Search

Solving individual differences between subjects is critical for the promotion of electrocardiogram (ECG) classification algorithms in the intelligent health monitoring industry. Popular inter-subject-based solutions usually require the manual labeling of heartbeats and frequent updating of the model for new subjects. To track these problems, we propose a hypergraph and cross-attention-based unsupervised domain adaptation (HGCA-UDA) framework for the myocardial infarction localization. Specifically, we first build a hypergraph-based dual-channel network, that can simultaneously learn specific feature representations from an ECG lead and disease category levels for samples from different domains. We then design a cross-attention module to align cross-domain locally similar samples. Subsequently, a domain alignment strategy based on the Wasserstein distance is proposed to align the global edge feature distribution. Finally, a pseudo-label generation scheme is proposed to further align fine-grained category information. We conduct extensive experiments on two public benchmark datasets (the Physikalisch-Technische Bundesanstalt (PTB) and PTB_XL database), and the results show that the proposed HGCR-UDA (with unlabeled patients) achieves comparable results compared with state-of-the-art inter-patient-based methods (with labeled patients) and has excellent applications prospects in the field of intelligent health monitoring. [ABSTRACT FROM AUTHOR]

Electrocardiography (ECG) is a sophisticated tool for the diagnosis of myocardial infarction (MI). Deep learning approaches can support MI diagnosis based on ECG data. However, due to privacy issues and the sensitive nature of ECG data, the use of deep learning methods to access large amounts of ECG data for training remains challenging. Insufficient data will lead to a decrease in diagnosis performance. In addition, most deep learning approaches are trained with multiple-lead ECG data, thereby limiting the extension to portable single-lead ECG monitoring devices. Investigating automated single-lead ECG interpretation is a continuing concern in the development of mobile and wearable ECG monitoring devices. This paper proposes an automated myocardial infarction detection model — SLC-GAN — that synthesizes single-lead ECG data with high morphological similarity through generative adversarial networks (GANs). It automatically detects MI using convolutional neural networks (CNNs) with real ECG data and synthetic ECGs from the GAN. The empirical results indicate that our new SLC-GAN method performs impressively compared with other MI classification methodologies on single-lead ECG from the PTB Diagnostic ECG Database. The MI classification accuracy of SLC-GAN reaches 99.06% with 5-fold cross-validation. [ABSTRACT FROM AUTHOR]

The practice of employing empirical likelihood (EL) components in place of parametric likelihood functions in the construction of Bayesian-type procedures has been well-addressed in the modern statistical literature. The EL prior, a Jeffreys-type prior, which asymptotically maximizes the Shannon mutual information between data and the parameters of interest, is rigorously derived. The focus of the proposed approach is on an integrated Kullback–Leibler distance between the EL-based posterior and prior density functions. The EL prior density is the density function for which the corresponding posterior form is asymptotically negligibly different from the EL. The proposed result can be used to develop a methodology for reducing the asymptotic bias of solutions of general estimating equations and M-estimation schemes by removing the first-order term. This technique is developed in a similar manner to methods employed to reduce the asymptotic bias of maximum likelihood estimates via penalizing the underlying parametric likelihoods by their Jeffreys invariant priors. A real data example related to a study of myocardial infarction illustrates the attractiveness of the proposed technique in practical aspects. [ABSTRACT FROM AUTHOR]

Abstract One of the most high-risk locations of plaque growth and rupture initiation (and hence occurrence of heart attack) is the first main bifurcation of the left main coronary artery; the aim of this investigation is to analyse the nonlinear three-dimensional biomechanics of bifurcated atherosclerotic left coronary artery. In order to examine the influence of different system parameters, a biomechanical model of a bifurcated coronary artery is developed. Three plaques of varying geometry and material properties inside the three branches of the left main (LM), the left anterior descending (LAD), and the left circumflex (LCx) are modelled incorporating three-dimensionality, nonlinear geometric and material properties, asymmetry, viscosity, and hyperelasticity, and fluid-solid interaction. A finite element method (FEM) is employed to incorporate all of the above-mentioned important features in addition to physiological blood pulsation, heart motion, active media layer contraction, lipid plaque, calcium deposition, three different artery layers, micro-calcification, and non-Newtonian model for blood. Moreover, the effects of different system features such as stenosis, curved shape of the artery, plaque location, and fibrous cap thickness on the stress field (shear and structural) are examined. The developed biomechanical model could be utilised to estimate the risk of the initiation of plaque rupture inside the human coronary artery and the occurrence of heart attack. [ABSTRACT FROM AUTHOR]

Background Understanding the effects of cardiac diseases on the heart's functionality which is the purpose of many biomedical researches, directly affects the diagnostic and therapeutic methods. Myocardial infarction (MI) is a common complication of cardiac ischemia, however, the impact of MI on the left ventricle (LV) flow patterns has not been widely considered by computational fluid dynamics studies thus far. Methods In this study, we present an insightful numerical method that creates an artificial MI on an image-based fluid-structure interactional model of normal LV to investigate its influence on the flow in comparison with the normal case. Seventeen different models were developed to evaluate the effects of location, percentage, myocardial material properties and dilation size of MI on the LV's performance, area strain, wall displacement, pressure-volume loop, wall shear stress and velocity field. Results The results show that MI considerably changes blood flow features which are fully dependent on MI parameters. For the case of constant MI location, the effect of a decrease of infarcted myocardium stiffness, increase of dilation size and increase of MI percentage are mostly similar. Although the location differences of MI under other constant conditions have similar impact on the ejection fraction, they also lead to dissimilar variations in the LV flow pattern and other indicators. Conclusions The presented model showed a capable computational method for investigating various mechanical MI conditions with respect to cardiac flow pattern. The perspective of this model development seems to be an applicable tool for MI clinical diagnosis and prediction of complications related to MI. [ABSTRACT FROM AUTHOR]

The electrocardiogram (ECG) is a useful diagnostic tool to diagnose various cardiovascular diseases (CVDs) such as myocardial infarction (MI). The ECG records the heart's electrical activity and these signals are able to reflect the abnormal activity of the heart. However, it is challenging to visually interpret the ECG signals due to its small amplitude and duration. Therefore, we propose a novel approach to automatically detect the MI using ECG signals. In this study, we implemented a convolutional neural network (CNN) algorithm for the automated detection of a normal and MI ECG beats (with noise and without noise). We achieved an average accuracy of 93.53% and 95.22% using ECG beats with noise and without noise removal respectively. Further, no feature extraction or selection is performed in this work. Hence, our proposed algorithm can accurately detect the unknown ECG signals even with noise. So, this system can be introduced in clinical settings to aid the clinicians in the diagnosis of MI. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVDs) are the main cause of cardiac death worldwide. The Coronary Artery Disease (CAD) is one of the leading causes of these CVD deaths. CAD condition progresses rapidly, if not diagnosed and treated at an early stage may eventually lead to an irreversible state of heart muscle death called Myocardial Infarction (MI). Normally, the presence of these cardiac conditions is primarily reflected on the electrocardiogram (ECG) signal. However, it is challenging and requires rich experience to manually interpret the visual subtle changes occurring in the ECG waveforms. Thus, many automated diagnostic systems are developed to overcome these limitations. In this study, the performance of an automated diagnostic system developed for detection of CAD and MI using three methods such as Discrete Wavelet Transform (DWT), Empirical Mode Decomposition (EMD) and Discrete Cosine Transform (DCT) are compared. In this study, ECG signals are subjected to DCT, DWT and EMD to obtain respective coefficients. These coefficients are reduced using Locality Preserving Projection (LPP) data reduction method. Then, the LPP features are ranked using F-value. Finally, the highly ranked coefficients are fed into the K-Nearest Neighbor (KNN) classifier to achieve the best classification performance. Our proposed system yielded highest classification results of 98.5% accuracy, 99.7% sensitivity and 98.5% specificity using only seven features obtained using DCT technique. The screening system can help the cardiologists in detecting the CAD and hence presents any possible MI by prescribing suitable medications. It can be employed in routine community screening, old age homes, polyclinics and hospitals. [ABSTRACT FROM AUTHOR]

• A fractional order COVID-19 model is developed to examine the spread of it with and without OMICRON variant. • The relationship of Omicron SARS-CoV-2 variant with heart attack using real data from the United Kingdom has been investigated. • By using least-squares curve fitting technique (LCM), the fitting of the parameters is implemented. • The sensitivity analysis of the parameters according to the reproduction number is given. • The memory trace and hereditary traits are taken into consideration. In this study, a new approach to COVID-19 pandemic is presented. In this context, a fractional order pandemic model is developed to examine the spread of COVID-19 with and without Omicron variant and its relationship with heart attack using real data from the United Kingdom. In the model, heart attack is adopted by considering its relationship with the quarantine strategy. Then, the existence, uniqueness, positivity and boundedness of the solution are studied. The equilibrium points and their stability conditions are achieved. Subsequently, we calculate the basic reproduction number (the virus transmission coefficient) that simply refers to the number of people, to whom an infected person can make infected, as R 0 = 3.6456 by using the next generation matrix method. Next, we consider the sensitivity analysis of the parameters according to R 0. In order to determine the values of the parameters in the model, the least squares curve fitting method, which is one of the leading methods in parameter estimation, is benefited. A total of 21 parameter values in the model are estimated by using real Omicron data from the United Kingdom. Moreover, in order to highlight the advantages of using fractional differential equations, applications related to memory trace and hereditary properties are given. Finally, the numerical simulations are presented to examine the dynamic behavior of the system. As a result of numerical simulations, an increase in the number of people who have heart attacks is observed when Omicron cases were first seen. In the future, it is estimated that the risk of heart attack will decrease as the cases of Omicron decrease. [ABSTRACT FROM AUTHOR]

• Scar tissue border zone is a major determinant of the onset of simulated cardiac reentry • Reentrant cycles may develop within a sub-epicardial border zone wedging between unexcitable scars • Reentrant cycles may develop within a homogeneous sub-epicardial border zone covering a scar • Reentrant pathways follow epicardial fiber direction regardless of the endocardial stimulation site • Thin, rather than thick, sub-epicardial border zone facilitates the onset of reentry Cardiac ventricular tachycardia (VT) is a life-threatening arrhythmia consisting of a well organized structure of reentrant electrical excitation pathways. Understanding the generation and maintenance of the reentrant mechanisms, which lead to the onset of VT induced by premature beats in presence of infarct scar, is one of the most important issues in current electrocardiology. We investigate, by means of numerical simulations, the role of infarct scar dimension, repolarization properties and anisotropic fiber structure of scar tissue border zone (BZ) in the genesis of VT. The simulations are based on the Bidomain model, a reaction-diffusion system of Partial Differential Equations, discretized by finite elements in space and implicit-explicit finite differences in time. The computational domain adopted is an idealized left ventricle affected by an infarct scar extending transmurally. We consider two different scenarios: i) the scar region extends along the entire transmural wall thickness, from endocardium to epicardium, with the exception of a BZ region shaped as a central sub-epicardial channel (CBZ); ii) the scar region extends transmurally along the ventricular wall, from endocardium to a sub-epicardial surface, and is surrounded by a BZ region (EBZ). In CBZ simulations, the results have shown that: i) the scar extent is a crucial element for the genesis of reentry; ii) the repolarization properties of the CBZ, in particular the reduction of IKs and IKr currents, play an important role in the genesis of reentrant VT. In EBZ simulations, since the possible reentrant pathway is not assigned a-priori, we investigate in depth where the entry and exit sites of the cycle of reentry are located and how the functional channel of reentry develops. The results have shown that: i) the interplay between the epicardial anisotropic fiber structure and the EBZ shape strongly affects the propensity that an endocardial premature stimulus generates a cycle of reentry; ii) reentrant pathways always develop along the epicardial fiber direction; iii) very thin EBZs rather than thick EBZs facilitate the onset of cycles of reentry; iv) the sustainability of cycles of reentry depends on the endocardial stimulation site and on the interplay between the epicardial breakthrough site, local fiber direction and BZ rim. [ABSTRACT FROM AUTHOR]