Detection of dominant reentries in multichannel electrograms of atrial fibrillation

Algorithms developed so far for the detection of local activation waves (LAWs) in electrograms (EGMs) of atrial fibrillation (AF) analyze each channel of the catheter separately, while dominant reentries of AF are captured by most of the catheter channels simultaneously. This encompasses the risk of losing or oversensing activations in the case of complex fractionated atrial electrograms (CFAEs). The proposed method analyzes multichannel recordings of AF from the least to the most fractionated. Activations are manually annotated and then EGMs are denoised, band-pass filtered by an alternative Bot-teron approach and thresholded. LAW detection is performed sequentially on all the channels by ascending fractionation order. Activations in the first EGM are found by an amplitude-based search, followed by a cycle length (CL) based search. Detection algorithm in the remaining signals is based on the previously detected LAWs, applying a varying search window according to the repetition rate of each activation. A CL-based search is also applied and activation time is computed from the barycenter of each LAW. The final step contains a secondary control that deletes all the low amplitude activations showing low repetition rate, so that any bias regarding the LAW detection of the first EGM is avoided. The method was compared with the equivalent sequential single-channel analysis, with the former showing better accuracy (90.82%) and positive predictive value (96.52%) than the single-channel approach (89.65% and 92.70%, respectively). Multichannel analysis performed a more selective analysis, ignoring some obvious but not repeated LAWs. Consequently, it can localize AF triggers and propagation phenomena more robustly than single channel method.