Atrial fibrillation subtypes classification using the General Fourier-family Transform

• Published in: Medical engineering & physics Vol. 36; no. 4; pp. 554 - 560
• Main Authors: Ortigosa, Nuria, Cano, Óscar, Ayala, Guillermo, Galbis, Antonio, Fernández, Carmen
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01-04-2014
• Subjects: Adult; Aged; Aged, 80 and over; Atrial fibrillation; Atrial Fibrillation - classification; Atrial Fibrillation - diagnosis; Atrial Fibrillation - physiopathology; Classification; Diagnosis, Computer-Assisted - methods; Diagnostic systems; Differentiation; Electrocardiography - methods; Female; Fibrillation; Fourier Analysis; Generalized Fourier Transform; Humans; Male; Medical; Middle Aged; Radiology; Recording; S-transform; Segments; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Support Vector Machine; Time–frequency transforms; Transforms; Time–frequency transforms; Atrial fibrillation; Generalized Fourier Transform; S-transform
• ISSN: 1350-4533; 1873-4030
• DOI: 10.1016/j.medengphy.2013.12.005

Abstract Atrial fibrillation patients can be classified into paroxysmal, persistent and permanent attending to the temporal pattern of this arrhythmia. The surface electrocardiogram hides this differentiation. A classification method to discriminate between the different subtypes of atrial fibrillation by using short segments of electrocardiograms recordings is presented. We will process the electrocardiograms (ECGs) using time–frequency techniques with a global accuracy of 80%. Real cases are evaluated showing promising results for an implementation in a semiautomated diagnostic system.