Early detection of cardiovascular diseases is crucial for effective treatment and an electrocardiogram (ECG) is pivotal for diagnosis. The accuracy of Deep Learning based methods for ECG signal classification has progressed in recent years to reach cardiologist-level performance. In clinical settings, a cardiologist makes a diagnosis based on the standard 12-channel ECG recording. Automatic analysis of ECG recordings from a multiple-channel perspective has not been given enough attention, so it is essential to analyze an ECG recording from a multiple-channel perspective. We propose a model that leverages the multiple-channel information available in the standard 12-channel ECG recordings and learns patterns at the beat, rhythm, and channel level. The experimental results show that our model achieved a macro-averaged ROC-AUC score of 0.9216, mean accuracy of 88.85\%, and a maximum F1 score of 0.8057 on the PTB-XL dataset. The attention visualization results from the interpretable model are compared against the cardiologist's guidelines to validate the correctness and usability.
In recent years, deep learning has witnessed its blossom in the field of Electrocardiography (ECG) processing, outperforming traditional signal processing methods in various tasks, for example, classification, QRS detection, wave delineation. Although many neural architectures have been proposed in the literature, there is a lack of systematic studies and open-source libraries for ECG deep learning. In this paper, we propose a deep learning framework, named \texttt{torch\_ecg}, which gathers a large number of neural networks, both from literature and novel, for various ECG processing tasks. It establishes a convenient and modular way for automatic building and flexible scaling of the networks, as well as a neat and uniform way of organizing the preprocessing procedures and augmentation techniques for preparing the input data for the models. Besides, \texttt{torch\_ecg} provides benchmark studies using the latest databases, illustrating the principles and pipelines for solving ECG processing tasks and reproducing results from the literature. \texttt{torch\_ecg} offers the ECG research community a powerful tool meeting the growing demand for the application of deep learning techniques.
Objective: Global (inter-patient) ECG classification for arrhythmia detection over Electrocardiogram (ECG) signal is a challenging task for both humans and machines. The main reason is the significant variations of both normal and arrhythmic ECG patterns among patients. Automating this process with utmost accuracy is, therefore, highly desirable due to the advent of wearable ECG sensors. However, even with numerous deep learning approaches proposed recently, there is still a notable gap in the performance of global and patient-specific ECG classification performances. This study proposes a novel approach to narrow this gap and propose a real-time solution with shallow and compact 1D Self-Organized Operational Neural Networks (Self-ONNs). Methods: In this study, we propose a novel approach for inter-patient ECG classification using a compact 1D Self-ONN by exploiting morphological and timing information in heart cycles. We used 1D Self-ONN layers to automatically learn morphological representations from ECG data, enabling us to capture the shape of the ECG waveform around the R peaks. We further inject temporal features based on RR interval for timing characterization. The classification layers can thus benefit from both temporal and learned features for the final arrhythmia classification. Results: Using the MIT-BIH arrhythmia benchmark database, the proposed method achieves the highest classification performance ever achieved, i.e., 99.21% precision, 99.10% recall, and 99.15% F1-score for normal (N) segments; 82.19% precision, 82.50% recall, and 82.34% F1-score for the supra-ventricular ectopic beat (SVEBs); and finally, 94.41% precision, 96.10% recall, and 95.2% F1-score for the ventricular-ectopic beats (VEBs).
In clinics, doctors rely on electrocardiograms (ECGs) to assess severe cardiac disorders. Owing to the development of technology and the increase in health awareness, ECG signals are currently obtained by using medical and commercial devices. Deep neural networks (DNNs) can be used to analyze these signals because of their high accuracy rate. However, researchers have found that adversarial attacks can significantly reduce the accuracy of DNNs. Studies have been conducted to defend ECG-based DNNs against traditional adversarial attacks, such as projected gradient descent (PGD), and smooth adversarial perturbation (SAP) which targets ECG classification; however, to the best of our knowledge, no study has completely explored the defense against adversarial attacks targeting ECG classification. Thus, we did different experiments to explore the effects of defense methods against white-box adversarial attack and black-box adversarial attack targeting ECG classification, and we found that some common defense methods performed well against these attacks. Besides, we proposed a new defense method called Adversarial Distillation Training (ADT) which comes from defensive distillation and can effectively improve the generalization performance of DNNs. The results show that our method performed more effectively against adversarial attacks targeting on ECG classification than the other baseline methods, namely, adversarial training, defensive distillation, Jacob regularization, and noise-to-signal ratio regularization. Furthermore, we found that our method performed better against PGD attacks with low noise levels, which means that our method has stronger robustness.
Cardiovascular disease has become one of the most significant threats endangering human life and health. Recently, Electrocardiogram (ECG) monitoring has been transformed into remote cardiac monitoring by Holter surveillance. However, the widely used Holter can bring a great deal of discomfort and inconvenience to the individuals who carry them. We developed a new wireless ECG patch in this work and applied a deep learning framework based on the Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) models. However, we find that the models using the existing techniques are not able to differentiate two main heartbeat types (Supraventricular premature beat and Atrial fibrillation) in our newly obtained dataset, resulting in low accuracy of 58.0 %. We proposed a semi-supervised method to process the badly labelled data samples with using the confidence-level-based training. The experiment results conclude that the proposed method can approach an average accuracy of 90.2 %, i.e., 5.4 % higher than the accuracy of conventional ECG classification methods.
Cardiovascular disease is a large worldwide healthcare issue; symptoms often present suddenly with minimal warning. The electrocardiogram (ECG) is a fast, simple and reliable method of evaluating the health of the heart, by measuring electrical activity recorded through electrodes placed on the skin. ECGs often need to be analyzed by a cardiologist, taking time which could be spent on improving patient care and outcomes. Because of this, automatic ECG classification systems using machine learning have been proposed, which can learn complex interactions between ECG features and use this to detect abnormalities. However, algorithms built for this purpose often fail to generalize well to unseen data, reporting initially impressive results which drop dramatically when applied to new environments. Additionally, machine learning algorithms suffer a "black-box" issue, in which it is difficult to determine how a decision has been made. This is vital for applications in healthcare, as clinicians need to be able to verify the process of evaluation in order to trust the algorithm. This paper proposes a method for visualizing model decisions across each class in the MIT-BIH arrhythmia dataset, using adapted saliency maps averaged across complete classes to determine what patterns are being learned. We do this by building two algorithms based on state-of-the-art models. This paper highlights how these maps can be used to find problems in the model which could be affecting generalizability and model performance. Comparing saliency maps across complete classes gives an overall impression of confounding variables or other biases in the model, unlike what would be highlighted when comparing saliency maps on an ECG-by-ECG basis.
Electrocardiography (ECG) is an effective and non-invasive diagnostic tool that measures the electrical activity of the heart. Interpretation of ECG signals to detect various abnormalities is a challenging task that requires expertise. Recently, the use of deep neural networks for ECG classification to aid medical practitioners has become popular, but their black box nature hampers clinical implementation. Several saliency-based interpretability techniques have been proposed, but they only indicate the location of important features and not the actual features. We present a novel interpretability technique called qLST, a query-based latent space traversal technique that is able to provide explanations for any ECG classification model. With qLST, we train a neural network that learns to traverse in the latent space of a variational autoencoder trained on a large university hospital dataset with over 800,000 ECGs annotated for 28 diseases. We demonstrate through experiments that we can explain different black box classifiers by generating ECGs through these traversals.
Electrocardiogram (ECG) is the most widely used diagnostic tool to monitor the condition of the human heart. By using deep neural networks (DNNs), interpretation of ECG signals can be fully automated for the identification of potential abnormalities in a patient's heart in a fraction of a second. Studies have shown that given a sufficiently large amount of training data, DNN accuracy for ECG classification could reach human-expert cardiologist level. However, despite of the excellent performance in classification accuracy, DNNs are highly vulnerable to adversarial noises that are subtle changes in the input of a DNN and may lead to a wrong class-label prediction. It is challenging and essential to improve robustness of DNNs against adversarial noises, which are a threat to life-critical applications. In this work, we proposed a regularization method to improve DNN robustness from the perspective of noise-to-signal ratio (NSR) for the application of ECG signal classification. We evaluated our method on PhysioNet MIT-BIH dataset and CPSC2018 ECG dataset, and the results show that our method can substantially enhance DNN robustness against adversarial noises generated from adversarial attacks, with a minimal change in accuracy on clean data.
This paper presents a new method to classify 1D signals using the signed cumulative distribution transform (SCDT). The proposed method exploits certain linearization properties of the SCDT to render the problem easier to solve in the SCDT space. The method uses the nearest subspace search technique in the SCDT domain to provide a non-iterative, effective, and simple to implement classification algorithm. Experiments show that the proposed technique outperforms the state-of-the-art neural networks using a very low number of training samples and is also robust to out-of-distribution examples on simulated data. We also demonstrate the efficacy of the proposed technique in real-world applications by applying it to an ECG classification problem. The python code implementing the proposed classifier can be found in PyTransKit (https://github.com/rohdelab/PyTransKit).
Despite the proliferation of numerous deep learning methods proposed for generic ECG classification and arrhythmia detection, compact systems with the real-time ability and high accuracy for classifying patient-specific ECG are still few. Particularly, the scarcity of patient-specific data poses an ultimate challenge to any classifier. Recently, compact 1D Convolutional Neural Networks (CNNs) have achieved the state-of-the-art performance level for the accurate classification of ventricular and supraventricular ectopic beats. However, several studies have demonstrated the fact that the learning performance of the conventional CNNs is limited because they are homogenous networks with a basic (linear) neuron model. In order to address this deficiency and further boost the patient-specific ECG classification performance, in this study, we propose 1D Self-organized Operational Neural Networks (1D Self-ONNs). Due to its self-organization capability, Self-ONNs have the utmost advantage and superiority over conventional ONNs where the prior operator search within the operator set library to find the best possible set of operators is entirely avoided. As the first study where 1D Self-ONNs are ever proposed for a classification task, our results over the MIT-BIH arrhythmia benchmark database demonstrate that 1D Self-ONNs can surpass 1D CNNs with a significant margin while having a similar computational complexity. Under AAMI recommendations and with minimal common training data used, over the entire MIT-BIH dataset 1D Self-ONNs have achieved 98% and 99.04% average accuracies, 76.6% and 93.7% average F1 scores on supra-ventricular and ventricular ectopic beat (VEB) classifications, respectively, which is the highest performance level ever reported.
We present our entry to the 2021 PhysioNet/CinC challenge - a waveform transformer model to detect cardiac abnormalities from ECG recordings. We compare the performance of the waveform transformer model on different ECG-lead subsets using approximately 88,000 ECG recordings from six datasets. In the official rankings, team prna ranked between 9 and 15 on 12, 6, 4, 3 and 2-lead sets respectively. Our waveform transformer model achieved an average challenge metric of 0.47 on the held-out test set across all ECG-lead subsets. Our combined performance across all leads placed us at rank 11 out of 39 officially ranking teams.
Using smart wearable devices to monitor patients electrocardiogram (ECG) for real-time detection of arrhythmias can significantly improve healthcare outcomes. Convolutional neural network (CNN) based deep learning has been used successfully to detect anomalous beats in ECG. However, the computational complexity of existing CNN models prohibits them from being implemented in low-powered edge devices. Usually, such models are complex with lots of model parameters which results in large number of computations, memory, and power usage in edge devices. Network pruning techniques can reduce model complexity at the expense of performance in CNN models. This paper presents a novel multistage pruning technique that reduces CNN model complexity with negligible loss in performance compared to existing pruning techniques. An existing CNN model for ECG classification is used as a baseline reference. At 60% sparsity, the proposed technique achieves 97.7% accuracy and an F1 score of 93.59% for ECG classification tasks. This is an improvement of 3.3% and 9% for accuracy and F1 Score respectively, compared to traditional pruning with fine-tuning approach. Compared to the baseline model, we also achieve a 60.4% decrease in run-time complexity.
This work aims to assess the reality and feasibility of the adversarial attack against cardiac diagnosis system powered by machine learning algorithms. To this end, we introduce adversarial beats, which are adversarial perturbations tailored specifically against electrocardiograms (ECGs) beat-by-beat classification system. We first formulate an algorithm to generate adversarial examples for the ECG classification neural network model, and study its attack success rate. Next, to evaluate its feasibility in a physical environment, we mount a hardware attack by designing a malicious signal generator which injects adversarial beats into ECG sensor readings. To the best of our knowledge, our work is the first in evaluating the proficiency of adversarial examples for ECGs in a physical setup. Our real-world experiments demonstrate that adversarial beats successfully manipulated the diagnosis results 3-5 times out of 40 attempts throughout the course of 2 minutes. Finally, we discuss the overall feasibility and impact of the attack, by clearly defining motives and constraints of expected attackers along with our experimental results.
The electrocardiogram (ECG) is one of the most widespread diagnostic tools in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a successful and popular technique to detect indications of disorders from an ECG signal. However, there are open questions around the robustness of these methods to various factors, including physiological ECG noise. In this study we generate clean and noisy versions of an ECG dataset before applying Symmetric Projection Attractor Reconstruction (SPAR) and scalogram image transformations. A pretrained convolutional neural network is trained using transfer learning to classify these image transforms. For the clean ECG dataset, F1 scores for SPAR attractor and scalogram transforms were 0.70 and 0.79, respectively, and the scores decreased by less than 0.05 for the noisy ECG datasets. Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. However, when the network trained on the noisy data was used to classify the clean dataset, the performance decrease was less than 0.05. We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing supervised networks for ECG classification.
ECG beats have a key role in the reduction of fatality rate arising from cardiovascular diseases (CVDs) by using Arrhythmia diagnosis computer-aided systems and get the important information from patient cardiac conditions to the specialist. However, the accuracy and speed of arrhythmia diagnosis are challenging in ECG classification systems, and the existence of noise, instability nature and imbalance in heartbeats challenged these systems. Accurate and on-time diagnosis of CVDs is a vital and important factor. So it has a significant effect on the treatment and recovery of patients. In this study, with the aim of accurate diagnosis of CVDs types, according to arrhythmia in ECG heartbeats, we implement an automatic ECG heartbeats classification by using discrete wavelet transformation on db2 mother wavelet and SMOTE oversampling algorithm as pre-processing level, and a classifier that consists of Convolutional neural network and BLSTM network. Then evaluate the proposed system on MIT-BIH imbalanced dataset, according to AAMI standards. The evaluations results show this approach with 50 epoch training achieved 99.78% accuracy for category F, 98.85% accuracy for category N, 99.43% accuracy for category S, 99.49% accuracy for category V, 99.87% accuracy for category Q. The source code is available at https://gitlab.com/arminshoughi/cnnlstmecg-classification. Our proposed classification system can be used as a tool for the automatic diagnosis of arrhythmia for CVDs specialists with the aim of primary screening of patients with heart arrhythmia.
Learning to classify time series with limited data is a practical yet challenging problem. Current methods are primarily based on hand-designed feature extraction rules or domain-specific data augmentation. Motivated by the advances in deep speech processing models and the fact that voice data are univariate temporal signals, in this paper, we propose Voice2Series (V2S), a novel end-to-end approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping. Leveraging the representation learning power of a large-scale pre-trained speech processing model, on 30 different time series tasks we show that V2S performs competitive results on 19 time series classification tasks. We further provide a theoretical justification of V2S by proving its population risk is upper bounded by the source risk and a Wasserstein distance accounting for feature alignment via reprogramming. Our results offer new and effective means to time series classification.
Arrhythmia is a cardiovascular disease that manifests irregular heartbeats. In arrhythmia detection, the electrocardiogram (ECG) signal is an important diagnostic technique. However, manually evaluating ECG signals is a complicated and time-consuming task. With the application of convolutional neural networks (CNNs), the evaluation process has been accelerated and the performance is improved. It is noteworthy that the performance of CNNs heavily depends on their architecture design, which is a complex process grounded on expert experience and trial-and-error. In this paper, we propose a novel approach, Heart-Darts, to efficiently classify the ECG signals by automatically designing the CNN model with the differentiable architecture search (i.e., Darts, a cell-based neural architecture search method). Specifically, we initially search a cell architecture by Darts and then customize a novel CNN model for ECG classification based on the obtained cells. To investigate the efficiency of the proposed method, we evaluate the constructed model on the MIT-BIH arrhythmia database. Additionally, the extensibility of the proposed CNN model is validated on two other new databases. Extensive experimental results demonstrate that the proposed method outperforms several state-of-the-art CNN models in ECG classification in terms of both performance and generalization capability.
The transformer based model (e.g., FusingTF) has been employed recently for Electrocardiogram (ECG) signal classification. However, the high-dimensional embedding obtained via 1-D convolution and positional encoding can lead to the loss of the signal's own temporal information and a large amount of training parameters. In this paper, we propose a new method for ECG classification, called low-dimensional denoising embedding transformer (LDTF), which contains two components, i.e., low-dimensional denoising embedding (LDE) and transformer learning. In the LDE component, a low-dimensional representation of the signal is obtained in the time-frequency domain while preserving its own temporal information. And with the low dimensional embedding, the transformer learning is then used to obtain a deeper and narrower structure with fewer training parameters than that of the FusingTF. Experiments conducted on the MIT-BIH dataset demonstrates the effectiveness and the superior performance of our proposed method, as compared with state-of-the-art methods.
Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity remains a central challenge in the field. Self-supervised learning represents a promising way to alleviate this issue. In this work, we put forward the first comprehensive assessment of self-supervised representation learning from clinical 12-lead ECG data. To this end, we adapt state-of-the-art self-supervised methods based on instance discrimination and latent forecasting to the ECG domain. In a first step, we learn contrastive representations and evaluate their quality based on linear evaluation performance on a recently established, comprehensive, clinical ECG classification task. In a second step, we analyze the impact of self-supervised pretraining on finetuned ECG classifiers as compared to purely supervised performance. For the best-performing method, an adaptation of contrastive predictive coding, we find a linear evaluation performance only 0.5% below supervised performance. For the finetuned models, we find improvements in downstream performance of roughly 1% compared to supervised performance, label efficiency, as well as robustness against physiological noise. This work clearly establishes the feasibility of extracting discriminative representations from ECG data via self-supervised learning and the numerous advantages when finetuning such representations on downstream tasks as compared to purely supervised training. As first comprehensive assessment of its kind in the ECG domain carried out exclusively on publicly available datasets, we hope to establish a first step towards reproducible progress in the rapidly evolving field of representation learning for biosignals.
Analyzing the inner mechanisms of deep neural networks is a fundamental task in machine learning. Existing work provides limited analysis or it depends on local theories, such as fixed-point analysis. In contrast, we propose to analyze trained neural networks using an operator theoretic approach which is rooted in Koopman theory, the Koopman Analysis of Neural Networks (KANN). Key to our method is the Koopman operator, which is a linear object that globally represents the dominant behavior of the network dynamics. The linearity of the Koopman operator facilitates analysis via its eigenvectors and eigenvalues. Our method reveals that the latter eigendecomposition holds semantic information related to the neural network inner workings. For instance, the eigenvectors highlight positive and negative n-grams in the sentiments analysis task; similarly, the eigenvectors capture the salient features of healthy heart beat signals in the ECG classification problem.