Arrhythmia Discrimination in Implantable Cardioverter Defibrillators Using Support Vector Machines Applied to a New Representation of Electrograms

Author

Milpied, Paola ; Dubois, Rémi ; Roussel, Pierre ; Henry, Christine ; Dreyfus, Gérard

Author_Institution

Dept. of Adv. Clinical Res., Sorin CRM, Clamart, France

Volume

58

Issue

6

fYear

2011

fDate

6/1/2011 12:00:00 AM

Firstpage

1797

Lastpage

1803

Abstract

Arrhythmia classification remains a major challenge for appropriate therapy delivery in implantable cardioverter defibrillators (ICDs). The purpose of this paper is to present a new algorithm for arrhythmia discrimination based on a statistical classification by support vector machines of a novel 2-D representation of electrograms (EGMs) named spatial projection of tachycardia (SPOT) EGMs. SPOT-based discrimination algorithm provided sensitivity and specificity of 98.8% and 91.3%, respectively, on a test database. A simplified version of the algorithm is also presented, which can be directly implemented in the ICD.

Keywords

defibrillators; electrocardiography; pacemakers; prosthetics; statistical analysis; support vector machines; 2D representation; SPOT-based discrimination algorithm; arrhythmia classification; arrhythmia discrimination; electrograms; implantable cardioverter defibrillators; statistical classification; support vector machines; tachycardia spatial projection; therapy delivery; Classification algorithms; Databases; Electric shock; Mathematical model; Support vector machine classification; Training; Arrhythmias; electrogram (EGM) morphology; implantable cardioverter defibrillators (ICDs); inappropriate therapy; spatial projection of tachycardia (SPOT); support vector machines (SVMs); Adult; Aged; Algorithms; Artificial Intelligence; Defibrillators, Implantable; Electrophysiologic Techniques, Cardiac; Female; Humans; Male; Middle Aged; Signal Processing, Computer-Assisted; Tachycardia;

fLanguage

English

Journal_Title

Biomedical Engineering, IEEE Transactions on

Publisher

ieee

ISSN

0018-9294

Type

jour

DOI

10.1109/TBME.2011.2117424

Filename

5716669