Empirical mode decomposition based ECG features in classifying and tracking ventricular arrhythmias

Ventricular arrhythmias (VA) are life-threatening pathophysiological conditions that seriously impact the normal functioning of the heart. Ventricular tachycardia (VT) and ventricular fibrillation (VF) are the two well known types of VA. VF is the lethal of the VAs and could be characterized by its organizational progression over time. The success of cardiac resuscitation strongly depends on the type of VA, its evolution over time and response to therapy. Due to the time critical nature of VF, computationally efficient quantification of VAs and swift feedback are essential. This work attempted to arrive at computationally efficient and data-driven techniques based on Empirical Mode Decomposition for classifying and tracking VAs over time. The approaches are divided into two aims: (1) 'in-hospital' scenarios for characterizing the dynamics of VA episodes to assist clinicians in planning long-term therapy options, and (2) 'out-of-hospital' scenarios for providing near real-time feedback to detect/track the progression of VAs over time to assist medical personnel select/modify therapy options. Using an ECG database of 61 60-s VA segments obtained for classifying VT vs. VF and sub-classifying VF into organized VF (OVF) and disorganized VF (DVF), maximum classification accuracies of 96.7% (AUC = 0.993) and 87.2% (AUC = 0.968) were obtained for classifying VT vs. VF and OVF vs. DVF during 'in-hospital' analysis. Additionally, two near real-time approaches were presented for 'out-of-hospital' analysis where average accuracies of 71% and 73% were achieved for VT/VF and OVF/DVF classification, as well as demonstrating strong potential for monitoring VA progressions over time.

Discriminative sparse coding of ECG during ventricular arrhythmias using LC-K-SVD approach

Ventricular tachycardia (VT) and ventricular fibrillation (VF) are two major types of ventricular arrhythmias that results due to abnormalities in the electrical activation in the ventricles of the heart. VF is the lethal of the two arrhythmias, which may lead to sudden cardiac death. The treatment options for the two arrhythmias are different. Therefore, detection and characterization of the two arrhythmias is critical to choose appropriate therapy options. Due to the time-varying nature of the signal content during cardiac arrhythmias, modeling and extracting information from them using time and frequency localized functions would be ideal. To this effect, in this work, we perform discriminative sparse coding of the ECG during ventricular arrhythmia with hybrid time-frequency dictionaries using the recently introduced Label consistent K-SVD (LC-K-SVD) approach. Using 944 segments of ventricular arrhythmias extracted from 23 patients in the Malignant Ventricular Ectopy and Creighton University Tachy-Arrhythmia databases, an overall classification accuracy of 71.55% was attained with a hybrid dictionary of Gabor and symlet4 atoms. In comparison, for the same database and non-trained dictionary (i.e the original dictionary) the classification accuracy was found to be 62.71%. In addition, the modeling error using the trained dictionary from LC-K-SVD approach was found to be significantly lower to the one using the non-trained dictionary.

Fusion of structural and functional cardiac magnetic resonance imaging data for studying ventricular fibrillation

Magnetic Resonance Imaging (MRI) techniques such as Current Density Imaging (CDI) and Diffusion Tensor Imaging (DTI) provide a complementing set of imaging data that can describe both the functional and structural states of biological tissues. This paper presents a Joint Independent Component Analysis (jICA) based fusion approach which can be utilized to fuse CDI and DTI data to quantify the differences between two cardiac states: Ventricular Fibrillation (VF) and Asystolic/Normal (AS/NM). Such an approach could lead to a better insight on the mechanism of VF. Fusing CDI and DTI data from 8 data sets from 6 beating porcine hearts, in effect, detects the differences between two cardiac states, qualitatively and quantitatively. This initial study demonstrates the applicability of MRI-based imaging techniques and jICA-based fusion approach in studying cardiac arrhythmias.

The effects of long chain polyunsaturated fatty acids on local activation properties in dogs vulnerable to atrial fibrillation

Marine derived long chain polyunsaturated fatty acids (PUFAs) were found to have benefits in reducing inducibility and maintenance of atrial fibrillation (AF) in a dog model. This study was conducted to evaluate the effect of PUFAs on local atrial electrical conduction properties acquired via a multi-electrode plaque sutured to the posterior wall of the left atrium of the heart in these dogs. Eleven dogs underwent simultaneous atrioventricular pacing (SAVP) for 2 weeks, and were organized into 2 groups: 5 dogs received no PUFAs (SAVP-PLACEBO), 6 dogs received Eicosapentaenoic or Docosahexaenoic acid derived from fish oils (SAVP-PUFA), where PUFAs were given for 21 days, starting 1 week prior to pacing and during the 2 week pacing period. Three features were extracted, which were the average conduction velocity, average intra atrial conduction time, and total activation time. The PUFA group had a faster average conduction velocity (0.82±0.19 m/s) than the PLACEBO group (0.47±0.21 m/s, P=0.02). Using the average conduction velocity feature, classification was performed with a linear classifier and leave-one-out method. In the SAVP-PLACEBO group, 60% of the dogs were correctly classified, and 66% of the dogs were correctly classified in SAVP-PUFA group, leading to an overall classification accuracy of 63.5%.

Blind source separation in characterizing ECG pre-shock waveforms during Ventricular Fibrillation

Ventricular Fibrillation (VF) is a cardiac arrhythmia for which the only available treatment option is defibrillation by electrical shock. Existing literature indicates that VF could be the manifestation of different sources controlling the heart with different degrees of organization. In this work we test the hypothesis that the pre-shock waveforms of successful and unsuccessful shock outcomes could be related to the number of independent sources present in these waveforms. The proposed method uses Blind Source Separation (BSS) to extract independent components in frequency direction from a pig database consisting of 20 pre-shock waveforms. The slope of the energy capture curve was used as an indicator to demonstrate the number of independent sources required to model the pre-shock waveforms. The results were also quantified by performing a linear discriminant analysis based classification achieving an overall classification accuracy of 75%. The results indicate that successful cases can be modeled with less number of independent sources compared to unsuccessful cases.

Automated signal pattern detection in ECG during human ventricular arrhythmias

Ventricular arrhythmias seriously affects cardiac function. Of these arrhythmias, Ventricular fibrillation is considered as a lethal cardiac condition. Recent studies have reported that ventricular arrhythmias are not completely random and may exhibit regional spatio-temporal organizations. These organizations could be indicative of reoccurring signal patterns and might be embedded within the surface electrocardiograms (ECGs) during ventricular arrhythmias. In this work, we aim to identify such reoccurring ECG signal patterns during ventricular arrhythmias. The detection of such signal patterns and their distribution could be of help in sub-classifying the affected population for better targeted diagnosis and treatment. Our analysis on 14 ECG segments (on average 3.24 minutes per segment) obtained from the MIT-BIH ventricular arrhythmia database identified three reoccurring signal patterns. A wavelet based technique was developed for automating the pattern identification process using ECGs. The proposed method achieved automated detection accuracies of 73.3%, 75.0% and 86.6% for the proposed signal patterns.

Wavelet-based features for characterizing ventricular arrhythmias in optimizing treatment options

Ventricular arrhythmias arise from abnormal electrical activity of the lower chambers (ventricles) of the heart. Ventricular tachycardia (VT) and ventricular fibrillation (VF) are the two major subclasses of ventricular arrhythmias. While VT has treatment options that can be performed in catheterization labs, VF is a lethal cardiac arrhythmia, often when detected the patient receives an implantable defibrillator which restores the normal heart rhythm by the application of electric shocks whenever VF is detected. The classification of these two subclasses are important in making a decision on the therapy performed. As in the case of all real world process the boundary between VT and VF is ill defined which might lead to many of the patients experiencing arrhythmias in the overlap zone (that might be predominately VT) to receive shocks by the an implantable defibrillator. There may also be a small population of patients who could be treated with anti-arrhythmic drugs or catheterization procedure if they can be diagnosed to suffer from predominately VT after objectively analyzing their intracardiac electrogram data obtained from implantable defibrillator. The proposed work attempts to arrive at a quantifiable way to scale the ventricular arrhythmias into VT, VF, and the overlap zone arrhythmias as VT-VF candidates using features extracted from the wavelet analysis of surface electrograms. This might eventually lead to an objective way of analyzing arrhythmias in the overlap zone and computing their degree of affinity towards VT or VF. A database of 24 human ventricular arrhythmia tracings obtained from the MIT-BIH arrhythmia database was analyzed and wavelet-based features that demonstrated discrimination between the VT, VF, and VT-VF groups were extracted. An overall accuracy of 75% in classifying the ventricular arrhythmias into 3 groups was achieved.

Phosalone poisoning on the cation-linked ATPases of central nervous system of Rana tigrina (Daudin)

An acute dose of phosalone, an organophosphate pesticide, widely used in crop fields, injected to Rana tigrina, intraperitoneally, inhibited the different inorganic ion linked ATPase enzymes of the central nervous system (CNS). Six discrete CNS compartments, namely telencephalon, mid-brain, rhombencephalon, cervical spinal cord, thoracic spinal cord and lumbar spinal cord showed markedly diminished ATPase activity. ATPases inhibition affected the neuronal activity and muscular coordination leading to moribund or comatose phase in the poisoned frogs. The specific inhibition of Mg(2+)-ATPase suggests the uncoupling action of the compound in the neuronal tissue. Increased oxygen uptake in the brain regions of phosalone-treated frogs also supports the above uncoupling action.