Search

This paper is about the personal identification algorithm for adapting ubiquitous environment using electrocardiogram (ECG) that has been studied by a few researchers recently. The main characteristic of proposed algorithm uses together features analysis and morphological analysis method. The Principle Component Analysis (PCA) algorithm was applied for morphological analysis method and the features analysis method adapting to Support Vector Machine (SVM) classifier algorithm. We choose 18 ECG files from MIT-BIH Normal Sinus Rhythm Database for estimating algorithm performance. The algorithm extracts 100 heartbeats from each ECG file, and use 40 heartbeats for training and 60 heartbeats for testing. The proposed algorithm shows clearly superior performance in all ECG data, amounting to 93.89% heartbeat recognition rate and 100% ECG recognition rate.

In this chapter,we have proposed an integrated methodology for electrocardiogram (ECG) based differentiation of arrhythmia and normal sinus rhythm using genetic algorithm optimized k-means clustering. Open source databases consisting of the MIT BIH arrhythmia and MIT BIH normal sinus rhythm data are used. The methodology consists of QRS-complex detection using the Pan-Tompkins algorithm, principal component analysis (PCA), and subsequent pattern classification using the k-means classifier, error back propagation neural network (EBPNN) classifier, and genetic algorithm optimized k-means clustering. The m-fold cross-validation scheme is used in choosing the training and testing sets for classification. The k-means classifier provides an average accuracy of 91.21 % over all folds, whereas EBPNN provides a greater average accuracy of 95.79 %. In the proposed method, the k-means classifier is optimized using the genetic algorithm (GA), and the accuracy of this classifier is 95.79 %, which is equal to that of EBPNN. In conclusion, the classification accuracy of simple unsupervised classifiers can be increased to near that of supervised classifiers by optimization using GA. The application of GA to other unsupervised algorithms to yield higher accuracy as a future direction is also observed.

This paper presents a frequency-degree mapping algorithm which enables network analysis of human electrocardiogram (ECG) time series. Two important topological quantities, the average degree (AD) and the average shortest path length (APL) have been investigated in the associated networks of ECG time series. The results demonstrate that the quantity of AD can serve as an effective and reliable indicator in distinguishing malignant ventricular arrhythmias from normal sinus rhythm and other benignant arrhythmias. Meanwhile, the quantity of APL is shown to be capable of characterizing the heart rate, which may be helpful in detecting shockable rhythms.

International audience; Personalisation, i.e. parameter estimation of a cardiac ElectroPhysiology (EP) model is needed to build patient-specific models, which could then be used to understand and predict the complex dynamics involved in patient's pathology. In this paper, we present an EP model personalisation approach applied to an infarcted porcine heart, using contact mapping data and Diffusion Tensor MRI. The contact mapping data was gathered during normal sinus rhythm, on the ventricles in-vivo, endocardially as well as epicardially, using a CARTO mapping system. The Diffusion Tensor MRI was then obtained ex-vivo, in order to have the true cardiac fibre orientations, for the infarcted heart. Both datasets were then used to build and personalise the 3D ventricular electrophysiological model, with the proposed personalisation approach. Secondly, the effect of using only endocardial mapping or epicardial mapping measurements, on the personalised EP model was also tested.

Magnetocardiography (MCG) recordings were carried out on 40 subjects comprising of both normal and those with cardiac anomalies, referred by the collaborating hospital, with the view to compare with the routine 12 lead ECG. An indigenously built four channel Low Tc - SQUID system inside a magnetically shielded room was used for the MCG. In this paper, results on a few specific subjects are presented. In the case of a 68 years old male with ECG indicating Left Bundle Branch Block characterized by wide QRS and a barely split R peak, the MCG showed two well separated RR’ waves making a M pattern over several chest positions. A 51 years old male with normal sinus rhythm in the ECG, exhibited fragmented QRS (

We examine the effects of cardiac geometry and architecture on the excitable media paradigm, and illustrate the effect of cardiac structure on the dynamics of arrhythmias by investigating scroll wave filament dynamics in two biophysically-detailed heterogeneous models of the human left ventricular free wall.

Two versions of a new detector for automatic real-time detection of atrial fibrillation in non-invasive ECG signals are introduced. The methods are based on beat to beat variability, tachogram analysis and simple signal filtering. The implementation on mobile devices is made possible due to the low demand on computing power of the employed analysis procedures. The proposed algorithms correctly identified 436 of 440 five minute episodes of atrial fibrillation or flutter and also correctly identified up to 302 of 342 episodes of no atrial fibrillation, including normal sinus rhythm as well as other cardiac arrhythmias. These numbers correspond to a sensitivity of 99.1 % and a specificity of 88.3%.

Atrial fibrillation (AF) is the most common cardiac arrhythmia encountered in the clinical practice in the western countries. People with AF usually have a significantly increased risk of stroke. Clinically, AF is diagnosed by a surface electrocardiogram (ECG). AF is characterized by the absence of P-waves and by a rapid irregular ventricular rhythm. The algorithms for automatic detection of AF either rely on the absence of P-waves or are based on ventricular rhythm variability (RR variability). This work presents an automatic algorithm for AF real time detection based on the analysis of the RR series (ventricular interbeat intervals) and of the difference between successive RR intervals (\({\it \Delta}{\rm RR}\) intervals). Coefficient of variation of \({\it \Delta}{\rm RR}\) series and Shannon Entropy of RR series, computed over 5 minutes segments, are used to discriminate AF from normal sinus rhythm. A classifier based on the Mahalanobis distance is then used.

In the heart disease, the important problem of ECG arrhythmia is to discriminate ventricular arrhythmias from normal cardiac rhythm. This paper presents novel method based on the neural network with weighted fuzzy membership functions (NEWFM) for the discrimination of ventricular tachycardia (VT) and ventricular fibrillation (VF) from normal sinus rhythm (NSR). This paper uses two pre-processes, the Haar wavelet function and extraction feature method are carried out in order. By using these methods, six features can be generated, which are the input data of NEWFM. NEWFM classifies NSR and VT/VF beats by the trained bounded sum of weighted fuzzy membership functions (BSWFMs) using six input features from the Creighton University Ventricular Tachyarrhythmia Data Base (CUDB). The results are better than Amann's phase space reconstruction (PSR) algorithm, accuracy and specificity rates of 90.4% and 93.3%, respectively.

Discrete hidden Markov models (HMM) are trained in order to differentiate between RR series of persons in normal sinus rhythm and of post-myocardial infarct patients with six or more ventricular premature complexes per hour during 24 hour Holter ECG recording.

Herein, wemake a theoretical effort to characterize the interplay of the main stimuli underlying the cardiac control. Based on the analysis of heartbeat intervals and using neural coding strategies, we investigate the hypothesis that information theoretic principles could be used to give insights to the strategy evolved to control the heart. This encodes the sympathetic and parasympathetic stimuli. As a result of analysis, we illustrate and emphasize the basic sources that might be attributed to control the heart rate based on the interplay of the autonomic tones.

This chapter presents an Interval Type-2 fuzzy classifier and its application to ECG arrhythmic classification problem. The uncertainties associated with the membership functions are encapsulated by the footprint of uncertainty (FOU) and it is totally characterized by the upper membership function (UMF) and lower membership function (LMF). To enable designed membership functions (MFs) reflect the data, we proposed three types of FOU design strategies according to the dispersion of the data. The first and second designs comprise of Gaussian MFs with uncertain standard deviations and means respectively whereas the third design is the combination of both. The FOU is then further optimized through Genetic Algorithm. The proposed Type-2 fuzzy classifier has been applied to ECG arrhythmic classification problem to discriminate three types of ECG signals, namely the normal sinus rhythm (NSR), ventricular fibrillation (VF), and ventricular tachycardia (VT). The performance of the classifier is tested on MIT-BIH Arrhythmia database. The average period and pulse width of ECG data are extracted as the inputs to the classifier. Different sources of noises have been included to model the uncertainties associated with the vagueness in MFs and the unpredictability of the data. The results show that the proposed strategies to design the FOU are essential to achieve a high performance fuzzy rule-based classifier in face of the uncertainties.

This paper addresses the problem of automatic discrimination of rhythms in ECG signals. In particular the main focus of the paper is at discriminating normal sinus rhythm (NSR), ventricular tachycardia (VT), and ventricular fibrillation (VF). After de-noising ECG signal using db6 wavelet, some features of ECG signal are extracted. Then matrix feature is produced that is given to PNN neural network to classify NSR, VF and VT. Results show classification for 98.15% of NSR, 90% of VT and 93.33% of VF events.

Intracardiac catheter recordings are available in common clinical practice. They can therefore be employed to adapt and validate atrial computer models of individual patients. Hence, their information content needs to be analyzed quantitatively. During treatment of atrial arrhythmia such as atrial flutter or fibrillation, the location of ectopic foci in the pulmonary veins is of special interest. In this study, virtual catheter signals are extracted from an atrial simulation on a realistic geometry with normal sinus rhythm as well as ectopic stimuli in all four pulmonary veins. Using a simplified Pan-Tompkins algorithm, the activation times are determined. Based on the analysis of the activation sequence in a circular mapping catheter simulated on the posterior left atrial wall, all four ectopic foci can clearly be associated with the pulmonary vein they came from. For a catheter on the anterior wall, this is possible for three of the four ectopic beats. Despite the knowledge gathered for the personalization of patient models, such simulations may help cardiologists to better classify measured signals.

In this work the authors have developed and evaluated a new approach for the feature analysis of normal and abnormal beats of electrocardiogram (ECG) based on the discrete-wavelet-transform (DWT) coefficients using Daubechies wavelets. In the first step the real ECG signals were collected from the normal and abnormal subjects. DWT coefficients of each data window were calculated in the Matlab 7.4.0 environment using Daubechies wavelets of order 5 to a scale level of 11. The detail information of levels 1 and 2 was discarded, as the frequencies covered by these levels were higher than frequency content of the ECG. Thus for a scale level 11 decomposition, coefficients associated with approximation level 11 and details level 3 to 11 were retained for further processing. The recorded ECG was classified in to normal sinus rhythm (NSR) and three different disease conditions, namely: atrial fibrillation (AF), acute myocardial infarction (AMI) and myocardial ischaemia based on the discrete wavelet transform coefficients of isolated beats from the multi-beat ECG information.

Ventricular tachycardia and fibrillation are dangerous cardiac arrhythmias. Anti-arrhythmic drugs such as lidocaine (a class I drug) reinstate normal sinus rhythm, but they have pro-arrhythmic side effects and their mechanisms of action are poorly understood. We used computational models of human ventricular tissues to elucidate and quantify these mechanisms.

In a substantial number of patients atrial fibrillation (AF) recurs after successful electrical cardioversion, but at present there are no reliable clinical markers for confidently identifying the patients in which recurrence will occur within a short period of time. This study evaluates the predictive classification performance of Sample Entropy (SampEn) in the discrimination between recurrent and non-recurrent AF episodes. A validated database of 35 ECG recordings acquired from AF subjects undergoing cardioversion was used throughout the study, together with their known recurrence status at one month. SampEn was applied to these QRST-reduced electrocardiograms, to atrial activity (AA), and also to heart rate (R-R intervals). The sample entropy of R–R intervals was significantly reduced (p=0.043) in the recurrent AF episodes compared with maintenance sinus rhythm episodes. SampEn applied to the AA signal showed a opposite results, it was reduced with a significant increasing trend in the maintenance sinus rhythm episodes (p=0.017). There is a need for welldefined studies with larger patient groups in order to assess the entropy changes further and to look for possible changes, which might predict AF recurrence.

With an inverse computational approach using a multi-lead ECG recording of normal sinus rhythm in a patient spread of activation and repolarization was computed. Using this timing information, contributions to the standard 12-lead ECG were computed for selected segments of the heart. The results show that in none of the precordial leads is the influence of the right ventricle larger than from the left. The electric activity of basal regions and the RVOT are relatively poorly represented in the standard 12-lead ECG.

The digitalis glycosides have been employed widely in clinical medicine for nearly two centuries as the principal drug in the treatment of congestive heart failure. Many important advances in the past few years have considerably improved understanding of the physiologic, subcellular, and pharmacodynamic properties of the glycosides and their application in patients (Mason and Awan, 1979). This chapter focuses attention on the cardiac action of digitalis on the failing and nonfailing heart. Finally, these observations are integrated to provide a unified concept of the actions of the glycosides on the cardiocirculation.

Computerized electrocardiography had its inception in the late 1950s with the work of Pipberger (17, 23) and Caceres (5), followed in the early 1960s by Smith (21) and Pordy (19). This initial thrust was extended in other centers, including Arvedson in Sweden. The basic principle involved is the conversion of the analog electrocardiographic (Ecg) or vectorcardiograph (Vcg), or both signals to digits, using an analog to digital converter. The records in digital format are then processed by the modern digital computers, with proper programming and at incredible speeds to produce analyses of the tracings comparable to that obtained by the human observer.

From January, 1975 to August, 1977 twelve patients ranging in age from 37–73 years presented with the presumptive diagnosis of life- threatening ventricular tachycardia (VT). All had cardiac catheteriza­tions and electrophysiologic studies. Cardiac catheterization revealed ten to have coronary artery disease and nine of these had associated ventricular aneurysms. Two had congestive cardiomyopathies. Electro­physiologic evaluation showed three to be suffering from supraventric­ular tachycardias (SVTs) rather than VTs, and seven to have atrio­ventricular accessory pathways (AVAP). In three cases, electrophysio­logic observations suggested bundle of His (BH) — bundle branch re­entry played a role in the initiation of their VTs.

Pneumatically-controlled circulation (PCC) was applied to seven patients suffering from peripheral vascular diseases and to two patients suffering from lymphoedema of the extremities aged between 32 and 81 years.

The wide range of effects attributed to the biologically active polypeptides indicates fundamental actions upon excitable cells, and thus suggests the possibility that some of these substances might affect cardiac tissue. With this in mind, we studied the effects of bradykinin and of 6-glycine bradykinin on hydrocarbon-epinephrine cardiac arrhythmia in dogs. It was found that bigeminy, or coupled ventricular beats, evoked in this situation could temporarily be restored to normal sinus rhythm, apparently by direct action on the heart (Vick et al., 1965).