Arrhythmias Ventricular Fibrillation Research Articles

Efficient classification of ventricular arrhythmias using feature selection and C4.5 classifier

Abstract The occurrence of sudden cardiac arrest (SCA) leads to a massive death across the world. Hence the early prediction of ventricular tachycardia (VT) and ventricular fibrillation (VF) becomes vital to prevent from ventricular arrhythmia. In this study, we present a process to detect and classify VT and VF arrhythmias using temporal, spectral, and statistical features. The CU Ventricular Tachyarrhythmia Database (CUDB) and MIT-BIH Malignant Ventricular Ectopy Database (VFDB) databases are used from PhysioNet database for evaluation and comparison of the proposed algorithm. Thirteen time-frequency based features were extracted for a window length of 5 s with an appropriate thresholding to make a feature set. The gain ratio attribute evaluation has been used for potential utilization of the informative features by ranking them according to their individual evaluation weightage. Classification of selected features for VF, VT, and normal sinus rhythm (NSR) is done by using cubic support vector machine (SVM) and the C4.5 classifiers. Assessment of this process is done on 57 records of electrocardiogram (ECG) signals and the result shows that the proposed method achieved a sensitivity of 90.97%, specificity of 97.86% and accuracy of 97.02% in C4.5 classifier, which was better than the obtained results of cubic SVM having an accuracy of 92.23%. This study demonstrated that by using informative features and classifying them with C4.5 algorithms, the system data could be an aid to the clinician for precise detection of ventricular arrhythmias.

Dynamic and not static change in ventricular repolarization is a substrate of ventricular arrhythmia on chronic ischemic myocardium.

The restitution mechanism has been the focus of attention as the possible mechanism behind ventricular fibrillation (VF). However, its contribution in chronic ischemic heart has not been established. We investigated chronic ischemic dogs with occlusion of left anterior descending artery. Sixty unipolar electrograms were simultaneously recorded from an entire cardiac surface. Activation-recovery intervals (ARIs) and QRST deflection area (AQRST) were measured during constant atrial pacing. The ischemic dogs were divided into two groups, five dogs in VF(+) group or seven dogs in VF(-) group, according to VF occurrence by programmed electrical stimulation. When investigating ARI dispersions on an epicardium, there was no difference between VF(+) and VF(-) groups. The relationship between ARIs and diastolic intervals was quantified as an electrical restitution curve. The slopes of the ARI restitution curve for the anterior left ventricle in VF(+) dogs were significantly steeper than those of VF(-) dogs. The amplitude of AQRST alternans were significantly greater in VF(+) dogs than VF(-) dogs. Combined observation of steep restitution slopes and increased electrical alternans supported the restitution mechanism as being involved in the arrhythmia. Dynamic restitution properties and not static single-beat ARI dispersion may play an important role in the VF arrhythmia in the chronic ischemic heart.

Spiral waves are stable in discrete element models of two-dimensional homogeneous excitable media.

The spontaneous breakup of a single spiral wave of excitation into a turbulent wave pattern has been observed in both discrete element models and continuous reaction-diffusion models of spatially homogeneous 2D excitable media. These results have attracted considerable interest, since spiral breakup is thought to be an important mechanism of transition from the heart rhythm disturbance ventricular tachycardia to the fatal arrhythmia ventricular fibrillation. It is not known whether this process can occur in the absence of disease-induced spatial heterogeneity of the electrical properties of the ventricular tissue. Candidate mechanisms for spiral breakup in uniform 2D media have emerged, but the physical validity of the mechanisms and their applicability to myocardium require further scrutiny. In this letter, we examine the computer simulation results obtained in two discrete element models and show that the instability of each spiral is an artifact resulting from an unphysical dependence of wave speed on wave front curvature in the medium. We conclude that spiral breakup does not occur in these two models at the specified parameter values and that great care must be exercised in the representation of a continuous excitable medium via discrete elements.