Early detection of ventricular fibrillation (VF) and rapid ventricular tachycardia (VT) is crucial for the success of the defibrillation therapy. A wide variety of detection algorithms have been proposed based on temporal, spectral, or complexity parameters extracted from the ECG. However, these algorithms are mostly constructed by considering each parameter individually. In this study, we present a novel life-threatening arrhythmias detection algorithm that combines a number of previously proposed ECG parameters by using support vector machines classifiers. A total of 13 parameters were computed accounting for temporal (morphological), spectral, and complexity features of the ECG signal. A filter-type feature selection (FS) procedure was proposed to analyze the relevance of the computed parameters and how they affect the detection performance. The proposed methodology was evaluated in two different binary detection scenarios: shockable (FV plus VT) versus nonshockable arrhythmias, and VF versus nonVF rhythms, using the information contained in the medical imaging technology database, the Creighton University ventricular tachycardia database, and the ventricular arrhythmia database. sensitivity (SE) and specificity (SP) analysis on the out of sample test data showed values of SE=95%, SP=99%, and SE=92% , SP=97% in the case of shockable and VF scenarios, respectively. Our algorithm was benchmarked against individual detection schemes, significantly improving their performance. Our results demonstrate that the combination of ECG parameters using statistical learning algorithms improves the efficiency for the detection of life-threatening arrhythmias.

This letter introduces the epsiv-Huber loss function in the support vector regression (SVR) formulation for the estimation of biophysical parameters extracted from remotely sensed data. This cost function can handle the different types of noise contained in the dataset. The method is successfully compared to other cost functions in the SVR framework, neural networks and classical bio-optical models for the particular case of the estimation of ocean chlorophyll concentration from satellite remote sensing data. The proposed model provides more accurate, less biased, and improved robust estimation results on the considered case study, especially significant when few in situ measurements are available

Background— Diastolic suction is a major determinant of early left ventricular filling in animal experiments. However, suction remains incompletely characterized in the clinical setting. Methods and Results— First, we validated a method for measuring the spatio-temporal distributions of diastolic intraventricular pressure gradients and differences (DIVPDs) by digital processing color Doppler M-mode recordings. In 4 pigs, the error of peak DIVPD was 0.0±0.2 mm Hg (intraclass correlation coefficient, 0.95) compared with micromanometry. Forty patients with dilated cardiomyopathy (DCM) and 20 healthy volunteers were studied at baseline and during dobutamine infusion. A positive DIVPD (toward the apex) originated during isovolumic relaxation, reaching its peak shortly after mitral valve opening. Peak DIVPD was less than half in patients with DCM than in control subjects (1.2±0.6 versus 2.5±0.8 mm Hg, P <0.001). Dobutamine increased DIVPD in control subjects by 44% ( P <0.001) but only by 23% in patients with DCM ( P =NS). DIVPDs were the consequence of 2 opposite forces: a driving force caused by local acceleration, and a reversed (opposed to filling) convective force that lowered the total DIVPD by more than one third. In turn, local acceleration correlated with E-wave velocity and ejection fraction, whereas convective deceleration correlated with E-wave velocity and ventriculo:annular disproportion. Convective deceleration was highest among patients showing a restrictive filling pattern. Conclusions— Patients with DCM show an abnormally low diastolic suction and a blunted capacity to recruit suction with stress. By raising the ventriculo:annular disproportion, chamber remodeling proportionally increases convective deceleration and adversely affects left ventricular filling. These previously unreported mechanisms of diastolic dysfunction can be studied by using Doppler echocardiography.

This paper presents a new approach to auto-regressive and moving average (ARMA) modeling based on the support vector method (SVM) for identification applications. A statistical analysis of the characteristics of the proposed method is carried out. An analytical relationship between residuals and SVM-ARMA coefficients allows the linking of the fundamentals of SVM with several classical system identification methods. Additionally, the effect of outliers can be cancelled. Application examples show the performance of SVM-ARMA algorithm when it is compared with other system identification methods.