Electrocardiogram Time Research Articles

Assessing the efficacy of electrocardiogram for heart rate evaluation during newborn resuscitation at birth: a prospective observational study.

This study aimed to assess the efficacy of electrocardiogram (ECG) compared to pulse oximetry (PO) in detecting heart rate (HR) during high-risk newborn resuscitation. A prospective observational study was performed with high-risk delivery cases to measure the time required for HR detection. A conventional PO and a standard ECG monitor were used for HR assessment. Forty-one infants were analyzed in the study, and 11 among them needed resuscitation. Nine were <32 gestational weeks (GA), 28 were 33-35 GA, and 4 were >36 GA at birth. ECG time for placement to HR detection was significantly faster than PO detection [30 (20-43.5) vs. 125 (100-175) seconds, P<0.001]. ECG time for placement to HR detection was the fastest in the infants below 32 GA at birth [19 (11.5-30) vs. 34.5 (25-44.25) vs. 39.5 (30-64.75) seconds, P=0.039). ECG effectively evaluated HR during neonatal resuscitation compared to PO. Low gestational age infants who need resuscitation often may benefit in HR evaluation with nearby standard ECG.

Application of Fractal Dimension for Cardiac Arrhythmias Classification

Fractal analysis is crucial for understanding complex, irregular patterns found in nature, finance, and various scientific fields. It helps to reveal self-similarity, where structures repeat at different scales, providing insights into chaotic systems like weather patterns, stock markets, and biological growth. By applying fractal analysis, researchers can model phenomena that traditional geometric methods cannot easily describe, enabling better predictions and deeper comprehension of dynamic systems. The Fractals are a fascinating mathematical tool for modeling the roughness of nature and understanding structure of such complex objects. They are considered a tool for understanding the world. In general, fractal objects are characterized by the fractal dimension. The application of fractal geometry to the analysis of ECG time series data is examined in this paper. A method based on the assessment of the Fractal Dimension (FD) of ECG recordings is suggested for the identification of cardiac diseases. In this work, and in order to exploit the fractal dimension to analyze fractal signals, the notion of fractal dimension is defined by presenting methods for calculating this dimension such as Higuchi algorithm, Katz method, regularization, box-counting etc… Each of them has its own advantages and disadvantages. This study has shown that the electrocardiogram (ECG) is a fractal signal. This allows to classify heartbeats founded on the concept of fractals. The main aim is to develop a digital technique to analyze ECG signals in order to make an accurate diagnosis of cardiovascular diseases.

Benchmarking Approaches: Time Series Versus Feature-Based Machine Learning in ECG Analysis on the PTB-XL Dataset.

Extensive research has been conducted on time series and tabular data in the context of classification tasks, considering their distinct data domains. While feature extraction enables the transformation of series into tabular data, direct comparative comparisons between these data types remain scarce. Especially in the domain of medical data, such as electrocardiograms (ECGs), deep learning faces challenges due to its lack of easy and fast interpretability and explainability. However, these are crucial aspects for a wide and reliable adoption in the field. In our study, we assess the performance of XGBoost and InceptionTime on ECG features and time series data respectively. Our findings reveal that features extracted from ECG signals not only achieve competitive performance but also retain advantages during training and inference. These advantages encompass accuracy, resource efficiency, stability, and a high level of explainability.

An active learning enhanced data programming (ActDP) framework for ECG time series

Supervised machine learning learns a mapping from input data to output labels, based on the patterns and relationships present in a huge labelled training data.Getting labelled data generally requires a substantial allocation of resources in terms of cost and time. In such scenarios, weak supervised learning techniques like data programming (DP) and active learning (AL) can be advantageous for time-series classification tasks. These paradigms can be used to assign data labels in an automated manner, and time-series classification can subsequently be carried out on the labeled data. This work proposes a novel framework titled AL enhanced data programming (ActDP). It uses a combination of DP and AL for electrocardiogram (ECG) beat classification using single-lead data. ECG beat classification is pivotal in cardiology and healthcare applications for diagnosing a broad spectrum of heart conditions and arrhythmias. To establish the usefulness of this proposed ActDP framework, the experiments have been conducted using the MIT-BIH dataset with 94,224 ECG beats. DP assigns a probabilistic label to each ECG beat using nine novel polar labelling functions and a generative model in this work. Further, AL improves the result of DP by replacing the labels for sampled ECG beats of a generative model with ground truth. Subsequently, a discriminative model is trained on these labels for each iteration. The experimental results show that by incorporating AL into DP in the ActDP framework, the accuracy of ECG classification strictly increases from 85.7% to 97.34% in 58 iterations. Comparatively, the proposed framework (ActDP) has demonstrated a higher classification accuracy of 97.34%. In contrast, DP with data augmentation (DA) achieves an accuracy of 92.2%, while DP without DA results in an accuracy of 85.7%, few-shot learning techniques yield 87.5%–89.2%, and multi-instance learning methods achieve accuracies in the range of 88.9%–94.1%

Deep neural networks detect regional wall motion abnormalities and preclinical cardiovascular disease from 12-lead ECGs.

Identifying regional wall motion abnormalities (RWMAs) is critical for diagnosing and risk stratifying patients with cardiovascular disease, particularly ischemic heart disease. We hypothesized that a deep neural network could accurately identify patients with regional wall motion abnormalities from a readily available standard 12-lead electrocardiogram (ECG). This observational, retrospective study included patients who were treated at Beth Israel Deaconess Medical Center and had an ECG and echocardiogram performed within 14 days of each other between 2008 and 2019. We trained a convolutional neural network to detect the presence of RWMAs, qualitative global right ventricular (RV) hypokinesis, and varying degrees of left ventricular dysfunction (left ventricular ejection fraction [LVEF] ≤50%, LVEF ≤40%, and LVEF ≤35%) identified by echocardiography, using ECG data alone. Patients were randomly split into development (80%) and test sets (20%). Model performance was assessed using area under the receiver operating characteristic curve (AUC). Cox proportional hazard models adjusted for age and sex were performed to estimate the risk of future acute coronary events. The development set consisted of 19,837 patients (mean age 66.7±16.4; 46.7% female) and the test set comprised of 4,953 patients (mean age 67.5±15.8 years; 46.5% female). On the test dataset, the model accurately identified the presence of RWMA, RV hypokinesis, LVEF ≤50%, LVEF ≤40%, and LVEF ≤35% with AUCs of 0.87 (95% CI 0.858-0.882), 0.888 (95% CI 0.878-0.899), 0.923 (95% CI 0.914-0.933), 0.93 (95% CI 0.921-0.939), and 0.876 (95% CI 0.858-0.896), respectively. Among patients with normal biventricular function at the time of the index ECG, those classified as having RMWA by the model were 3 times the risk (age- and sex-adjusted hazard ratio, 2.8; 95% CI 1.9-3.9) for future acute coronary events compared to those classified as negative. We demonstrate that a deep neural network can help identify regional wall motion abnormalities and reduced LV function from a 12-lead ECG and could potentially be used as a screening tool for triaging patients who need either initial or repeat echocardiographic imaging.

A novel hybrid GRU-CNN and residual bias (RB) based RB-GRU-CNN models for prediction of PTB Diagnostic ECG time series data

Time series analysis is crucial in the field of medical sciences. Recently, it has become crucial to comprehend the intricacies of data to forecast and assess the likelihood of survival in patients with different ailments. The study employs diverse datasets from multiple PTB electrocardiogram (ECG) datasets, which exhibit a high degree of uncorrelation. These datasets include patients with various heart diseases and age groups, ensuring dataset diversity. The paper presents two models that utilize deep learning and residual bias. The primary approach proposed is a hybrid GRU-CNN model. In contrast, the second model incorporates residual bias (RB) to improve upon the first model, referred to as the RB-GRU-CNN model. The hybrid GRU-CNN model has been compared to conventional deep learning models across multiple metrics, achieving the highest average percentage of improvement in RMSE (46.73%), MSE (67.46%), MAPE (43.92%), and MAE (48.52%) compared to LSTM. The RB-GRU-CNN proposed model demonstrated greater efficacy than the GRU-CNN proposed model, as confirmed by non-parametric statistical Friedman ranking and their corresponding Holm’s p-values. The comprehensive study of the results proves that the proposed models outperformed the performance of the traditional models.

Intelligent fatigue detection based on hierarchical multi-scale ECG representations and HRV measures

Fatigue detection based on electrocardiogram (ECG) from wearable devices is a convenient approach during exercise. However, how to model the data variations of ECG time series and capture effective information for accurate fatigue detection is still challenging. In this study, we propose a novel fatigue assessment architecture designed to adaptively extract and integrate both the ECG and heart rate variability (HRV) features, so as to obtain rich contextual information from ECG sequences and improve exercise-induced fatigue prediction performance. Inspired by the ECG observation process of human experts, the hierarchical transformer framework is designed to model the long-range dependencies of ECG time series and obtain multi-scale ECG representations. To reduce the computation cost, we also devise a sampling-efficient multi-head attention (SMA) mechanism. Finally, a novel gated feature fusion layer is developed to adaptively learn the weights of both the ECG and HRV features for fatigue prediction. The proposed fatigue prediction system is validated with real fatigue datasets which were collected from healthy participants. The experimental results show that the proposed approach outperforms other recent state-of-the-art systems in terms of accuracy 94.0%, specificity 99.0%, recall 89.3%, F1-score 93.7%, G-mean score 91.7%, MCC 0.837, and Cohen’s Kappa 0.847, based on the ECG time series with duration 20s. This demonstrates that the proposed system can be used to accurately detect fatigue in real time during exercise, such that assisting coaches or athletes to monitor and adjust their exercise session for preventing overexertion and fatigue-induced injury.

Tetanus Severity Classification in Low-Middle Income Countries through ECG Wearable Sensors and a 1D-Vision Transformer

Tetanus, a life-threatening bacterial infection prevalent in low- and middle-income countries like Vietnam, impacts the nervous system, causing muscle stiffness and spasms. Severe tetanus often involves dysfunction of the autonomic nervous system (ANS). Timely detection and effective ANS dysfunction management require continuous vital sign monitoring, traditionally performed using bedside monitors. However, wearable electrocardiogram (ECG) sensors offer a more cost-effective and user-friendly alternative. While machine learning-based ECG analysis can aid in tetanus severity classification, existing methods are excessively time-consuming. Our previous studies have investigated the improvement of tetanus severity classification using ECG time series imaging. In this study, our aim is to explore an alternative method using ECG data without relying on time series imaging as an input, with the aim of achieving comparable or improved performance. To address this, we propose a novel approach using a 1D-Vision Transformer, a pioneering method for classifying tetanus severity by extracting crucial global information from 1D ECG signals. Compared to 1D-CNN, 2D-CNN, and 2D-CNN + Dual Attention, our model achieves better results, boasting an F1 score of 0.77 ± 0.06, precision of 0.70 ± 0. 09, recall of 0.89 ± 0.13, specificity of 0.78 ± 0.12, accuracy of 0.82 ± 0.06 and AUC of 0.84 ± 0.05.

Data programming enabled weak supervised labeling for ECG time series

Electrocardiogram (ECG) beat labeling performed using conventional methods is unsuitable for ECG signals obtained from Internet of Things (IoT) wearable devices. The conventional methods employ manually labeled data captured using multiple leads, while most IoT devices produce unlabeled single lead data. Getting ECG data labeled by a subject matter expert (SME) is a resource/time/cost-intensive task. Our research addresses this challenge by proposing an automatic labeling technique for ECG time-series data obtained from a single lead. The technique employs a data programming (DP) enabled weak supervised learning (WSL) technique for automatic labeling of ECG beats. We have proposed nine novel heuristics-based labeling functions (LFs), applied them to each ECG beat and subsequently used a generative model (GM) to assign a probabilistic label to each ECG beat employing both intra and inter-patient paradigm on MIT-BIH and INCART datasets. Further, a discriminative model (DM) is trained on top of the GM for maximizing data coverage and ensure robustness. Finally, data augmentation (DA) is used to solve the class imbalance problem inherent in ECG data. Our experimental results demonstrate a simpler, faster, and more accurate labeling method i.e., approximately 105 ECG beats are labeled in an hour with an accuracy of 92.2% from single lead data. In contrast with human annotators, the time and cost requirements of our proposed labeling method are significantly less.

Distribution characteristics and prognostic value of 12-lead ECG PR interval in hospitalized patients with heart failure.

The aim of this study was to explore the distribution characteristics and prognostic value of the distance from the start of the P wave to the start of the QRS wave (PR interval) in 12-lead electrocardiogram (ECG) of hospitalized patients with heart failure.A total of 354 heart failure patients treated in our hospital from June 2018 to April 2020 were retrospectively selected as the study subjects. Among them, 86 cases were classified as the 101 ms-156 ms group, 92 cases as the 157 ms-169 ms group, 94 cases as the 170 ms-191 ms group, and 82 cases as the 192 ms-321 ms group based on the PR interval quartile. The clinical data of the subjects were collected and the changes in clinical data at different PR intervals were analyzed. The patients were followed up for 48 months and were further divided into 92 cases in the death group and 262 cases in the survival group. The changes in the levels of 12-lead ECG indexes in patients with different prognoses were analyzed. The receiver operating characteristic (ROC) curve was established to analyze the predictive value of 12-lead ECG on the prognosis of heart failure patients. The Kaplan-Meier survival curve was adopted to analyze the relationship between 12-lead ECG and survival time of heart failure patients.There were significant differences in age, body mass index (BMI), cardiac function classification, left ventricular ejection fraction (LVEF) and N-terminal pro-B-type natriuretic peptide (NT-proBNP) among patients with different PR intervals (p<0.05). P-wave, PR interval, and QRS complex levels increased with increasing PR staging fraction (p<0.05). Compared with the survival group, the proportion of P wave, PR interval 192 ms-321 ms, and the level of QRS complex in the death group were much higher (p<0.05). ROC curve analysis showed that the P wave, PR interval, and QRS complex were all factors influencing the poor prognosis of patients with heart failure (p<0.05, Table Ⅳ). QRS complexes were all predictive of prognosis in heart failure patients (p<0.05). The median survival time (MST) of patients with P wave ≥113 ms was 35 months, which was sharply shorter than the patients in P wave <113 ms group (46 months, p<0.05). The MST of patients with PR interval of 101 ms-156 ms was 45.5 months, 42 months in the 157 ms-169 ms group, 39 months in the 170 ms-191 ms group, and 35 months in the 192 ms-321 ms group, exhibiting significant differences among the groups (p<0.05). The MST of patients with QRS complex ≥121.44 ms was 38 months, which was memorably shorter than 44.5 months of the patients with QRS complex <121.44 ms (p<0.05).The 12-lead ECG of hospitalized patients with heart failure is significantly abnormal, and the PR interval, P wave width, and QRS complex are significantly prolonged. The P wave, PR intervals, and QRS complex had a certain correlation with the prognosis of heart failure patients.

Effect of chained one-stop emergency nursing combined with optimized triage path nursing on the rescue effect of chest pain patients in emergency department

ABSTRACT This study aimed to investigate the effect of chained one-stop emergency nursing combined with optimized triage path nursing on emergency chest pain patients. Data of 142 patients with chest pain in emergency department of our hospital were retrospectively analyzed, and from March to May 2022,71 patients with optimized triage route nursing were treated as control group, from June to August 2022, 71 patients with chain one-stop emergency care combined with optimized triage route care were selected as the observation group. Data of completion time of the first electrocardiogram (ECG) completion, troponin result giving time, door to balloon (D to B) time, length of hospital stay and rescue time (disease condition initial assessment time, preliminary examination time, first medical contact time of balloon dilation, D to B dilation time) were collected. The complication rate, adverse event rate and nursing satisfaction were compared between the two groups. The completion time of the first ECG, troponin result giving time, D to B time, initial condition assessment time, hospital stay and rescue time in the observation group were shorter than those in the control group, (all P<0.05). The incidence of complications and adverse events in the observation group were lower than control group (both P<0.05). The scores of nursing satisfaction in the observation group were evidently higher than those in the control group, (P<0.05). Chained one-stop emergency nursing combined with optimized triage path nursing has a good effect on emergency chest pain patients.

Unsupervised Transformer-Based Anomaly Detection in ECG Signals

Anomaly detection is one of the basic issues in data processing that addresses different problems in healthcare sensory data. Technology has made it easier to collect large and highly variant time series data; however, complex predictive analysis models are required to ensure consistency and reliability. With the rise in the size and dimensionality of collected data, deep learning techniques, such as autoencoder (AE), recurrent neural networks (RNN), and long short-term memory (LSTM), have gained more attention and are recognized as state-of-the-art anomaly detection techniques. Recently, developments in transformer-based architecture have been proposed as an improved attention-based knowledge representation scheme. We present an unsupervised transformer-based method to evaluate and detect anomalies in electrocardiogram (ECG) signals. The model architecture comprises two parts: an embedding layer and a standard transformer encoder. We introduce, implement, test, and validate our model in two well-known datasets: ECG5000 and MIT-BIH Arrhythmia. Anomalies are detected based on loss function results between real and predicted ECG time series sequences. We found that the use of a transformer encoder as an alternative model for anomaly detection enables better performance in ECG time series data. The suggested model has a remarkable ability to detect anomalies in ECG signal and outperforms deep learning approaches found in the literature on both datasets. In the ECG5000 dataset, the model can detect anomalies with 99% accuracy, 99% F1-score, 99% AUC score, 98.1% recall, and 100% precision. In the MIT-BIH Arrhythmia dataset, the model achieved an accuracy of 89.5%, F1 score of 92.3%, AUC score of 93%, recall of 98.2%, and precision of 87.1%.

Electrocardiogram Detection of Pulmonary Hypertension Using Deep Learning

BackgroundPulmonary hypertension (PH) is life-threatening, and often diagnosed late in its course. We aimed to evaluate if a deep learning approach using electrocardiogram (ECG) data alone can detect PH and clinically important subtypes. We asked: does an automated deep learning approach to ECG interpretation detect PH and its clinically important subtypes? Methods and ResultsAdults with right heart catheterization or an echocardiogram within 90 days of an ECG at the University of California, San Francisco (2012–2019) were retrospectively identified as PH or non-PH. A deep convolutional neural network was trained on patients’ 12-lead ECG voltage data. Patients were divided into training, development, and test sets in a ratio of 7:1:2. Overall, 5016 PH and 19,454 patients without PH were used in the study. The mean age at the time of ECG was 62.29 ± 17.58 years and 49.88% were female. The mean interval between ECG and right heart catheterization or echocardiogram was 3.66 and 2.23 days for patients with PH and patients without PH, respectively. In the test dataset, the model achieved an area under the receiver operating characteristic curve, sensitivity, and specificity, respectively of 0.89, 0.79, and 0.84 to detect PH; 0.91, 0.83, and 0.84 to detect precapillary PH; 0.88, 0.81, and 0.81 to detect pulmonary arterial hypertension, and 0.80, 0.73, and 0.76 to detect group 3 PH. We additionally applied the trained model on ECGs from participants in the test dataset that were obtained from up to 2 years before diagnosis of PH; the area under the receiver operating characteristic curve was 0.79 or greater. ConclusionsA deep learning ECG algorithm can detect PH and PH subtypes around the time of diagnosis and can detect PH using ECGs that were done up to 2 years before right heart catheterization/echocardiogram diagnosis. This approach has the potential to decrease diagnostic delays in PH.

DG-ECG: Multi-stream deep graph learning for the recognition of disease-altered patterns in electrocardiogram

Representation learning of electrocardiogram (ECG) has been an active research field for the automated detection of cardiac disease. In addition to extracting time and frequency domain features of ECG, an increasing amount of studies have adapted deep neural networks for the recognition of disease-altered ECG patterns. However, many deep learning models are deployed as blackboxes without fully exploring disease-pertinent information hidden in the signal. This, as a result, diminishes the efficacy and interpretability of the model and impedes applications in clinical practice. To address this problem, we develop a new multi-stream deep graph learning of ECG (DG-ECG) framework, which integrates multi-stream graph neural networks to uncover disease-altered ECG patterns from multifold perspectives (e.g., the morphology and rhythm of ECG signals). In each stream, visibility graphs are modeled to transform signal patterns into graph topological features, which are then mined by graph convolution. In addition, attention mechanisms are integrated into DG-ECG for multi-level information fusion to enhance its detection power and interpretability. Experimental results have demonstrated that the developed DG-ECG is better capable of gleaning disease-pertinent information from multi-channel ECG signals compared to benchmark models. The developed framework is extendable and suited for the pattern recognition of various cardiac disorders.

Abstract 14935: Deep Learning Pipeline for Frailty Screening Using the 12-Lead Electrocardiogram

Introduction: The electrocardiogram (ECG) contains information about age-related changes in cardiovascular physiology, which have been linked with the frailty syndrome. Hypothesis: We sought to develop and validate a predictive model leveraging the 12-lead ECG to screen for frailty as defined by a prospective reference standard. Methods: We conducted a population-based cohort study using data from the Canadian Longitudinal Study of Aging (CLSA). From 2010-2015, the CLSA enlisted a diverse and multi-ethnic sample of community-dwelling adults 45-85 years of age. Comprehensive phenotyping was performed through interviews at participants’ homes and assessments at data collection sites. Frailty was quantified by the 110-item Frailty Index (FI) Composite, consisting of self-reported comorbidities, blood tests, physical performance tests, body composition tests, cardiovascular and pulmonary tests, cognitive and sensory tests. After dividing our sample into training (80%) and test (20%) sets, we developed an end-to-end deep neural network to predict the FI score based on the 12-lead ECG time series. Results: A total of 26,700 ECGs with paired FI scores were evaluated. For classification of FI quintiles, a bidirectional long short-term memory (BiLSTM) neural network with a cross-entropy loss function achieved a 5-fold mean area under the receiver operating characteristics curve (AUROC) of 0.70 and area under the precision-recall curve (AUPRC) of 0.36. Predictive performance was superior for classification of the first (most robust) quintile that had AUROC 0.79 and AUPRC 0.46, and the fifth (most frail) quintile that had AUROC 0.79 and AUPRC 0.56, as compared to the middle quintiles that had AUROC 0.60-0.69 and AUPRC 0.27-0.29. Conclusions: Our deep learning model can be used to screen for high or low levels of frailty based on the readily available 12-lead ECG. Additional research is underway to gain insights into other representations of the ECG signal and relative importance of the ECG features.

Evaluation of handcrafted features and learned representations for the classification of arrhythmia and congestive heart failure in ECG

Electrocardiogram (ECG) is considered as an essential diagnostic tool to investigate life-threatening cardiac abnormalities, such as arrhythmia and congestive heart failure. It is observed that the atrial arrhythmias and congestive heart failure are closely related, wherein, one promotes the other and their co-existence can increase the mortality rate. Timely diagnosis of these diseases is essential to prevent sudden cardiac failure. In this work, we employ a two-fold approach to classify arrhythmia, congestive heart failure, and normal sinus rhythm using ECG fragments. First, we use a traditional hand-crafted feature based model which involves extraction of a number of linear and non-linear features from the ECG fragments. The linear features capture the time-varying and scale of variability information, whereas the non-linear features help to extract the hidden complexity and quantify the uncertainty of the non-stationary signal. Second, an automatic feature learning based approach is employed which uses a pre-trained deep learning network to automatically extract the relevant detailed information from the ECG time–frequency representations. Finally, we explored the combined effect of the two approaches to diagnose the arrhythmias and congestive heart failure patterns. Additionally, this study makes novel use of the subject-level ECG classification. This work on Physionet database shows that the proposed combined system gives an accuracy, sensitivity, specificity, and precision of 99.06%, 99.14%, 99.68%, and 99.32%, respectively, which are better than the state-of-the-art systems. For subject-specific experiment, a further improvement in these performance metrics is obtained using the voting procedure.

Development and Validation of an Algorithm for the Digitization of ECG Paper Images.

The electrocardiogram (ECG) signal describes the heart’s electrical activity, allowing it to detect several health conditions, including cardiac system abnormalities and dysfunctions. Nowadays, most patient medical records are still paper-based, especially those made in past decades. The importance of collecting digitized ECGs is twofold: firstly, all medical applications can be easily implemented with an engineering approach if the ECGs are treated as signals; secondly, paper ECGs can deteriorate over time, therefore a correct evaluation of the patient’s clinical evolution is not always guaranteed. The goal of this paper is the realization of an automatic conversion algorithm from paper-based ECGs (images) to digital ECG signals. The algorithm involves a digitization process tested on an image set of 16 subjects, also with pathologies. The quantitative analysis of the digitization method is carried out by evaluating the repeatability and reproducibility of the algorithm. The digitization accuracy is evaluated both on the entire signal and on six ECG time parameters (R-R peak distance, QRS complex duration, QT interval, PQ interval, P-wave duration, and heart rate). Results demonstrate the algorithm efficiency has an average Pearson correlation coefficient of 0.94 and measurement errors of the ECG time parameters are always less than 1 mm. Due to the promising experimental results, the algorithm could be embedded into a graphical interface, becoming a measurement and collection tool for cardiologists.

Classification of Tetanus Severity in Intensive-Care Settings for Low-Income Countries Using Wearable Sensing.

Infectious diseases remain a common problem in low- and middle-income countries, including in Vietnam. Tetanus is a severe infectious disease characterized by muscle spasms and complicated by autonomic nervous system dysfunction in severe cases. Patients require careful monitoring using electrocardiograms (ECGs) to detect deterioration and the onset of autonomic nervous system dysfunction as early as possible. Machine learning analysis of ECG has been shown of extra value in predicting tetanus severity, however any additional ECG signal analysis places a high demand on time-limited hospital staff and requires specialist equipment. Therefore, we present a novel approach to tetanus monitoring from low-cost wearable sensors combined with a deep-learning-based automatic severity detection. This approach can automatically triage tetanus patients and reduce the burden on hospital staff. In this study, we propose a two-dimensional (2D) convolutional neural network with a channel-wise attention mechanism for the binary classification of ECG signals. According to the Ablett classification of tetanus severity, we define grades 1 and 2 as mild tetanus and grades 3 and 4 as severe tetanus. The one-dimensional ECG time series signals are transformed into 2D spectrograms. The 2D attention-based network is designed to extract the features from the input spectrograms. Experiments demonstrate a promising performance for the proposed method in tetanus classification with an F1 score of 0.79 ± 0.03, precision of 0.78 ± 0.08, recall of 0.82 ± 0.05, specificity of 0.85 ± 0.08, accuracy of 0.84 ± 0.04 and AUC of 0.84 ± 0.03.

Utility of a novel wearable electrode embedded in an undershirt for electrocardiogram monitoring and detection of arrhythmias

BackgroundA 12-lead electrocardiogram (ECG) and Holter ECG have been established as gold standards for detection of arrhythmias. Recently, wearable ECG monitoring devices have been available. Our purpose of the present study was to investigate whether a novel wearable electrode embedded in an undershirt is useful for ECG monitoring and detection of arrhythmias.MethodsWe studied 31 consecutive hospitalized patients who underwent catheter ablation of tachyarrhythmias. Patients equipped a wearable electrode and a lead CM5 of Holter ECG simultaneously, and total heart beats, maximum heart rate (HR), mean HR, minimum HR, detections of arrhythmias, such as atrial fibrillation, non-sustained ventricular tachycardia, and premature ventricular contractions (Lown’s grade >II), were compared between the two methods using a Holter ECG analysis software.ResultsMedian recording time of ECG by wearable electrodes was 12.6 hours. Strong correlations between the two methods were observed in total heart beats (R = 0.999, P <0.001), maximum HR (R = 0.997, P <0.001), mean HR (R = 0.999, P <0.001), minimum HR (R = 0.989, P <0.001) and QRS duration (R = 0.900, P <0.001). Bland-Altman analysis showed excellent concordance between each parameter measured by two methods. In addition, the detection of atrial fibrillation (nine events), non-sustained ventricular tachycardia (two events), and premature ventricular contractions of Lown’s grade >II (five events) were concordant in two methods. In addition, there were no significant difference in parameters of time-domain and frequency-domain analyses of heart rate variability between the two methods.ConclusionsThe usefulness of a novel electrode embedded in an undershirt is equivalent to that of a Holter ECG in monitoring the ECG and detection of arrythmias.

Electrocardiogram Signal Classification Based on Mix Time-Series Imaging

Arrhythmia is a significant cause of death, and it is essential to analyze the electrocardiogram (ECG) signals as this is usually used to diagnose arrhythmia. However, the traditional time series classification methods based on ECG ignore the nonlinearity, temporality, or other characteristics inside these signals. This paper proposes an electrocardiogram classification method that encodes one-dimensional ECG signals into the three-channel images, named ECG classification based on Mix Time-series Imaging (EC-MTSI). Specifically, this hybrid transformation method combines Gramian angular field (GAF), recurrent plot (RP), and tiling, preserving the original ECG time series’ time dependence and correlation. We use a variety of neural networks to extract features and perform feature fusion and classification. This retains sufficient details while emphasizing local information. To demonstrate the effectiveness of the EC-MTSI, we conduct abundant experiments in a commonly-used dataset. In our experiments, the general accuracy reached 93.23%, and the accuracy of identifying high-risk arrhythmias of ventricular beats and supraventricular beats alone are as high as 97.4% and 96.3%, respectively. The results reveal that the proposed method significantly outperforms the existing approaches.