Organization tracking of long-term atrial fibrillation recordings: Differences between paroxysmal and persistent episodes

In this work, a method for non-invasive assessment of AF organization has been applied to discriminating between paroxysmal and long-term persistent AF episodes. Following extraction of the atrial activity (AA) signal, the dominant atrial frequency (DAF) of the AA was computed based on a hidden Markov model. Finally, the main atrial wave (MAW) was obtained by bandpass filtering centered on the DAF, thus providing a time series suitable for AF organization estimation with sample entropy (SampEn). The performance of the method was evaluated on 24-h Holter recordings with long-term changes in AF organization. The results showed that episodes of paroxysmal AF (0.0693 ± 0.0147) were consistently associated with lower SampEn than episodes with persistent AF (0.1056 ± 0.0146). Moreover, 94.2% of 1-min segments with paroxysmal AF and 88.6% of 1-min segments with persistent AF could be correctly classified based on SampEn information, thus making it possible to classify longterm recordings of patients without AF history.