Introduction: The catheter ablation is the current method with higher success rate in the treatment of supraventricular tachyarrhythmias. Some of the cases a second procedure is needed (40% of AF treated with PVI), due to several factor, being one, the correct location of the arrhythmogenesis and related circuits to be target by ablation. In this study is presented a methodology based in non-invasive maps to improve diagnostic of type and mechanism location. Methods: This work ranked 40 biomarkers extracted from Phase, Dominant Frequency, Organization Index, Local Activation Time and Optical Flow maps. These maps were obtained from 22 distinct realistic arrhythmic models (AT: 8, AFL: 4 and AF: 10), on both torso and reconstructed epicardium signals (ECGi).
The pipeline ranked the biomarker's contribution in the classification of the maintaining arrhythmic mechanism and its location, based on a combination of three different indices: Analysis of variation (ANOVA), Kendall tau and Lasso.
Arrhythmia classification: The two best biomarkers for each arrythmia classification were used in a logistic regression-based algorithm.
Mechanism location: The same biomarkers were extracted from 4 different areas of the maps (anterior, posterior, left, and right) and ranked based in its contribution to the spatial location (left or right atrium) of the mechanism or circuit.
Results: On the torso maps, the mechanism classification obtained an overall accuracy of 0.864, with the location accuracy of 0.818, and on epicardium reconstructed maps (i.e ECGi) the accuracy is yet to be calculated. The novel Optical Flow (along with phase and frequency) related biomarkers showed a great contribution in the location and classification of the arrhythmias' mechanisms.
Conclusion: Non-invasive maps allow extraction of biomarkers to classify arrhythmia and locate its mechanism in the atria non-invasively. ECGI plus BSPM biomarkers further improve current knowledge of the cardiac arrhythmias which might impact in clinic therapy decision.