SVM classification of patients prone to atrial fibrillation

Abstract

A method is presented for automatic analysis of the P-wave, based on lead II of a 12-lead standard ECG, in resting conditions during a routine examination for the detection of patients prone to atrial fibrillation (AF), one of the most prevalent arrhythmias. After the P-wave delineation, a set of parameters to detect patients prone to AF was calculated from the P-wave. The detection efficiency was validated on an ECG database of 112 patients, including a control group of 40 people and a study group of 72 patients with documented AF. A support vector machine method (SVM) was applied, and the results obtained showed a specificity of 90% and a sensitivity of 85.7%. This represents an increase of more than 20% compared to two other classical classification methods: discriminant analysis and neural network.