electrocardiogram (ECG) classification. In this paper, we proposed a new network model called CSL-NET that uses a combination of convolutional neural network (CNN), SE block and long short-term memory (LSTM) for ECG signal processing and arrhythmia classification. The algorithm uses wavelet transform to filter the ECG signal, and then input it to CNN to extract ECG features automatically. An SE block is added to the end of CNN layer, in which, the extracted features are recalibrated to selectively emphasize useful features and suppress less relevant features. After that, input the data to the LSTM layer to extract the temporal information from the ECG signal. The experiment was performed on the ECG signal collected in the MIT-BIH database. Ultimately, the accuracy, sensitivity (recall rate), predicted value and F1 score of the CSL-NET model we proposed reached 99.52%, 98.23%, 99.22% and 98.93% respectively. Experimental results indicate that the proposed model has great potential for application in clinical practice, including wearable devices and intensive care units.

In this paper, the authors propose an improved convolutional neural network for automatic arrhythmia classification using Electro-Cardio-Gram (ECG) signal. It is essential to periodically monitor the heart beat arrhythmia to reduce the risk of death due to cardiovascular disease (CVD). The Visual Geometry Group network (VGGNet) is being widely used in computer vision problems. However, the same network cannot be used for classification of ECG beats as ECG signal is different from image signal in terms of dimensionality and inherent features. Thus, the authors investigated the effect of decreasing depth and width of a convolutional neural network in context of cardiac arrhythmia classification. In this paper, six configurations differing in depth and width are evaluated using benchmark MIT-BIH database. A deep network having thirteen convolution layers but with a smaller number of filters (reduced width) showed outstanding performance for the given problem. Based on the findings, the work is further extended to propose an improved convolutional neural network named as modified VGGNet (mVGGNet) for the task of ECG arrhythmia classification into four classes which are normal (N), ventricular ectopic beat (VEB), supraventricular ectopic beat (SVEB) and fusion beat (F). The hyper-parameters of the proposed architecture were optimized using sequential model based global optimization (SMBO) algorithm. The proposed architecture is evaluated using subjected-oriented patient-independent evaluation protocol. The performance is evaluated using five-fold cross-validation. The proposed mVGGNet achieved 98.79% and 99.16% accuracy for ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB) classification respectively. The proposed method resulted in higher specificity and precision as compared to other state-of-the-art algorithms. Thus, it can be effectively used for ECG arrhythmia classification.

In this work, we have proposed an electrocardiogram (ECG) arrhythmia classification method for short 12-lead ECG records to identify nine types (one normal type and eight abnormal types), using a 1D densely connected CNN which is a relatively novel convolutional neural network (CNN) model and shows outstanding performance in the field of pattern recognition. Firstly, noticing that ECG records are one dimensional time series with different noise levels, several wavelet-based shrinkage filtering methods were adopted to the ECG records for data augmentation. Secondly, each ECG record was divided into segments with a fixed length of 10 s, and the total number of segments for an ECG record is 10. And then, 10 segments were fed into an optimized 1D densely connected CNN for training. And lastly, a threshold vector was trained for the multi-label classification since each record may have more than one abnormal types. The approach has been validated against The First China ECG Intelligent Competition data set, obtaining a final F1 score of 0.873 and 0.863 on the validation set and test set, respectively.

Cardiovascular disease (CVD) has become the leading cause of death worldwide. As a widely used method for diagnosing CVD, currently electrocardiogram (ECG) monitoring tends to be implemented in wearable devices. This paper presents the prototype an ECG delineation and arrhythmia classification (EDAC) system suitable for wearable ECG biosensors. The proposed EDAC system is intended to be implemented after the electrodes and the analog front-end circuit, and its aim is signal processing at a low hardware overhead. The system consists of a Delta-modulator-based analog-to-feature converter (AFC), a corresponding ECG detection/delineation/feature extraction algorithm (DDF), an automatic gain controller (AGC) block, and a patient-dependent linear kernel support vector machine (SVM) classifier. The AFC converts the input analog signal into digital data of the slope and slope variation of the input signal, which is then used for detecting QRS complexes, localizing the fiducial points, and extracting the feature vectors for each heartbeat in the DDF block. At the same time, the AGC sends out a gain control signal based on the detected QRS complex to adjust the gain of the front-end amplifier. Finally, the SVM block performs arrhythmia classification. The EDAC system performance is evaluated using the MIT-BIH arrhythmia database. The system achieves 0.88% (0.93%), 99.1% (99.1%), 87.0% (92.8%), 99.6% (99.5%), and 89.3% (92.9%) in F1 score, accuracy, sensitivity, specificity, and positive predictive values of the supraventricular ectopic beats (ventricular ectopic beats) versus normal heartbeats classification while maintaining a low power dissipation ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.66~\mu \text{W}$ </tex-math></inline-formula> at 1 kHz operating frequency in the front-end AFC block). The proposed system is attractive to future wearable long-term ECG monitoring biosensors.

Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health. Research on electrocardiogram (ECG) signals offers valuable opportunities to address these issues. However, existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks. To address these challenges, this study developed a multi-resolution feature encoding network based on residual networks, which effectively extracted local morphological features and global rhythm features of ECG signals, thereby enhancing feature representation. Furthermore, a model compression-based continual learning method was proposed, enabling the structured transfer of knowledge from simpler tasks to more complex ones, resulting in improved performance in downstream tasks. The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets, including tasks such as ECG QRS complex detection, arrhythmia classification, and emotion classification. The continual learning method achieved significant improvements over conventional training approaches in cross-domain, cross-task, and incremental data scenarios. These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.

The electrocardiogram (ECG) is the most clinically accepted diagnostic tool used by physicians for interpreting the functional activity of the heart. The existing ECG machines require an expert-in-the-loop for identifying abnormalities in cardiac activity - commonly referred to as Arrhythmia - of a patient. The accuracy of diagnosis is directly dependent on the skill set of the physician; as a result, in rural and remote places, where no ECG specialist wants to relocate, the patients are unable to get any help in case of life threatening arrhythmias. In this paper, we investigate the suitability of evolutionary algorithms to discriminate a normal ECG from an abnormal one with minimum user intervention. Consequently, the human dependent errors are minimized. The intelligent framework is efficient and can be used for realtime ECG analysis to complement the diagnostic efficiency and accuracy of ECG specialists. Moreover, the system could also be used to raise early alarms for patients where no ECG specialist is available. In this paper, we aim at autonomously detecting six types of Arrhythmia: (1) Tachycardia, (2) Bradycardia, (3) Right Bundle Branch Block, (4) Left Bundle Branch Block, (5) Old Inferior Myocardial Infarction, and (6) Old Anterior Myocardial Infarction. We evaluate the accuracy of our system by selecting the best back end classifier from a set of 8 evolutionary classifiers. The results of our experiments show that our system is able to achieve more than 98% accuracy in detecting most types of Arrhythmia.

ABSTRACTCardiac arrhythmia refers to irregular heartbeats caused by anomalies in electrical transmission in the heart muscle, and it is an important threat to cardiovascular health. Conventional monitoring and diagnosis still depend on the laborious visual examination of electrocardiogram (ECG) devices, even though ECG signals are dynamic and complex. This paper discusses the need for an automated system to assist clinicians in efficiently recognizing arrhythmias. The existing machine‐learning (ML) algorithms have extensive training cycles and require manual feature selection; to eliminate this, we present a novel deep learning (DL) architecture. Our research introduces a novel approach to ECG classification by combining the vision transformer (ViT) and the capsule network (CapsNet) into a hybrid model named ViT‐Cap. We conduct necessary preprocessing operations, including noise removal and signal‐to‐image conversion using short‐time Fourier transform (SIFT) and continuous wavelet transform (CWT) algorithms, on both normal and abnormal ECG data obtained from the MIT‐BIH database. The proposed model intelligently focuses on crucial features by leveraging global and local attention to explore spectrogram and scalogram image data. Initially, the model divides the images into smaller patches and linearly embeds each patch. Features are then extracted using a transformer encoder, followed by classification using the capsule module with feature vectors from the ViT module. Comparisons with existing conventional models show that our proposed model outperforms the original ViT and CapsNet in terms of classification accuracy for both binary and multi‐class ECG classification. The experimental findings demonstrate an accuracy of 99% on both scalogram and spectrogram images. Comparative analysis with state‐of‐the‐art methodologies confirms the superiority of our framework. Additionally, we configure a field‐programmable gate array (FPGA) to implement the proposed model for real‐time arrhythmia classification, aiming to enhance user‐friendliness and speed. Despite numerous suggestions for high‐performance FPGA accelerators in the literature, our FPGA‐based accelerator utilizes optimization of loop parallelization, FP data, and multiply accumulation (MAC) unit. Our accelerator architecture achieves a 57% reduction in processing time and utilizes fewer resources compared to a floating‐point (FlP) design.

Globally, cardiovascular disease kills more than 500000 people every year, thus becoming the primary reason for death. Nevertheless, cardiovascular health monitoring is essential for accurate analysis and therapy of heart disease. In this work, a novel deep learning-based StrIppeD NAS-Network (SID-NASNet) for arrhythmia categorization into octa-classes with electrocardiogram (ECG) signals is presented. First, the ECG signals are recorded in real time using 12-lead electrodes. Then, the Discrete Wavelet Transform (DWT) is used to denoise the signals to reduce repetition and increase resilience. The noise-free ECG signals are fed into a K-means clustering algorithm to group ECG signal segments into a set number of clusters to identify patterns that may indicate heart abnormalities. Subsequently, the deep learning-based NASNet with Stripped convolutional layers is used to detect ECG irregularities of arrhythmia. Each sample point is examined for its local fractal dimension before extracting the heartbeat waveforms within a predetermined window length. A bio-inspired Dingo Optimization (DO) algorithm is used in the SID-NASNet to normalize the parameters to improve the efficiency of the network with low network complexity. The efficiency of the proposed SID-NASNet is assessed with specificity, accuracy, precision, F1 score and recall based on the MIT-BIH arrhythmia dataset. From the test results, the proposed SID-NASNet achieves an accuracy of 98.22% for effective categorization of ECG signals. The proposed SID-NASNet improves the overall accuracy of 1.24%, 3.76%, 1.87%, and 0.22% better than ECG-NET, Deep Learning (DL)-based GAN, 1D-CNN, and GAN-Long-Short Term Memory (LSTM), respectively.

We present a study of the nonlinear dynamics of electrocardiogram (ECG) signals for arrhythmia characterization. The correlation dimension and largest Lyapunov exponent are used to model the chaotic nature of five different classes of ECG signals. The model parameters are evaluated for a large number of real ECG signals within each class and the results are reported. The presented algorithms allow automatic calculation of the features. The statistical analysis of the calculated features indicates that they differ significantly between normal heart rhythm and the different arrhythmia types and, hence, can be rather useful in ECG arrhythmia detection. On the other hand, the results indicate that the discrimination between different arrhythmia types is difficult using such features. The results of this work are supported by statistical analysis that provides a clear outline for the potential uses and limitations of these features.