Discriminating between supraventricular and ventricular tachycardias from EGM onset analysis

We hypothesize that the analysis of the ventricular electrogram onset (EGM onset) can discriminate between SVT and VT to obtain a simultaneous increase in sensitivity and specificity. We discuss our analysis of EGMs obtained during SVT and VT together with their preceding SRs in 38 SVT and 68 VT far field records from 16 patients. The, algorithmic implementation and the preprocessing tasks were performed through the support vector method (SVM), avoiding the overfitting by means of the statistical bootstrap resampling. To improve the safety for an individual patient, two new methods of incremental learning, based on the SVM, are proposed and tested on an independent set of spontaneous arrhythmia episodes.

[1]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..

[2]  J. M. Jenkins,et al.  Detection algorithms in implantable cardioverter defibrillators , 1996, Proc. IEEE.

[3]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Bramahn . Singh,et al.  Controlling cardiac arrhythmias: an overview with a historical perspective. , 1997, The American journal of cardiology.

[5]  Khaled H. Hamed,et al.  Time-frequency analysis , 2003 .

[6]  A. Artes-Rodriguez,et al.  Support vector black-box interpretation in ventricular arrhythmia discrimination , 2002, IEEE Engineering in Medicine and Biology Magazine.

[7]  W. M. Carey,et al.  Digital spectral analysis: with applications , 1986 .

[8]  M. Schlepper,et al.  Programmable VT Detection Enhancements in Implantable Cardioverter Defibrillator Therapy , 1995, Pacing and clinical electrophysiology : PACE.

[9]  S. Hohnloser,et al.  Intracardiac QRS Electrogram Width—An Arrhythmia Detection Feature for Implantable Cardioverter Defibrillators: Exercise Induced Variation as a Base for Device Programming , 1998, Pacing and clinical electrophysiology : PACE.

[10]  A. Schaumann,et al.  Enhanced detection criteria in implantable cardioverter-defibrillators to avoid inappropriate therapy. , 1996, The American journal of cardiology.

[11]  L. Bing Liem D.O.,et al.  Implantable Cardioverter-Defibrillator , 2001, Springer Netherlands.

[12]  Federico Girosi,et al.  Reducing the run-time complexity of Support Vector Machines , 1999 .

[13]  G. Wahba.  Support vector machines, reproducing kernel Hilbert spaces, and randomized GACV , 1999 .