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.

Why do we keep missing left circumflex artery myocardial infarctions?

BACKGROUND

Diagnosis of left circumflex artery (LCx) myocardial infarctions via 12‑lead electrocardiogram (ECG) has posed a challenge to healthcare professionals for many years.

METHODS AND RESULTS

A retrospective observational study was performed to analyze patients admitted with myocardial infarction. The study used electronic medical records and specific ICD-10 codes to identify eligible patients, resulting in 2032 encounters. After independent adjudication of cardiac biomarkers, coronary angiography, and electrocardiographic changes, a final patient population of 58 encounters with acute occlusion myocardial infarction (OMI) with a culprit LCx lesion was established. OMI was defined as a lesion with either thrombolysis in myocardial infarction flow (TIMI) 0-2 or TIMI 3 with Troponin I > 1 ng/mL (Reference range 0.00-0.03 ng/mL). ECGs of these patients were then independently evaluated and grouped into 8 different classifications based on the presence or absence of ST elevation and/or depression in corresponding leads. ECG patterns and anatomical characteristics (proximal or distal to the first obtuse marginal artery) of the LCx lesions were then correlated. The appropriateness of triage and delay in reperfusion therapy were also assessed. Those with a left dominant or codominant circulation, and with LCx lesions proximal to the first obtuse marginal artery, were more likely to present with no or subtle ST-segment changes that led to delays in reperfusion therapy.

CONCLUSIONS

Patients with left or codominant coronary artery circulation, with OMI proximal to the first obtuse marginal artery, may be less likely to have "classic" findings of ST-segment elevation on ECG due to cancellation forces in the limb leads.

Analysis of sympathetic responses to cognitive stress and pain through skin sympathetic nerve activity and electrodermal activity

We explored the non-invasive evaluation of the sympathetic nervous system (SNS) by employing two distinct physiological signals: skin sympathetic nerve activity (SKNA), extracted from electrocardiogram (ECG) signals, and electrodermal activity (EDA), a well-studied marker in the context of the SNS assessment. Our investigation focused on cognitive stress and pain; two conditions closely associated with the SNS. We sought to determine if the information and dynamics of EDA could be derived from the novel SKNA signal. To this end, ECG and EDA signals were recorded simultaneously during three experiments aimed at sympathetic stimulation, Valsalva maneuver (VM), Stroop test, and thermal-grill pain test. We calculated the integral area under the rectified SKNA signal (iSKNA) and decomposed the EDA signal to its phasic component (EDAphasic). An average delay of more than 4.6 s was observed in the onset of EDAphasic bursts compared to their corresponding iSKNA bursts. After shifting the EDAphasic segments by the extent of this delay and smoothing the corresponding iSKNA bursts, our results revealed a strong average correlation coefficient of 0.85±0.14 between the iSKNA and EDAphasic bursts, indicating a noteworthy similarity between the two signals. We also reconstructed the EDA signals with time-varying sympathetic (TVSymp) and modified TVSymp (MTVSymp) methods. Then we extracted the following features from iSKNA, EDAphasic, TVSymp, and MTVSymp signals: peak amplitude, average amplitude (aSKNA), standard deviation (vSKNA), and the cumulative duration during which the signals had higher amplitudes than a specified threshold (HaSKNA). A strong average correlation of 0.89±0.18 was found between vSKNA and subjects' self-rated pain levels during the pain test. Our statistical analysis also included applying Linear Mixed-Effects Models to check if there were significant differences in features across baseline and different levels of SNS stimulation. We then assessed the discriminating power of the features using Area Under the Receiver Operating Characteristic Curve (AUROC) and Fisher's Ratio. Finally, using all the four EDA features, a multi-layer perceptron (MLP) classifier reached the classification accuracies 95.56%, 89.29%, and 67.88% for the VM, Stroop, and thermal-grill pain control and stimulation classes. On the other hand, the highest classification accuracies based on SKNA features were achieved using K-nearest neighbors (KNN) (98.89%), KNN (89.29%), and MLP (95.11%) classifiers for the same experiments. Our comparative analysis showed the feasibility of SKNA as a novel tool for assessing the SNS with accurate classification capability, with a faster onset of amplitude increase in response to SNS activity, compared to EDA.

An improved Bi-LSTM method based on heterogeneous features fusion and attention mechanism for ECG recognition

Electrocardiogram (ECG) plays a critical role in early prevention and diagnosis of cardiovascular diseases. However, extracting powerful deep features from ECG signal for recognition is still a challenging problem today due to the variable abnormal rhythms and noise distribution. This work proposes a Bi-LSTM algorithm based on heterogeneous features fusion and attention mechanism (HFFAM + Bi-LSTM). Combining the empirical features and the features learned by the deep learning network, HFFAM + Bi-LSTM can comprehensively extract the temporal frequency information and spatial structure information of the ECG signal. Meanwhile, a novel attention mechanism based on improved DTW (AM-DTW) is designed to analyze and control the fusion process of features. The role of AM-DTW in HFFAM + Bi-LSTM is twofold, one is to measure the feature similarity between ECG signal sets with different labels using the improved DTW, and the other is to distinguish the features into isomorphic and heterogeneous features as well as adaptive weighting of the features. It is worth mentioning that overly similar isomorphic features are filtered out to further optimize the algorithm. Thus, HFFAM + Bi-LSTM has the advantage of strengthening the heterogeneous information in the feature subspace while accounting for the isomorphic features. The accuracy of HFFAM + Bi-LSTM reaches up to 98.1 % and 97.1 % on the simulated and real datasets, respectively. Compared to the all benchmark models, the classification accuracy of HFFAM + Bi-LSTM is 1.3 % higher than the best. The experiments also demonstrate that HFFAM + Bi-LSTM has better performance compared with existing methods, which provides a new scheme for automatic detection of ECG signal.

A machine learning approach to differentiate wide QRS tachycardia: distinguishing ventricular tachycardia from supraventricular tachycardia

BACKGROUND

Differential diagnosis of wide QRS tachycardia (WQCT) has been a challenging issue. Published algorithms to distinguish ventricular tachycardia (VT) and supraventricular tachycardia (SVT) have limited diagnostic capabilities.

METHODS

A total of 278 patients with WQCT from January 2010 to March 2022 were enrolled. The electrophysiological study confirmed SVT in 154 patients and VT in 65 ones. Two hundred nineteen WQCT 12-lead ECGs were randomly divided into development cohort (n = 165) and testing cohort (n = 54) data sets. The development cohort was split into a training group (n = 115) and an internal validation group (n = 50). Forty ECG features extracted from the 219 WQCT ECGs are fed into 9 iteratively trained ML algorithms. This novel ML algorithm was also compared with four published algorithms.

RESULTS

In the development cohort, the Gradient Boosting Machine (GBM) model displayed the maximum area under curve (AUC) (0.91, 95% confidence interval (CI) 0.81-1.00). In the testing cohort, the GBM model had a higher AUC of 0.97 compared to 4 validated ECG algorithms, namely, Brugada (0.68), avR (0.62), RWPTII (0.72), and LLA algorithms (0.70). Accuracy, sensitivity, specificity, negative predictive value, and positive predictive value of the GBM model were 0.94, 0.97, 0.90, 0.94, and 0.95, respectively.

CONCLUSIONS

A GBM ML model contributes to distinguishing SVT from VT based on surface ECG features. In addition, we were able to identify important indicators for distinguishing WQCT.

Physiological measurements for driving drowsiness: A comparative study of multi-modality feature fusion and selection

A large number of traffic accidents were caused by drowsiness while driving. In-vehicle alert system based on physiological signals was one of the most promising solutions to monitor driving fatigue. However, different physiological modalities can be used, and many relative studies compared different modalities without considering the implementation feasibility of portable or wearable devices. Moreover, evaluations of each modality in previous studies were based on inconsistent choices of fatigue label and signal features, making it hard to compare the results of different studies. Therefore, the modality comparison and fusion for continuous drowsiness estimation while driving was still unclear. This work sought to comprehensively compare widely-used physiological modalities, including forehead electroencephalogram (EEG), electrooculogram (EOG), R-R intervals (RRI) and breath, in a hardware setting feasible for portable or wearable devices to monitor driving fatigue. Moreover, a more general conclusion on modality comparison and fusion was reached based on the regression of features or their combinations and the awake-to-drowsy transition. Finally, the feature subset of fused modalities was produced by feature selection method, to select the optimal feature combination and reduce computation consumption. Considering practical feasibility, the most effective combination with the highest correlation coefficient was using forehead EEG or EOG, along with RRI and RRI-derived breath. If more comfort and convenience was required, the combination of RRI and RRI-derived breath was also promising.

Multi-center atrial fibrillation electrocardiogram (ECG) classification using Fourier space convolutional neural networks (FD-CNN) and transfer learning

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching >85% accuracy for various cardiac pathologies. Despite the high accuracy at individual institutions, challenges remain when it comes to multi-center deployment. Transfer learning (TL) is a technique in which a model trained for a specific task is repurposed for another related task, in this case ECG ML model trained at one institution is fine-tuned to be utilized to classify ECGs at another institution. Models trained at one institution, however, might not be generalizable for accurate classification when deployed broadly due to differences in type, time, and sampling rate of traditional ECG acquisition. In this study, we evaluate the performance of time domain (TD) and frequency domain (FD) convolutional neural network (CNN) classification models in an inter-institutional scenario leveraging three different publicly available datasets. The larger PTB-XL ECG dataset was used to initially train TD and FD CNN models for atrial fibrillation (AFIB) classification. The models were then tested on two different data sets, Lobachevsky University Electrocardiography Database (LUDB) and Korea University Medical Center database (KURIAS). The FD model was able to retain most of its performance (>0.81 F1-score), whereas TD was highly affected (<0.53 F1-score) by the dataset variations, even with TL applied. The FD CNN showed superior robustness to cross-institutional variability and has potential for widespread application with no compromise to ECG classification performance.

Enhancing the performance of premature ventricular contraction detection in unseen datasets through deep learning with denoise and contrast attention module

Premature ventricular contraction (PVC) is a common and harmless cardiac arrhythmia that can be asymptomatic or cause palpitations and chest pain in rare instances. However, frequent PVCs can lead to more serious arrhythmias, such as atrial fibrillation. Several PVC detection models have been proposed to enable early diagnosis of arrhythmias; however, they lack reliability and generalizability due to the variability of electrocardiograms across different settings and noise levels. Such weaknesses are known to aggravate with new data. Therefore, we present a deep learning model with a novel attention mechanism that can detect PVC accurately, even on unseen electrocardiograms with various noise levels. Our method, called the Denoise and Contrast Attention Module (DCAM), is a two-step process that denoises signals with a convolutional neural network (CNN) in the frequency domain and attends to differences. It focuses on differences in the morphologies and intervals of the remaining beats, mimicking how trained clinicians identify PVCs. Using three different encoder types, we evaluated 1D U-Net with DCAM on six external test datasets. The results showed that DCAM significantly improved the F1-score of PVC detection performance on all six external datasets and enhanced the performance of balancing both the sensitivity and precision of the models, demonstrating its robustness and generalization ability regardless of the encoder type. This demonstrates the need for a trainable denoising process before applying the attention mechanism. Our DCAM could contribute to the development of a reliable algorithm for cardiac arrhythmia detection under real clinical electrocardiograms.

Environmental pollutant pre- and polyfluoroalkyl substances are associated with electrocardiogram parameters disorder in adults

Environmental pollutants exposure might disrupt cardiac function, but evidence about the associations of per- and polyfluoroalkyl substances (PFASs) exposure and cardiac conduction system remains sparse. To explore the associations between serum PFASs exposure and electrocardiogram (ECG) parameters changes in adults, we recruited 1229 participants (mean age: 55.1 years) from communities of Guangzhou, China. 13 serum PFASs with detection rate > 85% were analyzed finally. We selected 6 ECG parameters [heart rate (HR), PR interval, QRS duration, Bazett heart rate-corrected QT interval (QTc), QRS electric axis and RV5 + SV1 voltage] as outcomes. Generalized linear models (GLMs) and Bayesian kernel machine regression (BKMR) model were conducted to explore the associations of individual and joint PFASs exposure and ECG parameters changes, respectively. We detected significant associations of PFASs exposure with decreased HR, QRS duration, but with increased PR interval. For example, at the 95th percentile of 6:2 Cl-PFESA, HR and QRS duration were - 6.98 [95% confidence interval (CI): - 9.07, - 4.90] and - 6.54(95% CI: -9.05, -4.03) lower, but PR interval was 7.35 (95% CI: 3.52, 11.17) longer than those at the 25th percentile. Similarly, significant joint associations were observed in HR, PR interval and QRS duration when analyzed by BKMR model.

Characterization of noise in long-term ECG monitoring with machine learning based on clinical criteria

Noise and artifacts affect strongly the quality of the electrocardiogram (ECG) in long-term ECG monitoring (LTM), making some of its parts impractical for diagnosis. The clinical severity of noise defines a qualitative quality score according to the manner clinicians make the interpretation of the ECG, in contrast to assess noise from a quantitative standpoint. So clinical noise refers to a scale of different levels of qualitative severity of noise which aims at elucidating which ECG fragments are valid to achieve diagnosis from a clinical point of view, unlike the traditional approach, which assesses noise in terms of quantitative severity. This work proposes the use of machine learning (ML) techniques to categorize different qualitative noise severity using a database annotated according to a clinical noise taxonomy as gold standard. A comparative study is carried out using five representative ML methods, namely, K neareast neighbors, decision trees, support vector machine, single-layer perceptron, and random forest. The models are fed by signal quality indexes characterizing the waveform in time and frequency domains, as well as from a statistical viewpoint, to distinguish between clinically valid ECG segments from invalid ones. A solid methodology to prevent overfitting to both the dataset and the patient is developed, taking into account balance of classes, patient separation, and patient rotation in the test set. All the proposed learning systems have demonstrated good classification performance, attaining a recall, precision, and F1 score up to 0.78, 0.80, and 0.77, respectively, in the test set by a single-layer perceptron approach. These systems provide a classification solution for assessing the clinical quality of the ECG taken from LTM recordings. Graphical Abstract Clinical Noise Severity Classification based on Machine Learning techniques towards Long-Term ECG Monitoring.

Fourier space approach for convolutional neural network (CNN) electrocardiogram (ECG) classification: A proof-of-concept study

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching > 85% accuracy for various cardiac pathologies. Although the accuracy within institutions might be high, models trained at one institution might not be generalizable enough for accurate detection when deployed in other institutions due to differences in type of signal acquisition, sampling frequency, time of acquisition, device noise characteristics and number of leads. In this proof-of-concept study, we leverage the publicly available PTB-XL dataset to investigate the use of time-domain (TD) and frequency-domain (FD) convolutional neural networks (CNN) to detect myocardial infarction (MI), ST/T-wave changes (STTC), atrial fibrillation (AFIB) and sinus arrhythmia (SARRH). To simulate interinstitutional deployment, the TD and FD implementations were also compared on adapted test sets using different sampling frequencies 50 Hz, 100 Hz and 250 Hz, and acquisition times of 5 s and 10s at 100 Hz sampling frequency from the training dataset. When tested on the original sampling frequency and duration, the FD approach showed comparable results to TD for MI (0.92 FD - 0.93 TD AUROC) and STTC (0.94 FD - 0.95 TD AUROC), and better performance for AFIB (0.99 FD - 0.86 TD AUROC) and SARRH (0.91 FD - 0.65 TD AUROC). Although both methods were robust to changes in sampling frequency, changes in acquisition time were detrimental to the TD MI and STTC AUROCs, at 0.72 and 0.58 respectively. Alternatively, the FD approach was able to maintain the same level of performance, and, therefore, showed better potential for interinstitutional deployment.

A denoising method of ECG signal based on variational autoencoder and masked convolution

Wearable electrocardiogram (ECG) equipment can realize continuous monitoring of cardiovascular diseases, but these devices are more susceptible to interference from various noises, which will seriously reduce the diagnostic correctness. In this work, a novel noise reduction model for ECG signals is proposed based on variational autoencoder and masked convolution. The variational Bayesian inference is conducted to capture the global features of the ECG signals by encouraging the approximate posterior of the latent variables to fit the prior distribution, and we use the skip connection and feature concatenation to realize the information interaction across the channels. To strengthen the connection of local features of the ECG signals, the masked convolution module is used to extract local feature information, which supplement the global features and the noise reduction performance of whole model can be greatly improved. Experiments are carried out on the MIT-BIH arrythmia database, and the results display that the performance metrics of signal-to-noise ratio (SNR) and root mean square error (RMSE) are significantly improved compared with other approaches while causing less signal distortion.

Signal Quality Indices Evaluation for Robust ECG Signal Quality Assessment Systems

As the current healthcare system faces problems of budget, staffing, and equipment, telemedicine through wearable devices gives a means of solving them. However, their adoption by physicians is hampered by the quality of electrocardiogram (ECG) signals recorded outside the hospital setting. Due to the dynamic nature of the ECG and the noise that can occur in real-world conditions, Signal Quality Assessment (SQA) systems must use robust signal quality indices (SQIs). The aim of this study is twofold: to assess the robustness of the most commonly used SQIs and to report on their complexity in terms of computational speed. A total of 39 SQIs were explored, of which 16 were statistical, 7 were non-linear, 9 were frequency-based and 7 were based on QRS detectors. With 6 databases, we manually constructed 2 datasets containing many rhythms. Each signal was labelled as "acceptable" or "unacceptable" (subcategories: "motion artefacts", "electromyogram noise", "additive white Gaussian noise", or "power line interference"). Our results showed that the performance of an SQI in distinguishing a good signal from a bad one depends on the type of noise. Furthermore, 23 SQIs were found to be robust. The analysis of their extraction time on 10-second signals revealed that statistics-based and frequency domain-based SQIs are the least complex with an average computational time of (mean: 1.40 ms, standard deviation: 1.30 ms), and (mean: 4.31 ms, standard deviation: 4.50 ms), respectively. Then, our results provide a basis for choosing SQIs to develop more general and faster SQAs.

Automatic classification of arrhythmias using multi-branch convolutional neural networks based on channel-based attention and bidirectional LSTM

Cardiac arrhythmia is an abnormal rhythm of the heartbeat and can be life-threatening Electrocardiogram (ECG) is a technology that uses an electrocardiograph machine to record a graph of the changes in electrical activity produced by the heart at each cardiac cycle. ECG can generally be used to check whether the examinee has arrhythmia, ion channel disease, cardiomyopathy, electrolyte disorder and other diseases. To reduce the workload of doctors and improve the accuracy of ECG signal recognition, a novel and lightweight automatic ECG classification method based on Convolutional Neural Network (CNN) is proposed. The multi-branch network with different receptive fields is used to extract the multi-spatial deep features of heartbeats. The Channel Attention Module (CAM) and Bidirectional Long Short-Term Memory neural network (BLSTM) module are used to filter redundant ECG features. CAM and BLSTM are beneficial for distinguishing different categories of heartbeats. In the experiments, a four-fold cross-validation technique is used to improve the generalization capability of the network, and it shows good performance on the testing set. This method divides heartbeats into five categories according to the American Advancement of Medical Instrumentation (AAMI) criteria, which is validated in the MIT-BIH arrhythmia database. The sensitivity of this method to Ventricular Ectopic Beat (VEB) is 98.5% and the F1 score is 98.2%. The precision of the Supraventricular Ectopic Beat (SVEB) is 91.1%, and the corresponding F1 score is 90.8%. The proposed method has high classification performance and a lightweight feature. In a word, it has broad application prospects in clinical medicine and health testing.

Automated inter-patient arrhythmia classification with dual attention neural network

BACKGROUND AND OBJECTIVES

Arrhythmia classification based on electrocardiograms (ECG) can enhance clinical diagnostic efficiency. However, due to the significant differences in the number of different categories of heartbeats, the performance of classes with fewer samples in arrhythmia classification have not met expectations under the inter-patient paradigm. This paper aims to mitigate the adverse effects of category imbalance and improve arrhythmia classification performance.

METHODS

We constructed a novel dual attention hybrid network (DA-Net) for arrhythmia classification under sample imbalance, based on modified convolutional networks with channel attention (MCC-Net) and sequence-to-sequence network with global attention (Seq2Seq). The refined local features of the input heartbeat are first extracted by MCC-Net and then sent to Seq2Seq for further feature fusion. By applying local and global attention in the feature extraction and fusion parts, respectively, the method fully fuses low-level feature details and high-level context information and enhances the ability to extract discriminative features.

RESULTS

Based on the MIT-BIH arrhythmia database, under the inter-patient paradigm without any data augmentation methods, the proposed method achieved 99.98% accuracy (ACC) for five categories. The various performance indicators are as follows: Class N: sensitivity (SEN) = 99.96%, specificity (SPEC) = 99.93%, positive predictive value (PPV) = 99.99%; Class S: SEN = 99.67%, SPEC = 99.98%, PPV = 99.56%; Class V: SEN = 100%, SPEC = 99.99%, PPV = 99.91%; Class F: SEN = 100%, PPV = 99.98%, SPEC = 97.17%. In further experiments simulating extreme cases, the model still achieved ACC of 99.54% and 98.91% in the three-category and five-category categories when the training sample size was much smaller than the test sample.

CONCLUSIONS

Without any data augmentation methods, the proposed model not only alleviates the negative impact of class imbalance and achieves excellent performance in all categories but also provides a new approach for dealing with class imbalance in arrhythmia classification. Additionally, our method demonstrates potential in conditions with fewer samples.

A new deep convolutional neural network incorporating attentional mechanisms for ECG emotion recognition

Using ECG signals captured by wearable devices for emotion recognition is a feasible solution. We propose a deep convolutional neural network incorporating attentional mechanisms for ECG emotion recognition. In order to address the problem of individuality differences in emotion recognition tasks, we incorporate an improved Convolutional Block Attention Module (CBAM) into the proposed deep convolutional neural network. The deep convolutional neural network is responsible for capturing ECG features. Channel attention in CBAM is responsible for adding weight information to ECG features of different channels and spatial attention is responsible for the weighted representation of ECG features of different regions inside the channel. We used three publicly available datasets, WESAD, DREAMER, and ASCERTAIN, for the ECG emotion recognition task. The new state-of-the-art results are set in three datasets for multi-class classification results, WESAD for tri-class results, and ASCERTAIN for two-category results, respectively. A large number of experiments are performed, providing an interesting analysis of the design of the convolutional structure parameters and the role of the attention mechanism used. We propose to use large convolutional kernels to improve the effective perceptual field of the model and thus fully capture the ECG signal features, which achieves better performance compared to the commonly used small kernels. In addition, channel attention and spatial attention were added to the deep convolutional model separately to explore their contribution levels. We found that in most cases, channel attention contributed to the model at a higher level than spatial attention.

A dataset on the physiological state and behavior of drivers in conditionally automated driving

This dataset contains data of 346 drivers collected during six experiments conducted in a fixed-base driving simulator. Five studies simulated conditionally automated driving (L3-SAE), and the other one simulated manual driving (L0-SAE). The dataset includes physiological data (electrocardiogram (ECG), electrodermal activity (EDA), and respiration (RESP)), driving and behavioral data (reaction time, steering wheel angle, …), performance data of non-driving-related tasks, and questionnaire responses. Among them, measures from standardized questionnaires were collected, either to control the experimental manipulation of the driver's state, or to measure constructs related to human factors and driving safety (drowsiness, mental workload, affective state, situation awareness, situational trust, user experience). In the provided dataset, some raw data have been processed, notably physiological data from which physiological indicators (or features) have been calculated. The latter can be used as input for machine learning models to predict various states (sleep deprivation, high mental workload, ...) that may be critical for driver safety. Subjective self-reported measures can also be used as ground truth to apply regression techniques. Besides that, statistical analyses can be performed using the dataset, in particular to analyze the situational awareness or the takeover quality of drivers, in different states and different driving scenarios. Overall, this dataset contributes to better understanding and consideration of the driver's state and behavior in conditionally automated driving. In addition, this dataset stimulates and inspires research in the fields of physiological/affective computing and human factors in transportation, and allows companies from the automotive industry to better design adapted human-vehicle interfaces for safe use of automated vehicles on the roads.

Heart and brain traumatic stress biomarker analysis with and without machine learning: A scoping review

The enigma of post-traumatic stress disorder (PTSD) is embedded in a complex array of physiological responses to stressful situations that result in disruptions in arousal and cognitions that characterise the psychological disorder. Deciphering these physiological patterns is complex, which has seen the use of machine learning (ML) grow in popularity. However, it is unclear to what extent ML has been used with physiological data, specifically, the electroencephalogram (EEG) and electrocardiogram (ECG) to further understand the physiological responses associated with PTSD. To better understand the use of EEG and ECG biomarkers, with and without ML, a scoping review was undertaken. A total of 124 papers based on adult samples were identified comprising 19 ML studies involving EEG and ECG. A further 21 studies using EEG data, and 84 studies employing ECG meeting all other criteria but not employing ML were included for comparison. Identified studies indicate classical ML methodologies currently dominate EEG and ECG biomarkers research, with derived biomarkers holding clinically relevant diagnostic implications for PTSD. Discussion of the emerging trends, algorithms used and their success is provided, along with areas for future research.

Fuzz-ClustNet: Coupled fuzzy clustering and deep neural networks for Arrhythmia detection from ECG signals

Electrocardiogram (ECG) is a widely used technique to diagnose cardiovascular diseases. It is a non-invasive technique that represents the cyclic contraction and relaxation of heart muscles. ECG can be used to detect abnormal heart motions, heart attacks, heart diseases, or enlarged hearts by measuring the heart's electrical activity. Over the past few years, various works have been done in the field of studying and analyzing the ECG signals to detect heart diseases. In this work, we propose a deep learning and fuzzy clustering (Fuzz-ClustNet) based approach for Arrhythmia detection from ECG signals. We started by denoising the collected ECG signals to remove errors like baseline drift, power line interference, motion noise, etc. The denoised ECG signals are then segmented to have an increased focus on the ECG signals. We then perform data augmentation on the segmented images to counter the effects of the class imbalance. The augmented images are then passed through a CNN feature extractor. The extracted features are then passed to a fuzzy clustering algorithm to classify the ECG signals for their respective cardio diseases. We ran intensive simulations on two benchmarked datasets and evaluated various performance metrics. The performance of our proposed algorithm was compared with several recently proposed algorithms for heart disease detection from ECG signals. The obtained results demonstrate the efficacy of our proposed approach as compared to other contemporary algorithms.

Electrocardiogram (ECG)-Based User Authentication Using Deep Learning Algorithms

Personal authentication security is an essential area of research in privacy and cybersecurity. For individual verification, fingerprint and facial recognition have proved particularly useful. However, such technologies have flaws such as fingerprint fabrication and external impediments. Different AI-based technologies have been proposed to overcome forging or impersonating authentication concerns. Electrocardiogram (ECG)-based user authentication has recently attracted considerable curiosity from researchers. The Electrocardiogram is among the most reliable advanced techniques for authentication since, unlike other biometrics, it confirms that the individual is real and alive. This study utilizes a user authentication system based on electrocardiography (ECG) signals using deep learning algorithms. The ECG data are collected from users to create a unique biometric profile for each individual. The proposed methodology utilizes Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) to analyze the ECG data. The CNNs are trained to extract features from the ECG data, while the LSTM networks are used to model the temporal dependencies in the data. The evaluation of the performance of the proposed system is conducted through experiments. It demonstrates that it effectively identifies users based on their ECG data, achieving high accuracy rates. The suggested techniques obtained an overall accuracy of 98.34% for CNN and 99.69% for LSTM using the Physikalisch-Technische Bundesanstalt (PTB) database. Overall, the proposed system offers a secure and convenient method for user authentication using ECG data and deep learning algorithms. The approach has the potential to provide a secure and convenient method for user authentication in various applications.

ECG Changes during Adult Life in Fabry Disease: Results from a Large Longitudinal Cohort Study

Background: Fabry disease (FD) is an X-linked, lysosomal storage disorder leading to severe cardiomyopathy in a significant proportion of patients. To identify ECG markers that reflect early cardiac involvement and disease progression, we conducted a long term retrospective study in a large cohort of FD patients. Methods: A total of 1995 ECGs from 133 patients with classical FD (64% females, 80% treated with enzyme replacement therapy), spanning 20 years of follow-up, were compared to ECGs from 3893 apparently healthy individuals. Generalized linear mixed models were used to evaluate the effect of age, FD and sex on: P-wave duration, PR-interval, QRS-duration, QTc, Cornell index, spatial QRS-T angle and frontal QRS-axis. Regression slopes and absolute values for each parameter were compared between FD patients and control subjects. Results: At a younger age (<40 years), the Cornell index was higher and frontal QRS-axis more negative in FD patients compared to controls (p < 0.05). For the other ECG parameters, the rate of change, more than the absolute value, was greater in FD patients compared to controls (p < 0.05). From the fifth decade (men) or sixth (women) onwards, absolute values for P-wave duration, QRS-duration, QTc and spatial QRS-T angle were longer and higher in FD patients compared to control subjects. Conclusions: ECG abnormalities indicative of FD are age and sex dependent. Tracking the rate of change in ECG parameters could be a good way to detect disease progression, guiding treatment initiation. Moreover, monitoring ECG changes in FD can be used to evaluate the effectiveness of treatment.

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.

A joint cross-dimensional contrastive learning framework for 12-lead ECGs and its heterogeneous deployment on SoC

The utilization of unlabeled electrocardiogram (ECG) data is always a critical topic in artificial intelligence healthcare, as the manual annotation for ECG data is a time-consuming task that requires much medical expertise. The recent development of self-supervised learning, especially contrastive learning, has provided helpful inspirations to solve this problem. In this paper, a joint cross-dimensional contrastive learning algorithm for unlabeled 12-lead ECGs is proposed. Unlike existing studies about ECG contrastive learning, our algorithm can simultaneously exploit unlabeled 1-dimensional ECG signals and 2-dimensional ECG images. A cross-dimensional contrastive learning method enhances the interaction between 1-dimensional and 2-dimensional ECG data, resulting in a more effective self-supervised feature learning. Combining this cross-dimensional contrastive learning, a 1-dimensional contrastive learning with ECG-specific transformations is employed to constitute a joint model. To pre-train this joint model, a new hybrid contrastive loss balances the 2 algorithms and uniformly describes the pre-training target. In the downstream classification task, the features learned by our algorithm shows impressive advantages. Compared with other representative methods, it achieves a at least 5.99% increase in accuracy. For real-world applications, an efficient heterogenous deployment on a "system-on-a-chip" (SoC) is designed. According to our experiments, the model can process 12-lead ECGs in real-time on the SoC. Furthermore, this heterogenous deployment can achieve a 14 × faster inference than the pure software deployment on the same SoC. In summary, our algorithm is a good choice for unlabeled 12-lead ECG utilization, the proposed heterogenous deployment makes it more practical in real-world applications.

Electrocardiogram lead conversion from single-lead blindly-segmented signals

BACKGROUND

The standard configuration's set of twelve electrocardiogram (ECG) leads is optimal for the medical diagnosis of diverse cardiac conditions. However, it requires ten electrodes on the patient's limbs and chest, which is uncomfortable and cumbersome. Interlead conversion methods can reconstruct missing leads and enable more comfortable acquisitions, including in wearable devices, while still allowing for adequate diagnoses. Currently, methodologies for interlead ECG conversion either require multiple reference (input) leads and/or require input signals to be temporally aligned considering the ECG landmarks.

METHODS

Unlike the methods in the literature, this paper studies the possibility of converting ECG signals into all twelve standard configuration leads using signal segments from only one reference lead, without temporal alignment (blindly-segmented). The proposed methodology is based on a deep learning encoder-decoder U-Net architecture, which is compared with adaptations based on convolutional autoencoders and label refinement networks. Moreover, the method is explored for conversion with one single shared encoder or multiple individual encoders for each lead.

RESULTS

Despite the more challenging settings, the proposed methodology was able to attain state-of-the-art level performance in multiple target leads, and both lead I and lead II seem especially suitable to convert certain sets of leads. In cross-database tests, the methodology offered promising results despite acquisition setup differences. Furthermore, results show that the presence of medical conditions does not have a considerable effect on the method's performance.

CONCLUSIONS

This study shows the feasibility of converting ECG signals using single-lead blindly-segmented inputs. Although the results are promising, further efforts should be devoted towards the improvement of the methodologies, especially the robustness to diverse acquisition setups, in order to be applicable to cardiac health monitoring in wearable devices and less obtrusive clinical scenarios.

The prediction of cardiac abnormality and enhancement in minority class accuracy from imbalanced ECG signals using modified deep neural network models

Cardiovascular disease (CVD) is the most fatal disease in the world, so its accurate and automated detection in the early stages will certainly support the medical expert in timely diagnosis and treatment, which can save many lives. Many types of research have been carried out in this regard, but due to the problem of data imbalance in the medical and health care sector, it may not provide the desired results in all aspects. To overcome this problem, a sequential ensemble technique has been proposed that detects 6 types of cardiac arrhythmias on large ECG imbalanced datasets, and the data imbalanced issue of the ECG dataset has been addressed by using a hybrid data resampling technique called "Synthetically Minority Oversampling Technique and Tomek Link (SMOTE + Tomek)". The sequential ensemble technique employs two distinct deep learning models: Convolutional Neural Network (CNN) and a hybrid model, CNN with Long Short-Term Memory Network (CNN-LSTM). The two standard datasets "MIT-BIH arrhythmias database" (MITDB) and "PTB diagnostic database" (PTBDB) are combined and extracted 23, 998 ECG beats for the model validation. In this work, the three models CNN, CNN-LSTM, and ensemble approach were tested on four kinds of ECG datasets: the original data (imbalanced), the data sampled using a random oversampled technique, data sampled using SMOTE, and the dataset resampled using SMOTE + Tomek algorithm. The overall highest accuracy was obtained of 99.02% on the SMOTE + Tomek sampled dataset by ensemble technique and the minority class accuracy result (Recall) is improved by 20% as compared to the imbalanced data.

E-Cardiac Care: A Comprehensive Systematic Literature Review

The Internet of Things (IoT) is a complete ecosystem encompassing various communication technologies, sensors, hardware, and software. IoT cutting-edge technologies and Artificial Intelligence (AI) have enhanced the traditional healthcare system considerably. The conventional healthcare system faces many challenges, including avoidable long wait times, high costs, a conventional method of payment, unnecessary long travel to medical centers, and mandatory periodic doctor visits. A Smart healthcare system, Internet of Things (IoT), and AI are arguably the best-suited tailor-made solutions for all the flaws related to traditional healthcare systems. The primary goal of this study is to determine the impact of IoT, AI, various communication technologies, sensor networks, and disease detection/diagnosis in Cardiac healthcare through a systematic analysis of scholarly articles. Hence, a total of 104 fundamental studies are analyzed for the research questions purposefully defined for this systematic study. The review results show that deep learning emerges as a promising technology along with the combination of IoT in the domain of E-Cardiac care with enhanced accuracy and real-time clinical monitoring. This study also pins down the key benefits and significant challenges for E-Cardiology in the domains of IoT and AI. It further identifies the gaps and future research directions related to E-Cardiology, monitoring various Cardiac parameters, and diagnosis patterns.

Atrial depolarization abnormalities in pulmonary sarcoidosis

BACKGROUND

Cardiac sarcoidosis, often manifested as sudden death, can be the first manifestation of sarcoidosis. Since 12-lead electrocardiogram (ECG) is recommended as an initial screening tool for cardiac sarcoidosis, the recognition of subtle abnormalities assumes utmost significance. The objective of this study was to identify the electrocardiographic abnormalities in patients with pulmonary sarcoidosis.

RESULTS

A detailed analysis of 12-lead ECGs obtained from sixty patients with histopathologically proven pulmonary sarcoidosis and no overt cardiac involvement was done. The findings were compared with those of an age-matched control group. Varying degrees of intraventricular conduction defects were common in the study group [67%], as well as the control group [57%] [P = 0.23]. There was a higher prevalence of biphasic P wave [P = 0.003] and bifid P wave [P = 0.029] in lead III and rsr' in lead aVF [P = 0.03] in the study group as compared to the control group.

CONCLUSIONS

Our study demonstrates a greater prevalence of subtle ECG abnormalities in patients with pulmonary sarcoidosis as compared to patients with other forms of pulmonary disease. Atrial depolarization abnormalities were commoner in patients with pulmonary sarcoidosis.

Graphene and graphene nanohybrid composites-based electrodes for physiological sensing applications

In this paper, three categories of ECG electrodes were fabricated. Graphene/PDMS(Polydimethylsiloxane)(G-I), Graphene/MWCNT-COOH(Carboxylic-acid functionalized Multi-walled Carbon Nanotubes)/PDMS(G-II),and Graphene/SWCNT-COOH(Carboxylic-acid functionalized Single-walled Carbon Nanotubes)/PDMS(G-III). Each group had thirteen electrodes with varying concentrations ranging from 0.1-5wt%. Since CNTs get tangled easily, it becomes necessary to disperse them properly. To achieve optimal dispersion, CNTs were first sonicated with Isopropyl Alcohol (IPA), and then with PDMS. Mold casting was the technique used for fabricating the electrodes. The results were compared with the conventional ECG electrodes. Best results were achieved from G-III at 3wt% as the value of capacitance is high (0.172nF) as compared to G-I and G-III values at 3wt% which are 0.036nF (0.036nF) and 0.015nF respectively. As capacitance has an inverse relationship with the resistance and impedance, thus at 3wt% the resistance (0.361MΩ) and impedance (0.36MΩ) values are low, which satisfies the relationship. The values of resistance and impedance of G-II are low when compared with the values of G-I and G-II. Great results and ECG waveform are achieved with 3wt% for G-II, which also uses less nanomaterials to produce such great ECG results. It was observed that even after using the electrodes for 5 days, the ECG signal did not degrade over time and no skin allergies were detected for any of the three groups. The ECG tracking system was developed on the concept of the Internet-of-Things (IoT) using various electronic hardware components and software solutions. The results from the fabricated electrodes were promising and were suitable for long-term, and continuous ECG monitoring.

ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects

OBJECTIVE

Studies showed that many COVID-19 survivors develop sub-clinical to clinical heart damage, even if subjects did not have underlying heart disease before COVID. Since Electrocardiogram (ECG) is a reliable technique for cardiovascular disease diagnosis, this study analyzes the 12-lead ECG recordings of healthy and post-COVID (COVID-recovered) subjects to ascertain ECG changes after suffering from COVID-19.

METHOD

We propose a shallow 1-D convolutional neural network (CNN) deep learning architecture, namely ECG-iCOVIDNet, to distinguish ECG data of post-COVID subjects and healthy subjects. Further, we employed ShAP technique to interpret ECG segments that are highlighted by the CNN model for the classification of ECG recordings into healthy and post-COVID subjects.

RESULTS

ECG data of 427 healthy and 105 post-COVID subjects were analyzed. Results show that the proposed ECG-iCOVIDNet model could classify the ECG recordings of healthy and post-COVID subjects better than the state-of-the-art deep learning models. The proposed model yields an F₁-score of 100%.

CONCLUSION

So far, we have not come across any other study with an in-depth ECG signal analysis of the COVID-recovered subjects. In this study, it is shown that the shallow ECG-iCOVIDNet CNN model performed good for distinguishing ECG signals of COVID-recovered subjects from those of healthy subjects. In line with the literature, this study confirms changes in the ECG signals of COVID-recovered patients that could be captured by the proposed CNN model. Successful deployment of such systems can help the doctors identify the changes in the ECG of the post-COVID subjects on time that can save many lives.

Basis pursuit sparse decomposition using tunable-Q wavelet transform (BPSD-TQWT) for denoising of electrocardiograms

The electrocardiogram (ECG) is an essential diagnostic tool to identify cardiac abnormalities. So, the primary issue in an ECG acquisition unit is noise interference. Essentially, the prominent ECG noise sources are power line interference (PLI) and Baseline drift (BD). Therefore, in the study, a new technique called the basis pursuit sparse decomposition (BPSD) using tunable-Q wavelet transform (TQWT) is proposed to remove the PLI and BD present in the ECG recordings. Chiefly, the TQWT method is a wavelet transform with distinct Quality factors (Q) which can adjust the signal to the natural non-stationary behaviour in time and space. Further, the method decomposes the signal into high-Quality factor and low-Quality factor components of wavelet coefficients to eliminate PLI and BD by choosing appropriate redundancy (r) and decomposition levels (J2). The 'r' and 'J' values are chosen based on the trial-and-error method concerning signal-to-noise ratio (SNR). It has been found that the PLI noise has been suppressed significantly with the redundancy of 3 and decomposition levels of 10; more so, the BD has been removed with the redundancy of 4 and decomposition levels of 19. The proposed method BPSD-TQWT was evaluated using the open-source MIT-BIH Arrhythmia database and the real-time ECG recordings collected through a wearable Silver Plated Nylon Woven (Ag-NyW) textile-based ECG monitoring system. The performance was then evaluated using fidelity metrics such as SNR, maximum absolute error (MAX), and normalized cross-correlation coefficient (NCC). The results were compared with IIR filter, stationary wavelet transform (SWT), non-local means (NLM) and local means (LM) methods. Using the proposed method on MIT-BIH Arrhythmia Database, performance evaluation parameters such as SNR, MAX, and NCC were improved by 4.3 dB and 6.8 dB, 0.37 and 0.78, 0.2 and 0.46 compared to IIR and SWT methods respectively. On the other hand, using the proposed method on the real-time datasets, values of SNR, MAX, and NCC were improved by 0.3 dB and 0.6 dB, 0.009 and 0.74 and 0.3 and 0.35 compared to IIR and SWT methods respectively. Finally, it can be concluded that the proposed method shows improved performance over IIR, SWT, NLM and LM methods for PLI and BD removal.

Non invasive jacketed telemetry in socially-housed rats for a combined assessment of respiratory system, electrocardiogram and activity using the DECRO system

Respiratory and cardiovascular systems are among the vital organ systems that should be studied in safety pharmacology core battery test. Non-invasive jacketed external telemetry technology that enables concomitant monitoring of both systems has been available and used widely for non-rodent species. Recently, the DECRO system, a miniaturized technology system in line with the "3Rs" principles, has been developed to provide a similar approach in rats. However, data to evaluate this system in socially-housed rats is lacking. Therefore, the objectives of this study were to determine the tolerability and the material integrity of this novel solution in pair-housed rats in two conditions: i) in a single session of 22 h simulating a stand-alone safety pharmacology study design, and ii) in three repeated sessions of 22 h each, simulating the inclusion of safety pharmacology endpoints in a 1-month toxicology study. In both conditions, the GABA_B receptor agonist baclofen was used as a reference compound inducing cardiorespiratory changes. Our results provided evidence that this novel solution was well tolerated, the material was resistant to deterioration and that it allowed the accurate recording, in a non-invasive manner, of cardiorespiratory parameters and activity level in freely moving, pair-housed rats in the above two conditions. In addition, the expected respiratory depressant effects of baclofen were recorded. These results pave the way for considering this novel solution as an enhanced approach for nonclinical safety assessment in rats.

Deepaware: A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection

BACKGROUND

State-of-the-art automatic atrial fibrillation (AF) detection models trained on RR-interval (RRI) features generally produce high performance on standard benchmark electrocardiogram (ECG) AF datasets. These models, however, result in a significantly high false positive rates (FPRs) when applied on ECG data collected under free-living ambulatory conditions and in the presence of non-AF arrhythmias.

METHOD

This paper proposes DeepAware, a novel hybrid model combining deep learning (DL) and context-aware heuristics (CAH), which reduces the FPR effectively and improves the AF detection performance on participant-operated ambulatory ECG from free-living conditions. It exploits the RRI and P-wave features, as well as the contextual features from the ambulatory ECG.

RESULTS

DeepAware is shown to be very generalizable and superior to the state-of-the-art models when applied on unseen benchmark ECG AF datasets. Most importantly, the model is able to detect AF efficiently when applied on participant-operated ambulatory ECG recordings from free-living conditions and has achieved a sensitivity (Se), specificity (Sp), and accuracy (Acc) of 97.94%, 98.39%, 98.06%, respectively. Results also demonstrate the effect of atrial activity analysis (via P-waves detection) and CAH in reducing the FPR over the RRI features-based AF detection model.

CONCLUSIONS

The proposed DeepAware model can substantially reduce the physician's workload of manually reviewing the false positives (FPs) and facilitate long-term ambulatory monitoring for early detection of AF.

ECG_SegNet: An ECG delineation model based on the encoder-decoder structure

With the increasing usage of wearable electrocardiogram (ECG) monitoring devices, it is necessary to develop models and algorithms that can analyze the large amounts of ECG data obtained in real-time. Accurate ECG delineation is key to assisting cardiologists in diagnosing cardiac diseases. The main objective of this study is to design a delineation model based on the encoder-decoder structure to detect different heartbeat waveforms, including P-waves, QRS complexes, T-waves, and No waves (NW), as well as the onset and offset of these waveforms. First, the introduction of a standard dilated convolution module (SDCM) into the encoder path enabled the model to extract more useful ECG signal-informative features. Subsequently, bidirectional long short-term memory (BiLSTM) was added to the encoding structure to obtain numerous temporal features. Moreover, the feature sets of the ECG signals at each level in the encoder path were connected to the decoder part for multi-scale decoding to mitigate the information loss caused by the pooling operation in the encoding process. Finally, the proposed model was trained and tested on both QT and LU databases, and it achieved accurate results compared to other state-of-the-art methods. Regarding the QT database, the average accuracy of ECG waveform classification was 96.90%, and an average classification accuracy of 95.40% was obtained on the LU database. In addition, average F1 values of 99.58% and 97.05% were achieved in the ECG delineation task of the QT and LU databases, respectively. The results show that the proposed ECG_SegNet model has good flexibility and reliability when applied to ECG delineation, and it is a reliable method for analyzing ECG signals in real-time.

Inter-patient arrhythmia classification with improved deep residual convolutional neural network

BACKGROUND AND OBJECTIVE

Early detection of arrhythmias has become critical due to the increased mortality from cardiovascular disease, and ECG is an effective tool for diagnosing cardiovascular disease and detecting arrhythmias. Classification based on ECG signal segments is more suitable for clinical application.

METHODS

An improved deep residual convolutional neural network is proposed to classify arrhythmias automatically. Firstly, the overlapping segmentation method is used to segment the ECG signals in the MIT-BIH database into segments of 5 seconds in length to overcome the imbalance between classes, and these segments of the ECG signals are re-labeled. Then the discrete wavelet transform (DWT) is used to denoise these segments and the improved deep residual convolutional neural network is used for arrhythmia classification. In addition, the focal loss function is used to overcome the imbalanced classification difficulty between classes.

RESULTS

The proposed method gives 94.54% sensitivity, 93.33% positive predictivity, and 80.80% specificity for normal segments. For the supraventricular ectopic segment, the proposed method gives 35.22% sensitivity, 65.88% positive predictivity, and 98.83% specificity. For the ventricular ectopic segment, the proposed method gives 88.35% sensitivity, 79.86% positive predictivity, and 94.92% specificity.

CONCLUSION

The results of this study indicate that the proposed improved deep residual convolutional neural network model trained by the training set obtained by using the overlapping segmentation method is comparable to a classical method and three state-of-art methods. In addition, the classification performance of the network model trained by focal loss as the loss function is further improved.

A novel wireless ECG system for prolonged monitoring of multiple zebrafish for heart disease and drug screening studies

Zebrafish and their mutant lines have been extensively used in cardiovascular studies. In the current study, the novel system, Zebra II, is presented for prolonged electrocardiogram (ECG) acquisition and analysis for multiple zebrafish within controllable working environments. The Zebra II is composed of a perfusion system, apparatuses, sensors, and an in-house electronic system. First, the Zebra II is validated in comparison with a benchmark system, namely iWORX, through various experiments. The validation displayed comparable results in terms of data quality and ECG changes in response to drug treatment. The effects of anesthetic drugs and temperature variation on zebrafish ECG were subsequently investigated in experiments that need real-time data assessment. The Zebra II's capability of continuous anesthetic administration enabled prolonged ECG acquisition up to 1 h compared to that of 5 min in existing systems. The novel, cloud-based, automated analysis with data obtained from four fish further provided a useful solution for combinatorial experiments and helped save significant time and effort. The system showed robust ECG acquisition and analytics for various applications including arrhythmia in sodium induced sinus arrest, temperature-induced heart rate variation, and drug-induced arrhythmia in Tg(SCN5A-D1275N) mutant and wildtype fish. The multiple channel acquisition also enabled the implementation of randomized controlled trials on zebrafish models. The developed ECG system holds promise and solves current drawbacks in order to greatly accelerate drug screening applications and other cardiovascular studies using zebrafish.

A CNN Model for Cardiac Arrhythmias Classification Based on Individual ECG Signals

PURPOSE

Wearable devices in the scenario of connected home healthcare integrated with artificial intelligence have been an effective alternative to the conventional medical devices. Despite various benefits of wearable electrocardiogram (ECG) device, several deficiencies remain unsolved such as noise problem caused by user mobility. Therefore, an insensitive and robust classification model for cardiac arrhythmias detection system needs to be devised.

METHODS

A one-dimensional seven-layer convolutional neural network (CNN) classification model with dedicated design of structure and parameters is developed to perform automatic feature extraction and classification based on large volume of original noisy signals. Record-based ten-fold cross validation scheme is devised for evaluation to ensure the independence of the training set and test set, and further improve the robustness of our method.

RESULTS

The model can effectively detect cardiac arrhythmias, and can reduce the computational workload to a certain extent. Our experimental results outperform most recent literature on the cardiac arrhythmias classification with diagnostic accuracy of 0.9874, sensitivity of 0.9811, and specificity of 0.9905 for original signals; diagnostic accuracy of 0.9876, sensitivity of 0.9813, and specificity of 0.9907 for de-noised signals, respectively.

CONCLUSION

The evaluation indicates that our proposed approach, which performs well on both original signals and de-noised signals, fits well with wearable ECG monitoring and applications.

Beneficial Effects of Black Cardamom (Amomum subulatum) on Hemodynamic Parameters in Normotensive and Spontaneously Hypertensive Rats

&lt;b&gt;Background and Objectives:&lt;/b&gt; &lt;i&gt;Amomum subulatum&lt;/i&gt; (AS) is used to improve cardiac health in traditional medicine practice. The present study evaluates the pharmacological effect of AS aqueous extract on blood pressure in Normotensive (NR) and Spontaneously Hypertensive Rats (SHR). &lt;b&gt;Materials and Methods:&lt;/b&gt; Blood pressure, Heart Rate (HR) and Heart Rate Variability (HRV), was recorded in catheterized Sprague-Dawley rats before and after AS intravenous administration by using Mikro-Tip Pressure-Volume System (MPVS), PowerLab. The receptor activity was assessed by using the drugs Acetylcholine (ACh) and Atropine (Atr). &lt;b&gt;Results:&lt;/b&gt; Preliminary phytochemistry of AS suggests that it contains tannins, flavonoids and saponins. Mean Arterial Pressure (MAP) was found to decrease significantly in NR and SHR as compared with the control. The lowest dose (1 mg kg&lt;sup&gt;&lt;/sup&gt;&lt;sup&gt;1&lt;/sup&gt;) produced the least (16%) while 30 mg kg&lt;sup&gt;&lt;/sup&gt;&lt;sup&gt;1&lt;/sup&gt; caused the maximum reduction (40%) in MAP. Electrocardiograph analysis revealed a significant increase in RR interval (decreased heart rate), time-domain Standard Deviation of Interbeat Interval (SDNN) and the Root Mean Square of the Successive Differences (RMSSD) and High-frequency Domain (HF%) parameters and a decrease in the Low-Frequency (LF) range, suggesting the activation and involvement of the parasympathetic limb. It was also observed that the cardiovascular effects of AS were comparable to Acetylcholine (ACh) and both were completely blocked by Atropine (1 μg kg&lt;sup&gt;&lt;/sup&gt;&lt;sup&gt;1&lt;/sup&gt;). &lt;b&gt;Conclusion:&lt;/b&gt; The obtained results suggest that AS has a hypotensive effect, with an impact on the HRV of NR and SHR. &lt;i&gt;Amomum subulatum&lt;/i&gt; might cause an augmented effect on the cholinergic limb of the Autonomic Nervous System (ANS) and decrease the blood pressure and heart rate significantly.

Relationship of echocardiographic left ventricular dyssynchrony with QRS width on surface electrocardiogram in patients with systolic heart failure: An observational study

This study aimed to evaluate left ventricular dyssynchrony with QRS width on ECG in patients with systolic heart failure. 100 study patients were classified into two groups. Narrow QRS group-N- QRS (80-119 msec) and Wide QRS group-W- QRS (120-160 msec). Out of each 50 patients in W- QRS group, 38(76%) had LV dyssynchrony and 18 (36%) in N- QRS group had ventricular dyssynchrony. Dyssynchrony in narrow QRS patients with heart failure also needs attention as a therapeutic target in future studies.

Frequency of Cardiac Arrhythmias in Children with Cardiological Consulting and Containing Electrocardiogram

BACKGROUND

Heart diseases are the leading causes of mortality and congenital heart disease (CHD) is the most common birth defect reported worldwide.

OBJECTIVE

The aim of this study was to evaluate the incidence of arrhythmias and CHD and the association between the two, among infants and children reported to our center.

METHODS

This cross-sectional study included infants and children who were referred to Shahid Madani Hospital, Khorramabad. Electrocardiogram (ECG) was performed in these children to determine the type of arrhythmia and records were used to obtain demographic data and the data regarding CHD.

RESULTS

Of 200 children enrolled in the study, 10 children had arrhythmias, 12 had tachycardia, 5 had bradycardia, and 31 had congenital disease. Among children with arrhythmias, 1 had atrial fibrillation, 4 patients had paroxysmal supraventricular tachycardia, 1 person had right bundle branch block, 1 had ventricular tachycardia, 2 had premature ventricular contractions and 1 had junctional ectopic tachycardia. Of the 31 children with CHD, 9 patients were presented with small ventricular septal defect, 4 children had patent foramen ovale, 2 had pulmonary stenosis and 1 of the children had tetralogy of fallout, arterial and ventricular septal defects and transposition of greater arteries, respectively.

CONCLUSION

We reported a positive correlation between the arrhythmias and CHD. A larger number of studies collecting focusing on different age groups are therefore required to verify our findings.

Limitation of standard ECG criteria to localize an outflow tract PVC

Multiple ECG algorithms exist to localize outflow tract PVCs. They can be invaluable in pre-procedure planning and patient counseling. We describe a case where the published algorithm for PVC localization did not predict the site of origin and successful ablation site. This case highlights the strengths and limitations of established ECG PVC localization algorithms.

Chia Seed Oil Ameliorates Doxorubicin-Induced Cardiotoxicity in Female Wistar Rats: An Electrocardiographic, Biochemical and Histopathological Approach

Doxorubicin (DOX) is a potent anti-cancer antibiotic that was widely used for treatment of various cancers. It produces free radicals which result in extreme dose-limiting cardiotoxicity. This study investigated the cardioprotective potential of chia seed oil, an active polyphenolic nutraceutical against doxorubicin-induced cardiotoxicity in Wistar rats. Twenty-four female Wistar rats were divided into four groups (n = 6) which consist of normal control, DOX control, test-A and test-B group. Animals were prophylactically treated with two different doses of test drug, i.e. chia seed oil 2.5 ml/kg/day and 5 ml/kg/day in test-A and test-B groups orally for 7 days. Doxorubicin (25 mg/kg; single dose) was administered intraperitoneally to DOX control, Test-A and Test-B animals on the seventh day to induce cardiotoxicity. ECG analysis was done before and after treatment. Besides ECG, CK, CK-MB, LDH, AST, MDA and GSH were analyzed. DOX had significantly altered ECG, CK, CK-MB, LDH, AST, MDA and GSH. Pre-treatment with chia seed oil significantly alleviated DOX-induced ECG changes and also guarded against DOX-induced rise of serum CK, CK-MB and AST levels. Chia seed oil alleviated histopathological alteration in DOX-treated rats. It also significantly inhibited DOX-induced GSH depletion and elevation of MDA. The present study revealed that chia seed oil exerts cardioprotection against doxorubicin-induced cardiotoxicity in female Wistar rats. Our study opens the perspective to clinical studies to precisely consider chia seed oil as a potential chemoprotectant nutraceutical in the combination chemotherapy with doxorubicin to limit its cardiotoxicity.

AMBtalk: A Cardiovascular IoT Device for Ambulance Applications

Acute Coronary Syndrome (ACS) and other heart emergency events require immediate chest pain identification in the ambulance. Specifically, early identification and triage is required so that patients with chest pain can be quickly sent to a hospital with appropriate care facilities for treatment. In the traditional approach, ambulance personnel often use symptom checklists to examine the patient and make a quick decision for the target hospital. However, not every hospital has specialist facilities to handle such emergency cases. If the result of the subsequent cardiac enzyme test performed at the target hospital strongly suggests the occurrence of myocardial infarction, the patient may need to be sent to another hospital with specialist facilities, such as Percutaneous Coronary Intervention. The standard procedure is time consuming, which may result in delayed treatment and reduce patent survival rate. To resolve this issue, we propose AMBtalk (Ambulance Talk) for accurate, early ACS identification in an ambulance. AMBtalk provides real-time connection to hospital resources, which reduces the elapsed time for treatment, and therefore, improves the patient survival rate. The key to success for AMBtalk is the development of the AllCheck^® Internet of Things (IoT) device, which can accurately and quickly provide cardiovascular parameter values for early ACS identification. The interactions between the AllCheck^® IoT device, the emergency medical service center, the ambulance personnel and the hospital are achieved through the AMBtalk IoT server in the cloud network. AllCheck^® outperforms the existing cardiovascular IoT device solutions for ambulance applications. The testing results of the AllCheck^® device show 99% correlation with the results of the hospital reports. Due to its excellent performance in quick ACS identification, the AllCheck^® device was awarded the 17th Taiwan Innovators Award in 2020.

Prolonged phenanthrene exposure reduces cardiac function but fails to mount a significant oxidative stress response in the signal crayfish (Pacifastacus leniusculus)

Crustaceans are important ecosystem bio-indicators but their response to pollutants such as polyaromatic hydrocarbons (PAHs) remains understudied, particularly in freshwater habitats. Here we investigated the effect of phenanthrene (at 0.5, 1.0 and 1.5 mg L^-1), a 3-ringed PAH associated with petroleum-based aquatic pollution on survival, in vivo and in situ cardiac performance, the oxidative stress response and the tissue burden in the signal crayfish (Pacifastacus leniusculus). Non-invasive sensors were used to monitor heart rate during exposure. Phenanthrene reduced maximum attainable heart rate in the latter half (days 8-15) of the exposure period but had no impact on routine heart rate. At the end of the 15-day exposure period, the electrical activity of the semi-isolated in situ crayfish heart was assessed and significant prolongation of the QT interval of the electrocardiogram was observed. Enzyme pathways associated with oxidative stress (superoxide dismutase and total oxyradical scavenging capacity) were also assessed after 15 days of phenanthrene exposure in gill, hepatopancreas and skeletal muscle; the results suggest limited induction of protective antioxidant pathways. Lastly, we report that 15 days exposure caused a dose-dependent increase in phenanthrene in hepatopancreas and heart tissues which was associated with reduced survivability. To our knowledge, this study is the first to provide such a thorough understanding of the impact of phenanthrene on a crustacean.

Over-fitting suppression training strategies for deep learning-based atrial fibrillation detection

Nowadays, deep learning-based models have been widely developed for atrial fibrillation (AF) detection in electrocardiogram (ECG) signals. However, owing to the inevitable over-fitting problem, classification accuracy of the developed models severely differed when applying on the independent test datasets. This situation is more significant for AF detection from dynamic ECGs. In this study, we explored two potential training strategies to address the over-fitting problem in AF detection. The first one is to use the Fast Fourier transform (FFT) and Hanning-window-based filter to suppress the influence from individual difference. Another is to train the model on the wearable ECG data to improve the robustness of model. Wearable ECG data from 29 patients with arrhythmia were collected for at least 24 h. To verify the effectiveness of the training strategies, a Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN)-based model was proposed and tested. We tested the model on the independent wearable ECG data set, as well as the MIT-BIH Atrial Fibrillation database and PhysioNet/Computing in Cardiology Challenge 2017 database. The model achieved 96.23%, 95.44%, and 95.28% accuracy rates on the three databases, respectively. Pertaining to the comparison of the accuracy rates on each training set, the accuracy of the model trained in conjunction with the proposed training strategies only reduced by 2%, while the accuracy of the model trained without the training strategies decreased by approximately 15%. Therefore, the proposed training strategies serve as effective mechanisms for devising a robust AF detector and significantly enhanced the detection accuracy rates of the resulting deep networks.

Estimation of the Respiratory Rate from Localised ECG at Different Auscultation Sites

The respiratory rate (RR) is a vital physiological parameter in prediagnosis and daily monitoring. It can be obtained indirectly from Electrocardiogram (ECG) signals using ECG-derived respiration (EDR) techniques. As part of the study in designing an early cardiac screening system, this work aimed to study whether the accuracy of ECG derived RR depends on the auscultation sites. Experiments were conducted on 12 healthy subjects to obtain simultaneous ECG (at auscultation sites and Lead I as reference) and respiration signals from a microphone close to the nostril. Four EDR algorithms were tested on the data to estimate RR in both the time and frequency domain. Results reveal that: (1) The location of the ECG electrodes between auscultation sites does not impact the estimation of RR, (2) baseline wander and amplitude modulation algorithms outperformed the frequency modulation and band-pass filter algorithms, (3) using frequency domain features to estimate RR can provide more accurate RR except when using the band-pass filter algorithm. These results pave the way for ECG-based RR estimation in miniaturised integrated cardiac screening device.

Performance evaluation of the spectral autocorrelation function and autoregressive models for automated sleep apnea detection using single-lead ECG signal

BACKGROUND AND OBJECTIVE

This paper addresses the automated recognition of obstructive sleep apnea (OSA) from the analysis of single-lead ECG signals. This is one of the most important problems that is, critical to the realization of monitoring patients with sleep apnea.

METHODS

In the present study, a novel solution based on autoregressive (AR) modeling of the single-lead ECG, and spectral autocorrelation function as an ECG feature extraction method is presented. The more effective features are opted by sequential forward feature selection (SFFS) technique and fed into the random forest for binary classification between the apnea and normal events.

RESULTS

Experimental results on Apnea-ECG database proved that the introduced algorithm resulted in an accuracy of 93.90% (sensitivity of 92.26% and specificity of 94.92%) in per-segment classification, which outperforms the other cutting-edge automatic OSA recognition techniques. Moreover, the proposed algorithm provided an accuracy of 97.14% (sensitivity of 95.65% and specificity of 100%) in discrimination of apnea patients from the normal subjects, which is comparable to the traditional and existing approaches.

CONCLUSIONS

This study suggests that automatic OSA recognition from single-lead ECG signals is possible, which can be used as an inexpensive and low complexity burden alternative to more conventional methods such as Polysomnography.

ECG changes at rest and during exercise in lowlanders with COPD travelling to 3100 m

BACKGROUND

The incidence and magnitude of cardiac ischemia and arrhythmias in patients with chronic obstructive pulmonary disease (COPD) during exposure to hypobaric hypoxia is insufficiently studied. We investigated electrocardiogram (ECG) markers of ischemia at rest and during incremental exercise testing (IET) in COPD-patients travelling to 3100 m.

STUDY DESIGN AND METHODS

Lowlanders (residence <800 m) with COPD (forced volume in the first second of expiration (FEV₁) 40-80% predicted, oxygen saturation (SpO₂) ≥92%, arterial partial pressure of carbon dioxide (PaCO₂) <6 kPa at 760 m) aged 18 to 75 years, without history of cardiovascular disease underwent 12‑lead ECG recordings at rest and during cycle IET to exhaustion at 760 m and after acute exposure of 3 h to 3100 m. Mean ST-changes in ECGs averaged over 10s were analyzed for signs of ischemia (≥1 mm horizontal or downsloping ST-segment depression) at rest, peak exercise and 2-min recovery.

RESULTS

80 COPD-patients (51% women, mean ± SD, 56.2 ± 9.6 years, body mass index (BMI) 27.0 ± 4.5 kg/m², SpO₂ 94 ± 2%, FEV₁ 63 ± 10% prEd.) were included. At 3100 m, 2 of 53 (3.8%) patients revealed ≥1 mm horizontal ST-depression during IET vs 0 of 64 at 760 m (p = 0.203). Multivariable mixed regression revealed minor but significant ST-depressions associated with altitude, peak exercise or recovery and rate pressure product (RPP) in multiple leads.

CONCLUSION

In this study, ECG recordings at rest and during IET in COPD-patients do not suggest an increased incidence of signs of ischemia with ascent to 3100 m. Whether statistically significant ST changes below the standard threshold of clinical relevance detected in multiple leads reflect a risk of ischemia during prolonged exposure remains to be elucidated.

Multi-information fusion neural networks for arrhythmia automatic detection

BACKGROUND AND OBJECTIVES

. The electrocardiograms (ECGs) are widely used to diagnose a variety of arrhythmias. Generally, the abnormalities of ECG signals mainly consist of ill-shaped ECG beat morphologies and irregular intervals. The ill-shaped ECG beat morphologies represent morphological information, while the irregular intervals denote the temporal information of ECG signals. But it is difficult to utilize morphological information and temporal information simultaneously when dealing with single ECG heartbeats, because RR interval is not contained in a single short heartbeat. Therefore, to handle this problems, a novel Multi-information Fusion Convolutional Bidirectional Recurrent Neural Network (MF-CBRNN) is proposed for arrhythmia automatic detection.

METHODS

. The MF-CBRNN is designed with two parallel hybrid branches that can simultaneously focus on the beat-based information in the ECG beats and the segment-based information in the adjacent segments of the beats. A single ECG beat provides the morphological information. At the same time, the adjacent segment of the ECG beat enriches the temporal information, so the two branches are designed to exploit the multiple information contained in ECGs. Furthermore, a combination of convolutional neural networks (CNNs) and a bidirectional long short memory (BLSTM) in each branch is utilized to capture the information from the two inputs. And all the features extracted from the two branches are fused for information aggregation.

RESULTS

. To evaluate the performance of the proposed model, the ECG signals from MIT-BIH databases are used for intra-patient and inter-patient paradigms. The proposed model yields an accuracy of 99.56% and an F1-score of 96.40% under the intra-patient paradigm. And it obtains an overall accuracy of 96.77% and F1-score of 77.83% under the inter-patient paradigm.

CONCLUSIONS

. Compared with other studies on arrhythmia detection, our method achieves a state-of-the-art performance. It indicates that the proposed model is a promising arrhythmia detection algorithm for computer-aided diagnostic systems.

Diagnostic Value of Atrial Fibrillation by Built-in Electrocardiogram Technology in a Blood Pressure Monitor

Background: Hypertension in patients with atrial fibrillation (AF) is a known independent risk factor for stroke. The Complete blood pressure (BP) monitor (Omron Healthcare, Kyoto, Japan) was developed as the first BP monitor with electrocardiogram (ECG) capability in a single device to simultaneously monitor ECG and BP readings. This study investigated whether the Complete can accurately differentiate sinus rhythm (SR) from AF during BP measurement.

Methods and Results: Fifty-six consecutive patients with persistent AF admitted for catheter ablation were enrolled in the study (mean age 65.8 years; 83.9% male). In all patients, 12-lead ECGs and simultaneous Complete recordings were acquired before and after ablation. The Complete interpretations were compared with physician-reviewed ECGs, whereas Complete recordings were reviewed by cardiologists in a blinded manner and compared with ECG interpretations. Sensitivity, specificity, and κ coefficient were also determined. In all, 164 Complete and ECG recordings were simultaneously acquired from the 56 patients. After excluding unclassified recordings, the Complete automated algorithm performed well, with 100% sensitivity, 86% specificity, and a κ coefficient of 0.87 compared with physician-interpreted ECGs. Physician-interpreted Complete recordings performed well, with 99% sensitivity, 85% specificity, and a κ coefficient of 0.85 compared with physician-interpreted ECGs.

Conclusions: The Complete, which combines BP and ECG monitoring, can accurately differentiate SR from AF during BP measurement.

A compressed-sensing-based compressor for ECG

Electrocardiogram (ECG) data compression has numerous applications. The time for generating compressed samples is a vital factor when we consider ambulatory devices, with the fact that data should be sent to the physician as soon as possible. In addition, there are some wearable ECG recorders that have limited power, and may only be capable of doing simple algorithms. With the aim of increasing the speed and simplicity of the compressors, we propose a system architecture that can generate compressed ECG samples, in a linear method and with CR 75%. We used sparsity of the ECG signal and proposed a system based on compressed sensing (CS) that can compress ECG samples, almost in real-time. We applied CS in a very small size in order to accelerate the compression phase and accordingly reducing the power consumption. Also, in the recovery phase, we used the recently developed Kronecker technique to improve the quality of the recovered signal. The system designed based on full-adder/subtractor (FAS) and shift registers, without using any external processor or any training algorithm.