Source Classification in Atrial Fibrillation Using a Machine Learning Approach

A precise analysis of the atrial activity (AA) signal in electrocardiogram (ECG) recordings is necessary for a better understanding of the mechanisms behind atrial fibrillation (AF). Blind source separation (BSS) techniques have proven useful in extracting the AA source from ECG recordings. However, the automated selection of the AA source among the other sources after BSS is still an issue. In this scenario, the present work proposes two contributions: i) the use of the normalized mean square error of the TQ segment (NMSE-TQ) as a new feature to quantify the AA content of a source, and ii) an automated classification of AA and non-AA sources using three well-known machine learning algorithms. The tested classifiers outperform the techniques present in literature. A pattern in the mean and standard deviation of the used features, for AA and non-AA sources, is also observed.