Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

Machine learning based detection of T-wave alternans in real ambulatory conditions

BACKGROUND AND OBJECTIVE

T-wave alternans (TWA) is a fluctuation in the repolarization morphology of the ECG. It is associated with cardiac instability and sudden cardiac death risk. Diverse methods have been proposed for TWA analysis. However, TWA detection in ambulatory settings remains a challenge due to the absence of standardized evaluation metrics and detection thresholds.

METHODS

In this work we use traditional TWA analysis signal processing-based methods for feature extraction, and two machine learning (ML) methods, namely, K-nearest-neighbor (KNN) and random forest (RF), for TWA detection, addressing hyper-parameter tuning and feature selection. The final goal is the detection in ambulatory recordings of short, non-sustained and sparse TWA events.

RESULTS

We train ML methods to detect a wide variety of alternant voltage from 20 to 100 μV, i.e., ranging from non-visible micro-alternans to TWA of higher amplitudes, to recognize a wide range in concordance to risk stratification. In classification, RF outperforms significantly the recall in comparison with the signal processing methods, at the expense of a small lost in precision. Despite ambulatory detection stands for an imbalanced category context, the trained ML systems always outperform signal processing methods.

CONCLUSIONS

We propose a comprehensive integration of multiple variables inspired by TWA signal processing methods to fed learning-based methods. ML models consistently outperform the best signal processing methods, yielding superior recall scores.

Deep Learning Model for Cosmetic Gel Classification Based on a Short-Time Fourier Transform and Spectrogram

Cosmetics and topical medications, such as gels, foams, creams, and lotions, are viscoelastic substances that are applied to the skin or mucous membranes. The human perception of these materials is complex and involves multiple sensory modalities. Traditional panel-based sensory evaluations have limitations due to individual differences in sensory receptors and factors such as age, race, and gender. Therefore, this study proposes a deep-learning-based method for systematically analyzing and effectively identifying the physical properties of cosmetic gels. Time-series friction signals generated by rubbing the gels were measured. These signals were preprocessed through short-time Fourier transform (STFT) and continuous wavelet transform (CWT), respectively, and the frequency factors that change over time were distinguished and analyzed. The deep learning model employed a ResNet-based convolution neural network (CNN) structure with optimization achieved through a learning rate scheduler. The optimized STFT-based 2D CNN model outperforms the CWT-based 2D and 1D CNN models. The optimized STFT-based 2D CNN model also demonstrated robustness and reliability through k-fold cross-validation. This study suggests the potential for an innovative approach to replace traditional expert panel evaluations and objectively assess the user experience of cosmetics.

Pulmonary Hypertension Detection Non-Invasively at Point-of-Care Using a Machine-Learned Algorithm

Artificial intelligence, particularly machine learning, has gained prominence in medical research due to its potential to develop non-invasive diagnostics. Pulmonary hypertension presents a diagnostic challenge due to its heterogeneous nature and similarity in symptoms to other cardiovascular conditions. Here, we describe the development of a supervised machine learning model using non-invasive signals (orthogonal voltage gradient and photoplethysmographic) and a hand-crafted library of 3298 features. The developed model achieved a sensitivity of 87% and a specificity of 83%, with an overall Area Under the Receiver Operator Characteristic Curve (AUC-ROC) of 0.93. Subgroup analysis showed consistent performance across genders, age groups and classes of PH. Feature importance analysis revealed changes in metrics that measure conduction, repolarization and respiration as significant contributors to the model. The model demonstrates promising performance in identifying pulmonary hypertension, offering potential for early detection and intervention when embedded in a point-of-care diagnostic system.

Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets

ECG classification or heartbeat classification is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of ECG signals assist human experts in the timely diagnosis of cardiac diseases and help save precious lives. This research aims at digitizing a dataset of images of ECG records into time series signals and then applying deep learning (DL) techniques on the digitized dataset. State-of-the-art DL techniques are proposed for the classification of the ECG signals into different cardiac classes. Multiple DL models, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a self-supervised learning (SSL)-based model using autoencoders are explored and compared in this study. The models are trained on the dataset generated from ECG plots of patients from various healthcare institutes in Pakistan. First, the ECG images are digitized, segmenting the lead II heartbeats, and then the digitized signals are passed to the proposed deep learning models for classification. Among the different DL models used in this study, the proposed CNN model achieves the highest accuracy of ∼92%. The proposed model is highly accurate and provides fast inference for real-time and direct monitoring of ECG signals that are captured from the electrodes (sensors) placed on different parts of the body. Using the digitized form of ECG signals instead of images for the classification of cardiac arrhythmia allows cardiologists to utilize DL models directly on ECG signals from an ECG machine for the real-time and accurate monitoring of ECGs.

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet

Introduction: Atrial fibrillation (AF) is the most common cardiac arrhythmia, which is clinically identified with irregular and rapid heartbeat rhythm. AF puts a patient at risk of forming blood clots, which can eventually lead to heart failure, stroke, or even sudden death. Electrocardiography (ECG), which involves acquiring bioelectrical signals from the body surface to reflect heart activity, is a standard procedure for detecting AF. However, the occurrence of AF is often intermittent, costing a significant amount of time and effort from medical doctors to identify AF episodes. Moreover, human error is inevitable, as even experienced medical professionals can overlook or misinterpret subtle signs of AF. As such, it is of critical importance to develop an advanced analytical model that can automatically interpret ECG signals and provide decision support for AF diagnostics. Methods: In this paper, we propose an innovative deep-learning method for automated AF identification using single-lead ECGs. We first extract time-frequency features from ECG signals using continuous wavelet transform (CWT). Second, the convolutional neural networks enhanced with residual learning (ReNet) are employed as the functional approximator to interpret the time-frequency features extracted by CWT. Third, we propose to incorporate a multi-branching structure into the ResNet to address the issue of class imbalance, where normal ECGs significantly outnumber instances of AF in ECG datasets. Results and Discussion: We evaluate the proposed Multi-branching Resnet with CWT (CWT-MB-Resnet) with two ECG datasets, i.e., PhysioNet/CinC challenge 2017 and ECGs obtained from the University of Oklahoma Health Sciences Center (OUHSC). The proposed CWT-MB-Resnet demonstrates robust prediction performance, achieving an F1 score of 0.8865 for the PhysioNet dataset and 0.7369 for the OUHSC dataset. The experimental results signify the model's superior capability in balancing precision and recall, which is a desired attribute for ensuring reliable medical diagnoses.

Enhanced multi-label cardiology diagnosis with channel-wise recurrent fusion

The timely detection of abnormal electrocardiogram (ECG) signals is vital for preventing heart disease. However, traditional automated cardiology diagnostic methods have the limitation of being unable to simultaneously identify multiple diseases in a segment of ECG signals, and do not consider the potential correlations between the 12-lead ECG signals. To address these issues, this paper presents a novel network architecture, denoted as Branched Convolution and Channel Fusion Network (BCCF-Net), designed for the multi-label diagnosis of ECG cardiology to achieve simultaneous identification of multiple diseases. Among them, the BCCF-Net incorporates the Channel-wise Recurrent Fusion (CRF) network, which is designed to enhance the ability to explore potential correlation information between 12 leads. Furthermore, the utilization of the squeeze and excitation (SE) attention mechanism maximizes the potential of the convolutional neural network (CNN). In order to efficiently capture complex patterns in space and time across various scales, the multi branch convolution (MBC) module has been developed. Through extensive experiments on two public datasets with seven subtasks, the efficacy and robustness of the proposed ECG multi-label classification framework have been comprehensively evaluated. The results demonstrate the superior performance of the BCCF-Net compared to other state-of-the-art algorithms. The developed framework holds practical application in clinical settings, allowing for the refined diagnosis of cardiac arrhythmias through ECG signal analysis.

Multi-Feature Automatic Extraction for Detecting Obstructive Sleep Apnea Based on Single-Lead Electrocardiography Signals

Obstructive sleep apnea (OSA), a prevalent sleep disorder, is intimately associated with various other diseases, particularly cardiovascular conditions. The conventional diagnostic method, nocturnal polysomnography (PSG), despite its widespread use, faces challenges due to its high cost and prolonged duration. Recent developments in electrocardiogram-based diagnostic techniques have opened new avenues for addressing these challenges, although they often require a deep understanding of feature engineering. In this study, we introduce an innovative method for OSA classification that combines a composite deep convolutional neural network model with a multimodal strategy for automatic feature extraction. This approach involves transforming the original dataset into scalogram images that reflect heart rate variability attributes and Gramian angular field matrix images that reveal temporal characteristics, aiming to enhance the diversity and richness of data features. The model comprises automatic feature extraction and feature enhancement components and has been trained and validated on the PhysioNet Apnea-ECG database. The experimental results demonstrate the model's exceptional performance in diagnosing OSA, achieving an accuracy of 96.37%, a sensitivity of 94.67%, a specificity of 97.44%, and an AUC of 0.96. These outcomes underscore the potential of our proposed model as an efficient, accurate, and convenient tool for OSA diagnosis.

Real-Time Myocardial Infarction Detection Approaches with a Microcontroller-Based Edge-AI Device

Myocardial Infarction (MI), commonly known as heart attack, is a cardiac condition characterized by damage to a portion of the heart, specifically the myocardium, due to the disruption of blood flow. Given its recurring and often asymptomatic nature, there is the need for continuous monitoring using wearable devices. This paper proposes a single-microcontroller-based system designed for the automatic detection of MI based on the Edge Computing paradigm. Two solutions for MI detection are evaluated, based on Machine Learning (ML) and Deep Learning (DL) techniques. The developed algorithms are based on two different approaches currently available in the literature, and they are optimized for deployment on low-resource hardware. A feasibility assessment of their implementation on a single 32-bit microcontroller with an ARM Cortex-M4 core was examined, and a comparison in terms of accuracy, inference time, and memory usage was detailed. For ML techniques, significant data processing for feature extraction, coupled with a simpler Neural Network (NN) is involved. On the other hand, the second method, based on DL, employs a Spectrogram Analysis for feature extraction and a Convolutional Neural Network (CNN) with a longer inference time and higher memory utilization. Both methods employ the same low power hardware reaching an accuracy of 89.40% and 94.76%, respectively. The final prototype is an energy-efficient system capable of real-time detection of MI without the need to connect to remote servers or the cloud. All processing is performed at the edge, enabling NN inference on the same microcontroller.

Template subtraction based methods for non-invasive fetal electrocardiography extraction

Assessment of fetal heart rate (fHR) through non-invasive fetal electrocardiogram (fECG) is challenging task. This study compares the performance of five template subtraction (TS) methods on Labor (12 5-min recordings) and Pregnancy datasets (10 20-min recordings). The methods include TS without adaptation, TS using singular value decomposition (TS[Formula: see text]), TS using linear prediction (TS[Formula: see text]), TS using scaling factor (TS[Formula: see text]), and sequential analysis (SA). The influence of the chosen maternal wavelet for the continuous wavelet transform (CWT) detector is also compared. The F1 score was used to measure performance. Each recording in both datasets consisted of four signals, resulting in a total comparison of 88 signals for the TS-based methods. The study reported the following results: F1 = 95.71% with TS, F1 = 95.93% with TS[Formula: see text], F1 = 95.30% with TS[Formula: see text], F1 = 95.82% with TS[Formula: see text], and F1 = 95.99% with SA. The study identified gaus3 as the suitable maternal wavelet for fetal R-peak detection using the CWT detector. Furthermore, the study classified signals from the tested datasets into categories of high, medium, and low quality, providing valuable insights for subsequent fECG signal extraction. This research contributes to advancing the understanding of non-invasive fECG signal processing and lays the groundwork for improving fetal monitoring in clinical settings.

An Interpretable Deep Learning Optimized Wearable Daily Detection System for Parkinson's Disease

Walking detection in the daily life of patients with Parkinson's disease (PD) is of great significance for tracking the progress of the disease. This study aims to implement an accurate, objective, and passive detection algorithm optimized based on an interpretable deep learning architecture for the daily walking of patients with PD and to explore the most representative spatiotemporal motor features. Five inertial measurement units attached to the wrist, ankle, and waist are used to collect motion data from 100 subjects during a 10-meter walking test. The raw data of each sensor are subjected to the continuous wavelet transform to train the classification model of the constructed 6-channel convolutional neural network (CNN). The results show that the sensor located at the waist has the best classification performance with an accuracy of 98.01%±0.85% and the area under the receiver operating characteristic curve (AUC) of 0.9981±0.0017 under ten-fold cross-validation. The gradient-weighted class activation mapping shows that the feature points with greater contribution to PD were concentrated in the lower frequency band (0.5~3Hz) compared with healthy controls. The visual maps of the 3D CNN show that only three out of the six time series have a greater contribution, which is used as a basis to further optimize the model input, greatly reducing the raw data processing costs (50%) while ensuring its performance (AUC=0.9929±0.0019). To the best of our knowledge, this is the first study to consider the visual interpretation-based optimization of an intelligent classification model in the intelligent diagnosis of PD.

Multi-classification method of arrhythmia based on multi-scale residual neural network and multi-channel data fusion

Since ECG contains key characteristic information of arrhythmias, extracting this information is crucial for identifying arrhythmias. Based on this, in order to effectively extract ECG data features and realize automatic detection of arrhythmia, a multi-classification method of arrhythmia based on multi-scale residual neural network and multi-channel data fusion is proposed. First, the features of single-lead ECG signals are extracted and converted into two-dimensional images, and the feature data sets are labeled and divided according to different types of arrhythmias. The improved residual neural network is trained on the training set to obtain the classification model of the neural network. Finally, the classification model is applied to the automatic detection of arrhythmias during exercise. The accuracy of the classification model of this method is as high as 99.60%, and it has high accuracy and generalization ability. The automatic identification of arrhythmia also contributes to the research and development of future wearable devices.

2D-WinSpatt-Net: A Dual Spatial Self-Attention Vision Transformer Boosts Classification of Tetanus Severity for Patients Wearing ECG Sensors in Low- and Middle-Income Countries

Tetanus is a life-threatening bacterial infection that is often prevalent in low- and middle-income countries (LMIC), Vietnam included. Tetanus affects the nervous system, leading to muscle stiffness and spasms. Moreover, severe tetanus is associated with autonomic nervous system (ANS) dysfunction. To ensure early detection and effective management of ANS dysfunction, patients require continuous monitoring of vital signs using bedside monitors. Wearable electrocardiogram (ECG) sensors offer a more cost-effective and user-friendly alternative to bedside monitors. Machine learning-based ECG analysis can be a valuable resource for classifying tetanus severity; however, using existing ECG signal analysis is excessively time-consuming. Due to the fixed-sized kernel filters used in traditional convolutional neural networks (CNNs), they are limited in their ability to capture global context information. In this work, we propose a 2D-WinSpatt-Net, which is a novel Vision Transformer that contains both local spatial window self-attention and global spatial self-attention mechanisms. The 2D-WinSpatt-Net boosts the classification of tetanus severity in intensive-care settings for LMIC using wearable ECG sensors. The time series imaging-continuous wavelet transforms-is transformed from a one-dimensional ECG signal and input to the proposed 2D-WinSpatt-Net. In the classification of tetanus severity levels, 2D-WinSpatt-Net surpasses state-of-the-art methods in terms of performance and accuracy. It achieves remarkable results with an F1 score of 0.88 ± 0.00, precision of 0.92 ± 0.02, recall of 0.85 ± 0.01, specificity of 0.96 ± 0.01, accuracy of 0.93 ± 0.02 and AUC of 0.90 ± 0.00.

DWT-CNNTRN: a Convolutional Transformer for ECG Classification with Discrete Wavelet Transform

Cardiovascular diseases are the leading cause of death worldwide. The diagnoses of cardiovascular diseases are usually carried out by cardiologists utilizing Electrocardiograms (ECGs). To assist these physicians in making an accurate diagnosis, there is a growing need for reliable and automatic ECG classifiers.In this study, a new method is proposed to classify 12-lead ECG recordings. The proposed model is composed of four components: the CNN(Convolutional Neural Network) module, the transformer module, the global hybrid pooling layer, and a classification layer. To improve the classification performance, the model takes the discrete wavelet transform of ECG signals as the model inputs and utilizes a hybrid pooling layer to condense the most important features over each period.The proposed model is evaluated using the test set of the China Physiological Signal Challenge 2018 dataset with 12-lead ECGs. It performs with an average accuracy of 0.86 and an average F1-scores of 0.83. The scores are particularly good for the block conditions (LBBB, RBBB, I-AVB). The main advantage of the proposed model is that, it obtains good results with a significantly smaller number of parameters compared to other individual and ensemble models.Clinical relevance- This work establishes a new ECG classifier model with high performance and low model size. It can make automatic ECG analysis more accessible, efficient, and accurate, especially in remote or underserved areas.

[An image classification method for arrhythmias based on Gramian angular summation field and improved Inception-ResNet-v2]

Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.

Multimodal Deep Learning for Predicting Adverse Birth Outcomes Based on Early Labour Data

Cardiotocography (CTG) is a widely used technique to monitor fetal heart rate (FHR) during labour and assess the health of the baby. However, visual interpretation of CTG signals is subjective and prone to error. Automated methods that mimic clinical guidelines have been developed, but they failed to improve detection of abnormal traces. This study aims to classify CTGs with and without severe compromise at birth using routinely collected CTGs from 51,449 births at term from the first 20 min of FHR recordings. Three 1D-CNN and LSTM based architectures are compared. We also transform the FHR signal into 2D images using time-frequency representation with a spectrogram and scalogram analysis, and subsequently, the 2D images are analysed using a 2D-CNNs. In the proposed multi-modal architecture, the 2D-CNN and the 1D-CNN-LSTM are connected in parallel. The models are evaluated in terms of partial area under the curve (PAUC) between 0-10% false-positive rate; and sensitivity at 95% specificity. The 1D-CNN-LSTM parallel architecture outperformed the other models, achieving a PAUC of 0.20 and sensitivity of 20% at 95% specificity. Our future work will focus on improving the classification performance by employing a larger dataset, analysing longer FHR traces, and incorporating clinical risk factors.

A Review on the Applications of Time-Frequency Methods in ECG Analysis

The joint time-frequency analysis method represents a signal in both time and frequency. Thus, it provides more information compared to other one-dimensional methods. Several researchers recently used time-frequency methods such as the wavelet transform, short-time Fourier transform, empirical mode decomposition and reported impressive results in various electrophysiological studies. The current review provides comprehensive knowledge about different time-frequency methods and their applications in various ECG-based analyses. Typical applications include ECG signal denoising, arrhythmia detection, sleep apnea detection, biometric identification, emotion detection, and driver drowsiness detection. The paper also discusses the limitations of these methods. The review will form a reference for future researchers willing to conduct research in the same field.

A Tiny Matched Filter-Based CNN for Inter-Patient ECG Classification and Arrhythmia Detection at the Edge

Automated electrocardiogram (ECG) classification using machine learning (ML) is extensively utilized for arrhythmia detection. Contemporary ML algorithms are typically deployed on the cloud, which may not always meet the availability and privacy requirements of ECG monitoring. Edge inference is an emerging alternative that overcomes the concerns of cloud inference; however, it poses new challenges due to the demanding computational requirements of modern ML algorithms and the tight constraints of edge devices. In this work, we propose a tiny convolutional neural network (CNN) classifier for real-time monitoring of ECG at the edge with the aid of the matched filter (MF) theory. The MIT-BIH dataset with inter-patient division is used for model training and testing. The model generalization capability is validated on the INCART, QT, and PTB diagnostic databases, and the model performance in the presence of noise is experimentally analyzed. The proposed classifier can achieve average accuracy, sensitivity, and F1 scores of 98.18%, 91.90%, and 92.17%, respectively. The sensitivity of detecting supraventricular and ventricular ectopic beats (SVEB and VEB) is 85.3% and 96.34%, respectively. The model is 15 KB in size, with an average inference time of less than 1 ms. The proposed model achieves superior classification and real-time performance results compared to the state-of-the-art ECG classifiers while minimizing the model complexity. The proposed classifier can be readily deployed on a wide range of resource-constrained edge devices for arrhythmia monitoring, which can save millions of cardiovascular disease patients.

Machine Learning approach for TWA detection relying on ensemble data design

Background and objective

T-wave alternans (TWA) is a fluctuation of the ST-T complex of the surface electrocardiogram (ECG) on an every-other-beat basis. It has been shown to be clinically helpful for sudden cardiac death stratification, though the lack of a gold standard to benchmark detection methods limits its application and impairs the development of alternative techniques. In this work, a novel approach based on machine learning for TWA detection is proposed. Additionally, a complete experimental setup is presented for TWA detection methods benchmarking.

Methods

The proposed experimental setup is based on the use of open-source databases to enable experiment replication and the use of real ECG signals with added TWA episodes. Also, intra-patient overfitting and class imbalance have been carefully avoided. The Spectral Method (SM), the Modified Moving Average Method (MMA), and the Time Domain Method (TM) are used to obtain input features to the Machine Learning (ML) algorithms, namely, K Nearest Neighbor, Decision Trees, Random Forest, Support Vector Machine and Multi-Layer Perceptron.

Results

There were not found large differences in the performance of the different ML algorithms. Decision Trees showed the best overall performance (accuracy 0.88 ± 0.04 , precision 0.89 ± 0.05 , Recall 0.90 ± 0.05 , F1 score 0.89 ± 0.03 ). Compared to the SM (accuracy 0.79, precision 0.93, Recall 0.64, F1 score 0.76) there was an improvement in every metric except for the precision.

Conclusions

In this work, a realistic database to test the presence of TWA using ML algorithms was assembled. The ML algorithms overall outperformed the SM used as a gold standard. Learning from data to identify alternans elicits a substantial detection growth at the expense of a small increment of the false alarm.

Advanced Time-Frequency Methods for ECG Waves Recognition

ECG wave recognition is one of the new topics where only one of the ECG beat waves (P-QRS-T) was used to detect heart diseases. Normal, tachycardia, and bradycardia heart rhythm are hard to detect using either time-domain or frequency-domain features solely, and a time-frequency analysis is required to extract representative features. This paper studies the performance of two different spectrum representations, iris-spectrogram and scalogram, for different ECG beat waves in terms of recognition of normal, tachycardia, and bradycardia classes. These two different spectra are then sent to two different deep convolutional neural networks (CNN), i.e., Resnet101 and ShuffleNet, for deep feature extraction and classification. The results show that the best accuracy for detection of beats rhythm was using ResNet101 and scalogram of T-wave with an accuracy of 98.3%, while accuracy was 94.4% for detection using iris-spectrogram using also ResNet101 and QRS-Wave. Finally, based on these results we note that using deep features from time-frequency representation using one wave of ECG beat we can accurately detect basic rhythms such as normal, tachycardia, and bradycardia.

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.

Deep arrhythmia classification based on SENet and lightweight context transform

Arrhythmia is one of the common cardiovascular diseases. Nowadays, many methods identify arrhythmias from electrocardiograms (ECGs) by computer-aided systems. However, computer-aided systems could not identify arrhythmias effectively due to various the morphological change of abnormal ECG data. This paper proposes a deep method to classify ECG samples. Firstly, ECG features are extracted through continuous wavelet transform. Then, our method realizes the arrhythmia classification based on the new lightweight context transform blocks. The block is proposed by improving the linear content transform block by squeeze-and-excitation network and linear transformation. Finally, the proposed method is validated on the MIT-BIH arrhythmia database. The experimental results show that the proposed method can achieve a high accuracy on arrhythmia classification.

A Denoising and Fourier Transformation-Based Spectrograms in ECG Classification Using Convolutional Neural Network

The non-invasive electrocardiogram (ECG) signals are useful in heart condition assessment and are found helpful in diagnosing cardiac diseases. However, traditional ways, i.e., a medical consultation required effort, knowledge, and time to interpret the ECG signals due to the large amount of data and complexity. Neural networks have been shown to be efficient recently in interpreting the biomedical signals including ECG and EEG. The novelty of the proposed work is using spectrograms instead of raw signals. Spectrograms could be easily reduced by eliminating frequencies with no ECG information. Moreover, spectrogram calculation is time-efficient through short-time Fourier transformation (STFT) which allowed to present reduced data with well-distinguishable form to convolutional neural network (CNN). The data reduction was performed through frequency filtration by taking a specific cutoff value. These steps makes architecture of the CNN model simple which showed high accuracy. The proposed approach reduced memory usage and computational power through not using complex CNN models. A large publicly available PTB-XL dataset was utilized, and two datasets were prepared, i.e., spectrograms and raw signals for binary classification. The highest accuracy of 99.06% was achieved by the proposed approach, which reflects spectrograms are better than the raw signals for ECG classification. Further, up- and down-sampling of the signals were also performed at various sampling rates and accuracies were attained.

A robust multiple heartbeats classification with weight-based loss based on convolutional neural network and bidirectional long short-term memory

Background: Analysis of electrocardiogram (ECG) provides a straightforward and non-invasive approach for cardiologists to diagnose and classify the nature and severity of variant cardiac diseases including cardiac arrhythmia. However, the interpretation and analysis of ECG are highly working-load demanding, and the subjective may lead to false diagnoses and heartbeats classification. In recent years, many deep learning works showed an excellent role in accurate heartbeats classification. However, the imbalance of heartbeat classes is universal in most of the available ECG databases since abnormal heartbeats are always relatively rare in real life scenarios. In addition, many existing approaches achieved prominent results by removing noise and extracting features in data preprocessing, which relies heavily on powerful computers. It is a pressing need to develop efficient and automatic light weighted algorithms for accurate heartbeats classification that can be used in portable ECG sensors. Objective: This study aims at developing a robust and efficient deep learning method, which can be embedded into wearable or portable ECG monitors for classifying heartbeats. Methods: We proposed a novel and light weighted deep learning architecture with weight-based loss based on a convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) that can automatically identify five types of ECG heartbeats according to the AAMI EC57 standard. It was also true that the raw ECG signals were simply segmented without noise removal and other feature extraction processing. Moreover, to tackle the challenge of classification bias due to imbalanced ECG datasets for different types of arrhythmias, we introduced a weight-based loss function to reduce the influence of over-weighted categories in the ECG dataset. For avoiding the influence of the division of validation dataset, k-fold method was adopted to improve the reliability of the model. Results: The proposed algorithm is trained and tested on MIT-BIH Arrhythmia Database, and achieves an average of 99.33% accuracy, 93.67% sensitivity, 99.18% specificity, 89.85% positive prediction, and 91.65% F₁ score.

Automated diagnosis of coronary artery disease using scalogram-based tensor decomposition with heart rate signals

Early identification of coronary artery disease (CAD) can facilitate timely clinical intervention and save lives. This study aims to develop a machine learning framework that uses tensor analysis on heart rate (HR) signals to automate the CAD detection task. A third-order tensor representing a time-frequency relationship is constructed by fusing scalograms as vertical slices of the tensor. Each scalogram is computed from the considered time frame of a given HR signal. The derived scalogram represents the heterogeneity of data as a two-dimensional map. These two-dimensional maps are stacked one after the other horizontally along the z-axis to form a 3-way tensor for each HR signal. Each two-dimensional map is represented as a vertical slice in the xy - plane. Tensor factorization of such a fused tensor for every HR signal is performed using canonical polyadic (CP) decomposition. Only the core factor is retained later, excluding the three unitary matrices to provide the latent feature set for the detection task. The resultant latent features are then fed to machine learning classifiers for binary classification. Bayesian optimization is performed in a five-fold cross-validation strategy in search of the optimal machine learning classifier. The experimental results yielded the accuracy, sensitivity, and specificity of 96.62%, 96.53%, and 96.67%, respectively, with the bagged trees ensemble method. The proposed tensor decomposition deciphered higher-order interrelations among the considered time-frequency representations of HR signals.

A Reparameterization Multifeature Fusion CNN for Arrhythmia Heartbeats Classification

Aiming at arrhythmia heartbeats classification, a novel multifeature fusion deep learning-based method is proposed. The stationary wavelet transforms (SWT) and RR interval features are firstly extracted. Based on the traditional one-dimensional convolutional neural network (1D-CNN), a parallel multibranch convolutional network is designed for training. The subband of SWT is input into the multiscale 1D-CNN separately. The output fused with RR interval features are fed to the fully connected layer for classification. To achieve the lightweight network while maintaining the powerful inference capability of the multibranch structure, the redundant branches of the network are removed by reparameterization. Experimental results and analysis show that it outperforms existing methods by many in arrhythmic heartbeat classification.

ECG Classification Based on Wasserstein Scalar Curvature

Electrocardiograms (ECG) analysis is one of the most important ways to diagnose heart disease. This paper proposes an efficient ECG classification method based on Wasserstein scalar curvature to comprehend the connection between heart disease and the mathematical characteristics of ECG. The newly proposed method converts an ECG into a point cloud on the family of Gaussian distribution, where the pathological characteristics of ECG will be extracted by the Wasserstein geometric structure of the statistical manifold. Technically, this paper defines the histogram dispersion of Wasserstein scalar curvature, which can accurately describe the divergence between different heart diseases. By combining medical experience with mathematical ideas from geometry and data science, this paper provides a feasible algorithm for the new method, and the theoretical analysis of the algorithm is carried out. Digital experiments on the classical database with large samples show the new algorithm's accuracy and efficiency when dealing with the classification of heart disease.

Electrocardiogram classification using TSST-based spectrogram and ConViT

As an important auxiliary tool of arrhythmia diagnosis, Electrocardiogram (ECG) is frequently utilized to detect a variety of cardiovascular diseases caused by arrhythmia, such as cardiac mechanical infarction. In the past few years, the classification of ECG has always been a challenging problem. This paper presents a novel deep learning model called convolutional vision transformer (ConViT), which combines vision transformer (ViT) with convolutional neural network (CNN), for ECG arrhythmia classification, in which the unique soft convolutional inductive bias of gated positional self-attention (GPSA) layers integrates the superiorities of attention mechanism and convolutional architecture. Moreover, the time-reassigned synchrosqueezing transform (TSST), a newly developed time-frequency analysis (TFA) method where the time-frequency coefficients are reassigned in the time direction, is employed to sharpen pulse traits for feature extraction. Aiming at the class imbalance phenomena in the traditional ECG database, the smote algorithm and focal loss (FL) are used for data augmentation and minority-class weighting, respectively. The experiment using MIT-BIH arrhythmia database indicates that the overall accuracy of the proposed model is as high as 99.5%. Furthermore, the specificity (Spe), F1-Score and positive Matthews Correlation Coefficient (MCC) of supra ventricular ectopic beat (S) and ventricular ectopic beat (V) are all more than 94%. These results demonstrate that the proposed method is superior to most of the existing methods.

A Parallel Cross Convolutional Recurrent Neural Network for Automatic Imbalanced ECG Arrhythmia Detection with Continuous Wavelet Transform

Automatic detection of arrhythmia using electrocardiogram (ECG) and deep learning (DL) is very important to reduce the global death rate from cardiovascular diseases (CVD). Previous studies on automatic arrhythmia detection relied largely on various ECG features and have achieved considerable classification accuracy using DL-based models. However, most previous research has ignored multi-class imbalanced problems in ECG arrhythmia detection. Therefore, it remains a challenge to improve the classification performance of the DL-based models. This paper proposes a novel parallel cross convolutional recurrent neural network in order to improve the arrhythmia detection performance of imbalanced ECG signals. The proposed model incorporates a recurrent neural network and a two-dimensional (2D) convolutional neural network (CNN) and can effectively learn temporal characteristics and rich spatial information of raw ECG signals. Continuous wavelet transform (CWT) is used to transform the ECG signals into a 2D scalogram composed of time-frequency components, and subsequently, the 2D-CNN can learn spatial information from the 2D scalogram. The proposed model is not only efficient in learning features with imbalanced samples but can also significantly improve model convergence with higher accuracy. The overall performance of our proposed model is evaluated based on the MIT-BIH arrhythmia dataset. Detailed analysis of evaluation metrics reveals that the proposed model is very effective in arrhythmia detection and significantly better than the existing hierarchical network models.

Environmental Benefits of Sleep Apnoea Detection in the Home Environment

Sleep Apnoea (SA) is a common chronic illness that affects nearly 1 billion people around the world, and the number of patients is rising. SA causes a wide range of psychological and physiological ailments that have detrimental effects on a patient’s wellbeing. The high prevalence and negative health effects make SA a public health problem. Whilst the current gold standard diagnostic procedure, polysomnography (PSG), is reliable, it is resource-expensive and can have a negative impact on sleep quality, as well as the environment. With this study, we focus on the environmental impact that arises from resource utilisation during SA detection, and we propose remote monitoring (RM) as a potential solution that can improve the resource efficiency and reduce travel. By reusing infrastructure technology, such as mobile communication, cloud computing, and artificial intelligence (AI), RM establishes SA detection and diagnosis support services in the home environment. However, there are considerable barriers to a widespread adoption of this technology. To gain a better understanding of the available technology and its associated strength, as well as weaknesses, we reviewed scientific papers that used various strategies for RM-based SA detection. Our review focused on 113 studies that were conducted between 2018 and 2022 and that were listed in Google Scholar. We found that just over 50% of the proposed RM systems incorporated real time signal processing and around 20% of the studies did not report on this important aspect. From an environmental perspective, this is a significant shortcoming, because 30% of the studies were based on measurement devices that must travel whenever the internal buffer is full. The environmental impact of that travel might constitute an additional need for changing from offline to online SA detection in the home environment.

Human activity recognition from textile electrocardiograms

Textile sensors for physiological signals bear the potential of unobtrusive and continuous application in daily life. Recently, textile electrocardiography (ECG) sensors became available which are of particular interest for physical activity monitoring due to the high effect of exercise on the heart rate. In this work, we evaluate the effectiveness of a single-lead ECG signal acquired using a non-medical-grade ECG shirt for human activity recognition (HAR). Healthy volunteers (N=10) wore the shirt during four different activities (sleeping, sitting, walking, running) in an uncontrolled environment and ECG data (256 Hz, 12 Bit) was stored, manually checked, and unusable segments (e.g. no sensor contact) were removed, resulting in a total of 228 hours of recording. Signals were split in short segments of different duration (10, 30, 60s), transformed using the Short-time Fourier Transform (STFT) to a spectrogram image and fed into a state-of-the-art convolutional neural network (CNN). The best configuration results in an F'l-Score of 73% and an accuracy of 77% on the test set. Results with leave-one-subject-out cross-validation show F'l-Scores ranging from 41 % to 80%. Thus, a single-lead, wearable-generated ECG has an informative value for HAR to a certain extent. In future work, we aim at using more sensors of the smart shirt and sensor fusion.

A data analytic end-to-end framework for the automated quantification of ergonomic risk factors across multiple tasks using a single wearable sensor

Existing ergonomic risk assessment tools require monitoring of multiple risk factors. To eliminate the direct observation, we investigated the effectiveness of an end-to-end framework that works with the data from a single wearable sensor. The framework is used to identify the performed task as the major contextual risk factor, and then estimate the task duration and number of repetitions as two main indicators of task intensity. For evaluation of the framework, we recruited 37 participants to complete 10 simulated work tasks in a laboratory setting. In testing, we achieved an average accuracy of 92% for task identification, 7.3% error in estimation of task duration, and 7.1% error for counting the number of task repetitions. Moreover, we showed the utility of the framework outputs in two ergonomic tools to estimate the risk of injury. Overall, we indicated the feasibility of using data from wearable sensors to automate the ergonomic risk assessment in workplaces.

DE-PNN: Differential Evolution-Based Feature Optimization with Probabilistic Neural Network for Imbalanced Arrhythmia Classification

In this research, a heartbeat classification method is presented based on evolutionary feature optimization using differential evolution (DE) and classification using a probabilistic neural network (PNN) to discriminate between normal and arrhythmic heartbeats. The proposed method follows four steps: (1) preprocessing, (2) heartbeat segmentation, (3) DE feature optimization, and (4) PNN classification. In this method, we have employed direct signal amplitude points constituting the heartbeat acquired from the ECG holter device with no secondary feature extraction step usually used in case of hand-crafted, frequency transformation or other features. The heartbeat types include normal, left bundle branch block, right bundle branch block, premature ventricular contraction, atrial premature, ventricular escape, ventricular flutter and paced beat. Using ECG records from the MIT-BIH, heartbeats are identified to start at 250 ms before and end at 450 ms after the respective R-peak positions. In the next step, the DE method is applied to reduce and optimize the direct heartbeat features. Although complex and highly computational ECG heartbeat classification algorithms have been proposed in the literature, they failed to achieve high performance in detecting some minority heartbeat categories, especially for imbalanced datasets. To overcome this challenge, we propose an optimization step for the deep CNN model using a novel classification metric called the Matthews correlation coefficient (MCC). This function focuses on arrhythmia (minority) heartbeat classes by increasing their importance. Maximum MCC is used as a fitness function to identify the optimum combination of features for the uncorrelated and non-uniformly distributed eight beat class samples. The proposed DE-PNN scheme can provide better classification accuracy considering 8 classes with only 36 features optimized from a 253 element feature set implying an 85.77% reduction in direct amplitude features. Our proposed method achieved overall 99.33% accuracy, 94.56% F1, 93.84% sensitivity, and 99.21% specificity.

Automatic ECG analysis system with hybrid optimization algorithm based feature selection and classifier

Cardio vascular disease threatens human life with higher mortality rate. Therefore it is quite important to monitor. An arrhythmia is an abnormal heart beat and rhythm which causes the disease. The best tool to find the heart rhythm of heart is Electro Cardiogram (ECG) which provides information about the different types of arrhythmias. This paper aims at proposing an automatic framework by employing multi-domain features to classify ECG signals. Proposed work uses optimum method of feature selection to improvise the efficiency of the classification process. A hybrid optimization algorithm is used for feature selection and proposed to optimize the parameters of the existing Support Vector Machine (SVM) classifier. Proposed hybrid optimization algorithm was developed using Particle Swarm Optimization (PSO) and Migration Modified Biogeography Based Optimization (MMBBO) algorithm. Algorithm provides an improved solution to the optimizing the parameters of ECG signals. Results are evaluated by implementing in MATLAB software and the performance is justified with comparative analysis. The proposed framework enhances the process of automatic prediction of various arrhythmias or rhythm abnormalities which performs in gaining better accuracy. For data sets, the average classification accuracy of this method is 97.89%. This result is an improvement of 4–5% over the comparison of other methods.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

A Powerful Paradigm for Cardiovascular Risk Stratification Using Multiclass, Multi-Label, and Ensemble-Based Machine Learning Paradigms: A Narrative Review

Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

A Shallow Domain Knowledge Injection (SDK-Injection) Method for Improving CNN-Based ECG Pattern Classification

ECG pattern classification for identifying the progress status of various heart diseases is a typical nonlinear problem. Therefore, deep learning-based automatic ECG diagnosis is being widely studied, and for this purpose, the CNN is mainly used to classify ECG patterns. In this case, it is hard to expect any further improvement in accuracy after optimizing the parameters. We propose a shallow domain knowledge injection method that can improve the accuracy of the existing parameter-optimized CNN. The proposed method can improve the accuracy by effectively injecting shallow domain knowledge, that can be acquired by non-medical experts, into the existing parameter-optimized CNN. The experiments show that the proposed method can be applied to both heart disease diagnoses and general ECG classification tasks, while improving the existing accuracy for both types of tasks.

Application of Internet of Things on the Healthcare Field Using Convolutional Neural Network Processing

Population at risk can benefit greatly from remote health monitoring because it allows for early detection and treatment. Because of recent advances in Internet-of-Things (IoT) paradigms, such monitoring systems are now available everywhere. Due to the essential nature of the patients being monitored, these systems demand a high level of quality in aspects such as availability and accuracy. In health applications, where a lot of data are accessible, deep learning algorithms have the potential to perform well. In this paper, we develop a deep learning architecture called the convolutional neural network (CNN), which we examine in this study to see if it can be implemented. The study uses the IoT system with a centralised cloud server, where it is considered as an ideal input data acquisition module. The study uses cloud computing resources by distributing CNN operations to the servers with outsourced fitness functions to be performed at the edge. The results of the simulation show that the proposed method achieves a higher rate of classifying the input instances from the data acquisition tools than other methods. From the results, it is seen that the proposed CNN achieves an average accurate rate of 99.6% on training datasets and 86.3% on testing datasets.

An Automated System for ECG Arrhythmia Detection Using Machine Learning Techniques

The new advances in multiple types of devices and machine learning models provide opportunities for practical automatic computer-aided diagnosis (CAD) systems for ECG classification methods to be practicable in an actual clinical environment. This imposes the requirements for the ECG arrhythmia classification methods that are inter-patient. We aim in this paper to design and investigate an automatic classification system using a new comprehensive ECG database inter-patient paradigm separation to improve the minority arrhythmical classes detection without performing any features extraction. We investigated four supervised machine learning models: support vector machine (SVM), k-nearest neighbors (KNN), Random Forest (RF), and the ensemble of these three methods. We test the performance of these techniques in classifying: Normal beat (NOR), Left Bundle Branch Block Beat (LBBB), Right Bundle Branch Block Beat (RBBB), Premature Atrial Contraction (PAC), and Premature Ventricular Contraction (PVC), using inter-patient real ECG records from MIT-DB after segmentation and normalization of the data, and measuring four metrics: accuracy, precision, recall, and f1-score. The experimental results emphasized that with applying no complicated data pre-processing or feature engineering methods, the SVM classifier outperforms the other methods using our proposed inter-patient paradigm, in terms of all metrics used in experiments, achieving an accuracy of 0.83 and in terms of computational cost, which remains a very important factor in implementing classification models for ECG arrhythmia. This method is more realistic in a clinical environment, where varieties of ECG signals are collected from different patients.