Electrocardiogram Features Research Articles

An ECG Classification Method Based on Multi-Task Learning and CoT Attention Mechanism.

Electrocardiogram (ECG) is an efficient and simple method for the diagnosis of cardiovascular diseases and has been widely used in clinical practice. Because of the shortage of professional cardiologists and the popularity of electrocardiograms, accurate and efficient arrhythmia detection has become a hot research topic. In this paper, we propose a new multi-task deep neural network, which includes a shared low-level feature extraction module (i.e., SE-ResNet) and a task-specific classification module. Contextual Transformer (CoT) block is introduced in the classification module to dynamically model the local and global information of ECG feature sequence. The proposed method was evaluated on public CPSC2018 and PTB-XL datasets and achieved an average F1 score of 0.827 on the CPSC2018 dataset and an average F1 score of 0.833 on the PTB-XL dataset.

Electrocardiogram to Determine Mitral and Aortic Valve Opening and Closure.

Knowledge of the timing of cardiac valve opening and closing is important in cardiac physiology. The relationship between valve motion and electrocardiogram (ECG) is often assumed, however is not clearly defined. Here we investigate the accuracy of cardiac valve timing estimated using only the ECG, compared to Doppler echocardiography (DE) flow imaging as the gold standard. DE was obtained in 37 patients with simultaneous ECG recording. ECG was digitally processed and identifiable features (QRS, T, P waves) were examined as potential reference points to determine opening and closure of aortic and mitral valves, as compared to DE outflow and inflow measurement. Timing offset of the cardiac valves opening and closure between ECG features and DE was measured from derivation set (n = 19). The obtained mean offset in combination with the ECG features model was then evaluated on a validation set (n = 18). Using the same approach, additional measurement was also done for the right sided valves. From the derivation set, we found a fixed offset of 22 ± 9 ms, 2 ± 13 ms, 90 ± 26 ms, and -2 ± -27 ms when comparing S to aortic valve opening, Tend to aortic valve closure, Tend to mitral valve opening, and R to mitral valve closure respectively. Application of this model to the validation set showed good estimation of aortic and mitral valve opening and closure timing value, with low model absolute error (median of the mean absolute error of the four events = 19 ms compared to the gold standard DE measurement). For the right-sided (tricuspid and pulmonic) valves in our patient set, there was considerably higher median of the mean absolute error of 42 ms for the model. ECG features can be used to estimate aortic and mitral valve timings with good accuracy as compared to DE, allowing useful hemodynamic information to be derived from this easily available test.

A novel physiological feature selection method for emotional stress assessment based on emotional state transition.

The connection between emotional states and physical health has attracted widespread attention. The emotional stress assessment can help healthcare professionals figure out the patient's engagement toward the diagnostic plan and optimize the rehabilitation program as feedback. It is of great significance to study the changes of physiological features in the process of emotional change and find out subset of one or several physiological features that can best represent the changes of psychological state in a statistical sense. Previous studies had used the differences in physiological features between discrete emotional states to select feature subsets. However, the emotional state of the human body is continuously changing. The conventional feature selection methods ignored the dynamic process of an individual's emotional stress in real life. Therefore, a dedicated experimental was conducted while three peripheral physiological signals, i.e., ElectroCardioGram (ECG), Galvanic Skin Resistance (GSR), and Blood Volume Pulse (BVP), were continuously acquired. This paper reported a novel feature selection method based on emotional state transition, the experimental results show that the number of physiological features selected by the proposed method in this paper is 13, including 5 features of ECG, 4 features of PPG and 4 features of GSR, respectively, which are superior to PCA method and conventional feature selection method based on discrete emotional states in terms of dimension reduction. The classification results show that the accuracy of the proposed method in emotion recognition based on ECG and PPG is higher than the other two methods. These results suggest that the proposed method can serve as a viable alternative to conventional feature selection methods, and emotional state transition deserves more attention to promote the development of stress assessment.

ECG data compression using the formation of QRS-complex segment bank and integer DCT-based plateau region processing

Electrocardiogram (ECG) data is essential for evaluating cardiac health conditions. Long-term ECG signal monitoring needs a considerable amount of memory for storage, impacting data bandwidth allocation. The ECG data compression is challenging in preserving significant features, using low computational resources, and achieving a higher compression ratio at lower reconstruction error. This paper proposes an innovative QRS-complex and plateau (Non-QRS) region segregation for QRS-complex subsegment bank formation and integer cosine transform-based ECG data compression. An adaptive QRS-complex subsegment template bank is formed by: (i) QRS and Non-QRS region segmentation; (ii) QRS region identification; (iii) QRS region alignment; (iv) Dc equalization and sub-template formation of the QRS region. A discrete integer cosine transform, quantization, and grouping with a significance map are used on the non-QRS segment of the ECG. Both the QRS and non-QRS regions are coded by lossless arithmetic encoding. Experiments are enumerated on the MIT BIH arrhythmia database, which validates the potential of the proposed approach by achieving an average value equal to 31.51, 0.84, and 28.57 for compression ratio, percentage-root-mean-square-difference, and quality-score, respectively. The average distortion measure for the proposed ECG compressor is less than 2%, which is within the clinically acceptable limit. The proposed method is also compared to existing state-of-the-art ECG compression techniques. It performs better in terms of compression ratio and preservation of ECG features. Additionally, this method typically requires less computational resources and is easy to implement, which is an advantage over other ECG compression methods.

A vigilance estimation method for high-speed rail drivers using physiological signals with a two-level fusion framework

The vigilance decrement of high-speed rail (HSR) drivers is one of the main factors contributing to accidents. It’s necessary to develop an effective and reliable method to estimate HSR drivers’ vigilance. Given that response speed is one of the most important capabilities of HSR drivers, the reaction time (RT) of signal detection would be an objective indicator of vigilance. We explored the relationship between RTs and self-reported Karolinska Sleepiness Scale (KSS) scores. And analyzed the change of electroencephalogram (EEG) and electrocardiogram (ECG) features with RTs. Then, a regression model with two-level fusion was proposed to continuously evaluate HSR drivers’ vigilance by estimating their RTs. In the feature-level fusion, a convolutional neural network (CNN) module was used to fuse selected EEG and ECG. Then, EEG, ECG, and fused features were fed into three long short-term memory (LSTM) models to calculate HSR drivers’ RTs in parallel. In the decision-level fusion, a threshold filter was performed on the sub-results of three long short-term memory (LSTM) models to calculate the weights, and the final result was fused with the sub-results with a linear regression (LR) model. Data of 30 HSR drivers in a simulated experiment were used to validate our proposed method. The mean absolute error (MAE), root mean square error (RMSE), and Pearson correlation coefficient (PCC) of our model were 80.13 ms, 109.42 ms, and 0.83, respectively. The results indicated that the estimation accuracy and reliability were improved significantly. This method would make some contributions to developing HSR driver vigilance monitoring systems.

Affect and stress detection based on feature fusion of LSTM and 1DCNN

The impact of emotions on health, especially stress, is receiving increasing attention. It is important to provide a non-invasive affect detection system that can be continuously monitored for a long period of time. Multi-sensor fusion strategies can better improve the performance of affect detection models, but there are also problems such as insufficient feature extraction and poor spatiotemporal feature fusion. Therefore, this study proposes a feature-level fusion method based on long short-term memory and one-dimensional convolutional neural network to extract temporal and spatial features of electrocardiogram, electromyogram, electrical activity, temperature, accelerator and response data, respectively, and then fuse them in a summation fashion for affect and stress detection. In particular, we added the tanh activation function before feature fusion, which can improve the model’s performance. We used the wearable affect and stress detection dataset to train the model, which includes three different emotion states (neutral, stress, and amusement) for three-class emotion classification with accuracy and F1-scores of 87.82% and 86.68%, respectively. Due to the importance of stress, we also studied binary classification for stress detection, where neutral and amusement were combined as non-stress, with accuracy and F1-scores of 94.9% and 94.98%, respectively. The performance of the proposed model outperforms other control models and can effectively improve the performance of affect and stress detection, and promote medical care, health care and elderly care.

Percutaneous Epicardial Ablation of Ventricular Arrhythmias Arising from the Left Ventricular Summit.

The left ventricular summit (LVS) is the highest point of the left ventricular epicardium, and ventricular arrhythmias originating from this area accounts for 10% to 15% of idiopathic outflow tract ventricular arrhythmias. Direct epicardial ablation of outflow tract ventricular arrhythmias arising from the LVS is successful only in a minority of patients because of close proximity to the coronary artery or thick epicardial fat. Therefore, alternative strategies should be prioritized before performing epicardial approach. When performed, electrocardiogram characteristics suggestive of the site of origin to be the accessible area within the LVS needs be evaluated to avoid ineffective epicardial approach.

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.

Towards Automated Optimization of Residual Convolutional Neural Networks for Electrocardiogram Classification.

The interpretation of biological data such as theElectroCardioGram (ECG) signalgives clinical information and helps to assess theheart function. There are distinct ECG patterns associated with a specific class of arrhythmia. The convolutional neural network, inspired by findings in the study of biological vision, is currently one of the most commonly employed deep neural network algorithms for ECG processing. However, deep neural network models require many hyperparameters to tune. Selecting the optimal or thebest hyperparameter for the convolutional neural network algorithm is a highly challenging task. Often, we end up tuning the model manually with different possible ranges of values until a best fit model is obtained. Automatic hyperparameters tuning using Bayesian Optimization (BO) and evolutionary algorithms can provide an effective solution to current labour-intensive manual configuration approaches. In this paper, we propose to optimize the Residual one Dimensional Convolutional Neural Network model (R-1D-CNN) at two levels. At the first level, a residual convolutional layer and one-dimensional convolutional neural layers are trained to learn patient-specific ECG features over which multilayer perceptron layers can learn to produce the final class vectors of each input. This level is manual and aims to limit the search space and select the most important hyperparameters to optimize. The second level is automatic and based on our proposed BO-based algorithm. Our optimized proposed architecture (BO-R-1D-CNN) is evaluated on two publicly available ECG datasets. Comparative experimental results demonstrate that our BO-based algorithm achieves an optimal rate of 99.95% for the MIT-BIH database to discriminate between five kinds of heartbeats, including normal heartbeats, left bundle branch block, atrial premature, right bundle branch block, and premature ventricular contraction. Moreover, experiments demonstrate that the proposed architecture fine-tuned with BO achieves a higher accuracy tested on the10,000 ECG patients datasetcompared to the other proposed architectures. Our optimized architecture achieves excellent results compared to previous works on the two benchmark datasets.

A novel time representation input based on deep learning for ECG classification

Electrocardiogram (ECG) is an important tool used to analyze abnormal heart activity and assess heart health, especially in remote cardiac health monitoring. Although deep learning has achieved significant results in automatic ECG classification, how to combine the characteristics of ECG physiological signals to construct inputs or features with differentiation is still a key point of classification. To this end, a novel representation input method with temporal characteristics was proposed in this paper. At first, the temporal characteristic of ECG signals was extracted and transformed into a time representation input with the original input. Subsequently, the deep learning network combining Convolutional Neural Network and Long Short-Term Memory was employed for feature extraction. Simultaneous attention mechanism was used to focus on feature differences. The proposed method was validated in the classification of five classes of heartbeats (Normal heartbeat, Left bundle branch block heartbeat, Right bundle branch block heartbeat, Atrial Premature Contraction, Premature ventricular contraction), achieving a higher average accuracy, precision, sensitivity, and specificity of 98.95%, 97.07%, 96.54%, and 99.33% respectively in the MIT-BIH arrhythmia database. The results show that our method is able to combine the periodic characteristics of ECG to construct a better temporal representation input than traditional feature fusion. This method can provide a new way to classify similar physiological signals with periodic characteristics.

The Cardiovascular Disease Prediction Using Machine Learning

Because of technology developments, the ECG yields improved outcomes in the realm of biomedical science and research. The Electrocardiogram reveals basic the heart's electrical activity. Early detection of aberrant heart disorders is crucial for diagnosing cardiac problems and averting sudden cardiac deaths. Measurements on an electrocardiogram (ECG) among people with comparable cardiac issues are essentially equal. Analyzing the Electrocardiogram characteristics can help predict abnormalities. Medical professionals presently base the preponderance of their Electrocardiogram diagnosis on their unique particular areas of expertise, which places a substantial load on their shoulders and reduces their performance. The use of technology that automatically analyses ECGs as hospital personnel performs their duties will be advantageous. A suitable algorithm must be able to categories Input signal with uncertain awesome feature on just how much they approximate Input signal having known characteristics in order to speed up the identification of heart illnesses. A possibility of identifying a tachycardia is raised if this predictor can reliably recognize connections, and this technique may be helpful in lab settings. To accurately diagnose myocardial illness, a powerful machine learning technique should be used. Through using recommended method, the effectiveness of cardiovascular disease identification using ECG dataset was evaluated. The reliability, sensitivities, and validity obtained using the Svm algorithm were 99.314%, 97.60%, and 97.60% respectively.

Clinical characteristics of Danon disease

Objective: To review the clinical data of 7 patients with Danon disease and analyze their clinical characteristics. Methods: The medical records of 7 patients with Danon disease, who were hospitalized in Peking Union Medical College Hospital of Chinese Academy of Medical Sciences from April 2008 to July 2021, were reviewed and summarized, of which 6 cases were diagnosed as Danon disease by lysosomal-associated membrane protein-2 (LAMP-2) gene mutation detection and 1 case was diagnosed by clinicopathological features. Clinical manifestations, biochemical indexes, electrocardiogram, echocardiography, skeletal muscle and myocardial biopsy and gene detection results were analyzed, and patients received clinical follow-up after discharge. Results: Six patients were male and average age was (15.4±3.5) years and the average follow-up time was (27.7±17.0) months. The main clinical manifestations were myocardial hypertrophy (6/7), decreased myodynamia (2/7) and poor academic performance (3/7). Electrocardiogram features included pre-excitation syndrome (6/7) and left ventricular hypertrophy (7/7). Echocardiography examination evidenced myocardial hypertrophy (6/7), and left ventricular dilatation and systolic dysfunction during the disease course (1/7). The results of skeletal muscle biopsy in 6 patients were consistent with autophagy vacuolar myopathy. Subendocardial myocardial biopsy was performed in 3 patients, and a large amount of glycogen deposition with autophagosome formation was found in cardiomyocytes. LAMP-2 gene was detected in 6 patients, and missense mutations were found in all these patients. During the follow-up period, implantable cardioverter defibrillator implantation was performed in 1 patient because of high atrioventricular block 4 years after diagnosis, and there was no death or hospitalization for cardiovascular events in the other patients. Conclusion: The main clinical manifestations of Danon disease are cardiomyopathy, myopathy and mental retardation. Pre-excitation syndrome is a common electrocardiographic manifestation. Autophagy vacuoles can be seen in skeletal muscle and myocardial pathological biopsies. LAMP-2 gene mutation analysis is helpful in the diagnose of this disease.

ECG bio-identification using Fréchet classifiers: A proposed methodology based on modeling the dynamic change of the ECG features

Recently, the use of electrocardiogram (ECG) for human identification has attracted great attention. Generally, most existing ECG based biometric systems relay on extracting the static fiducial or non-fiducial features of the cardiac signal. However, the recorded ECG data is more likely to be different whenever it is measured. Such problem can be addressed by utilizing the dynamic change in ECG features. This paper proposes a new methodology for human identification via ECG, based on tracking the dynamic change in ECG features and utilizing the Fréchet distance measures for multiclass classification of feature matrices. The proposed dynamic feature matrices can be utilized to model nonstationary signals because they provide continues information on feature variability. Technically, we utilize the consecutive change of ECG power spectral density as significant feature. In addition, we use the dynamic change of QRS features as a distinguishable characteristic. At the classification stage, we use equations of Fréchet distances to perform multiclass classification because the covariance matrices of the dynamic feature matrices are symmetric positive definite, and their relative geometric space is not Euclidian. The performance of our methodology was evaluated using the publicly available ECG ID database of 62 subjects. To support real world applicability of our method, we randomized the reference / test data selection using data windowing techniques for examining the stability of our method by changing the datasets. The experimental results show that our methodology was able to achieve an identification accuracy of 97.03% with 0.971 precision, 0.999 specificity, 0.97 recall, 0.029 false rejection rate and 0.00048 false acceptance rate. Furthermore, the findings of our work show that Fréchet distances perform better than the Euclidian distance for ECG data classification in the context of multiclass classification problems.

Hybrid CNN-SVR Blood Pressure Estimation Model Using ECG and PPG Signals.

Continuous blood pressure (BP) measurement is vital in monitoring patients' health with a high risk of cardiovascular disease. The complex and dynamic nature of the cardiovascular system can influence BP through many factors, such as cardiac output, blood vessel wall elasticity, circulated blood volume, peripheral resistance, respiration, and emotional behavior. Yet, traditional BP measurement methods in continuously estimating the BP are cumbersome and inefficient. This paper presents a novel hybrid model by integrating a convolutional neural network (CNN) as a trainable feature extractor and support vector regression (SVR) as a regression model. This model can automatically extract features from the electrocardiogram (ECG) and photoplethysmography (PPG) signals and continuously estimates the systolic blood pressure (SBP) and diastolic blood pressure (DBP). The CNN takes the correct topology of input data and establishes the relationship between ECG and PPG features and BP. A total of 120 patients with available ECG, PPG, SBP, and DBP data are selected from the MIMIC III database to evaluate the performance of the proposed model. This novel model achieves an overall Mean Absolute Error (MAE) of 1.23 ± 2.45 mmHg (MAE ± STD) for SBP and 3.08 ± 5.67 for DBP, all of which comply with the accuracy requirements of the AAMI SP10 standard.

Intelligent Feature Selection for ECG-Based Personal Authentication Using Deep Reinforcement Learning.

In this study, the optimal features of electrocardiogram (ECG) signals were investigated for the implementation of a personal authentication system using a reinforcement learning (RL) algorithm. ECG signals were recorded from 11 subjects for 6 days. Consecutive 5-day datasets (from the 1st to the 5th day) were trained, and the 6th dataset was tested. To search for the optimal features of ECG for the authentication problem, RL was utilized as an optimizer, and its internal model was designed based on deep learning structures. In addition, the deep learning architecture in RL was automatically constructed based on an optimization approach called Bayesian optimization hyperband. The experimental results demonstrate that the feature selection process is essential to improve the authentication performance with fewer features to implement an efficient system in terms of computation power and energy consumption for a wearable device intended to be used as an authentication system. Support vector machines in conjunction with the optimized RL algorithm yielded accuracy outcomes using fewer features that were approximately 5%, 3.6%, and 2.6% higher than those associated with information gain (IG), ReliefF, and pure reinforcement learning structures, respectively. Additionally, the optimized RL yielded mostly lower equal error rate (EER) values than the other feature selection algorithms, with fewer selected features.

Conflicting results on the role of ECG in risk-stratification for sudden cardiac death in childhood hypertrophic cardiomyopathy.

The research group at University College London introduced the concept of standardizing the quantification of risk by assessing risk of sudden death or equivalent malignant arrhythmia event occurring during the subsequent 5 years of follow-up after diagnosis. While the aims in the recent article by Norrish et al.1 published in this journal are laudable, it is imperative to highlight the methodological shortcomings underlying their analysis. The authors aim to assess the ability of the electrocardiogram (ECG) risk-score and other aspects of the 12-lead ECG to predict ‘major arrhythmic cardiac event’. They selected a subset (356/1029) of the multi-centre cohort of paediatric patients with hypertrophic cardiomyopathy (HCM) used to construct the HCM Risk-Kids algorithm, where ECGs had been archived. This subset however consisted mainly of recently recruited patients, and so median follow-up was only 3.9 years (interquartile range Q1–Q3 2.0–7.7).1 A major concern is that Norrish et al. did not restrict their analysis to include only those survivors who had reached 5 years of follow-up (n = 77 + 68 = 145), and the patients who had a ‘major arrhythmic cardiac event’ within 5 years of follow-up (n = 17). Instead they compared all patients without events, even if 25% of them had <2 years follow-up, with all patients who had major arrhythmic cardiac event, even if 8 of them had an event later than 5 years of follow-up. Thus, in fact, only 17 (patients with major arrhythmic cardiac event within 5 years) + 145 (patients with ≥5 years follow-up without event) = 162 of the patients are actually statistically informative about the end-point of major arrhythmic cardiac event within 5 years.1 This constitutes only 46% of the total ECG group analysed. The other 194 actually confuse the results as patients with high-risk ECG features and short follow-up might have had a major arrhythmic cardiac event later on within the 5-year span. Similarly, the ECGs of patients with major arrhythmic cardiac event after >5 years of follow-up might have evolved more ECG changes closer to the event as shown in other studies.2 Thus including these late major arrhythmic cardiac events will underestimate the sensitivity of the method.

Electrocardiographic findings in patients with arrhythmogenic cardiomyopathy and right bundle branch block ventricular tachycardia.

Little is known about patients with right bundle branch block (RBBB)-ventricular tachycardia (VT) and arrhythmogenic cardiomyopathy (ACM). Our aims were: (i) to describe electrocardiogram (ECG) characteristics of sinus rhythm (SR) and VT; (ii) to correlate SR with RBBB-VT ECGs; and (iii) to compare VT ECGs with electro-anatomic mapping (EAM) data. From the European Survey on ACM, 70 patients with spontaneous RBBB-VT were included. Putative left ventricular (LV) sites of origin (SOOs) were estimated with a VT-axis-derived methodology and confirmed by EAM data when available. Overall, 49 (70%) patients met definite Task Force Criteria. Low QRS voltage predominated in lateral leads (n = 37, 55%), but QRS fragmentation was more frequent in inferior leads (n = 15, 23%). T-wave inversion (TWI) was equally frequent in inferior (n = 28, 42%) and lateral (n = 27, 40%) leads. TWI in inferior leads was associated with reduced LV ejection fraction (LVEF; 46 ± 10 vs. 53 ± 8, P = 0.02). Regarding SOOs, the inferior wall harboured 31 (46%) SOOs, followed by the lateral wall (n = 17, 25%), the anterior wall (n = 15, 22%), and the septum (n = 4, 6%). EAM data were available for 16 patients and showed good concordance with the putative SOOs. In all patients with superior-axis RBBB-VT who underwent endo-epicardial VT activation mapping, VT originated from the LV. In patients with ACM and RBBB-VT, RBBB-VTs originated mainly from the inferior and lateral LV walls. SR depolarization and repolarization abnormalities were frequent and associated with underlying variants.

Correlations Between Endocardial Voltage Mapping, Diagnosis, and Genetics in Patients With Arrhythmogenic Right Ventricular Cardiomyopathy

The relations between endocardial voltage mapping and the genetic background of patients with arrhythmogenic right ventricular cardiomyopathy (ARVC) have not been investigated so far. A total of 97 patients with proved or suspected ARVC who underwent 3-dimensional endocardial mapping and genetic testing have been retrospectively included. Presence, localization, and size of scar areas were correlated to ARVC diagnosis and the presence of a pathogenic variant. A total of 78 patients (80%) presented with some bipolar or unipolar scar on endocardial voltage mapping, whereas 43 carried pathogenic variants (44%). Significant associations were observed between presence of endocardial scars on voltage mapping and previous or inducible ventricular tachycardia, right ventricular function and dimensions, or electrocardiogram features of ARVC. A total of 60 of the 78 patients (77%) with an endocardial scar fulfilled the criteria for a definitive arrhythmogenic right ventricular dysplasia diagnosis versus 8 of 19 patients (42%) without scar (p=0.003). Patients with a definitive diagnosis of ARVC had more scars from any location and the scars were larger in patients with ARVC. In the 68 patients with a definitive diagnosis of ARVC, the presence of any endocardial scar was similar whether an ARVC-causal mutation was present or not. Only scar extent was significantly greater in patients with pathogenic variants. There was no difference in the presence and characteristics of scars in PKP2 mutated versus other mutated patients. The 3-dimensional endocardial mapping could have an important role for refining ARVC diagnosis and may be able to detect minor forms with otherwise insufficient criteria for diagnosis. The trend for larger scar extent were observed in mutated patients, without any difference according to the mutated genes.

Blood glucose estimation based on ECG signal.

Successful self-management of diabetes requires Continuous Glucose Monitors (CGMs). These CGMs have several limitations such as being invasive, expensive and limited in terms of use. Many techniques, in vain, have been proposed to overcome these limitations. Nowadays, with the help of the Internet of Medical Things (IoMT) technologies, researchers are working to find alternative solutions. They succeed to predict hypoglycemia and hyperglycemia peaks using Electrocardiogram (ECG) signals. However, they failed to use it to estimate the Blood Glucose Concentration (BGC) directly and in real time. Three patients with 08days of measurements from the D1namo dataset contributed to the study. A new technique has been proposed to estimate the BGC curves based on ECG signals. We used a convolutional neural network to segment the different regions of ECG signals as well as we extracted ECG features that were required for the next step. Then, five regression models have been employed to estimate BGC using as input sixth ECG parameters. We were able to segment the ECG signals with an accuracy of 94% using the convolutional neural network algorithm. The best performance among all simulated models was provided by Exponential Gaussian Process Regression (GPR) with Root Mean Squared Error (RMSE) values of 0.32, 0.41, 0.67 and R-squared (R2) values of 98%, 80%, and 70% for patients 01, 02 and 03 respectively. The method indicates the potential use of ECG wearable devices as non-invasive for continuous blood glucose monitoring, which is affordable and durable.

Identification of Coronary Culprit Lesion in ST Elevation Myocardial Infarction by Using Deep Learning.

Early revascularization of the occluded coronary artery in patients with ST elevation myocardial infarction (STEMI) has been demonstrated to decrease mortality and morbidity. Currently, physicians rely on features of electrocardiograms (ECGs) to identify the most likely location of coronary arteries related to an infarct. We sought to predict these culprit arteries more accurately by using deep learning. A deep learning model with a convolutional neural network (CNN) that incorporated ECG signals was trained on 384 patients with STEMI who underwent primary percutaneous coronary intervention (PCI) at a medical center. The performances of various signal preprocessing methods (short-time Fourier transform [STFT] and continuous wavelet transform [CWT]) with different lengths of input ECG signals were compared. The sensitivity and specificity for predicting each infarct-related artery and the overall accuracy were evaluated. ECG signal preprocessing with STFT achieved fair overall prediction accuracy (79.3%). The sensitivity and specificity for predicting the left anterior descending artery (LAD) as the culprit vessel were 85.7% and 88.4%, respectively. The sensitivity and specificity for predicting the left circumflex artery (LCX) were 37% and 99%, respectively, and the sensitivity and specificity for predicting the right coronary artery (RCA) were 88.4% and 82.4%, respectively. Using CWT (Morlet wavelet) for signal preprocessing resulted in better overall accuracy (83.7%) compared with STFT preprocessing. The sensitivity and specificity were 93.46% and 80.39% for LAD, 56% and 99.7% for LCX, and 85.9% and 92.9% for RCA, respectively. Our study demonstrated that deep learning with a CNN could facilitate the identification of the culprit coronary artery in patients with STEMI. Preprocessing ECG signals with CWT was demonstrated to be superior to doing so with STFT.