Novel Rank-based Features of atrial potentials for the Classification Between Paroxysmal and Persistent Atrial Fibrillation

Hanie Moghaddasi1, Richard Hendriks1, Alle-Jan van der Veen1, Natasja de Groot2, Borbala Hunyadi1
1TU Delft, 2Erasmus MC


Atrial fibrillation (AF) is the most common arrhythmia. Although the exact cause is unclear, electropathology of atrial tissue is one contributing factor. Electropathological characteristics derived from intra-operative epicardial measurements, such as conduction block (CB), can be used to assess the severity of AF. In sinus rhythm, however, this parameters does not indicate significant differences between different development stages of AF, such as paroxysmal and persistent AF. Therefore, we propose a methodology to improve AF severity detection using intra-operative electrograms. We propose a model that describes the spatial diversity of atrial potential waveforms during a single beat on the multi-channel electrograms. Based on this model, we derive two novel features. During sinus rhythm, we used 334 beats from patients with a history of PAF or PsAF. Using a random forest classifier, we achieved 80.38\% classification accuracy, while classification based on the CB leads to an accuracy of 57.22\%