Rotors Location During Atrial Fibrillation: A Framework Based on Data Fusion and Information Quality

Persistent atrial fibrillation (AF), a prevalent cardiac arrhythmia, is primarily sustained by rotor-type reentries, with their localization crucial for successful ablation treatment. Fractionated atrial electrogram (EGM) signals have been associated with the tip of the rotors, thus considered as ablation targets. However, the typical noise problems of physiological signals affect the result of EGM processing tools and, consequently, the ablation outcome. This study proposes a data fusion framework based on the Joint Directors of Laboratories model and information quality (IQ) assessment for locating rotor tips from EGMs simulated in a 2D model of human atrial tissue under AF conditions. Validation tests involved IQ criteria with metrics: i) EGMs underwent noise contamination to assess tolerance. ii) Signals were pre-processed. iii) Features were extracted to generate maps iv) Fuzzy inference was applied for evaluating the situation and risk. The IQ was mapped using a support vector machine by level. Finally, the IQ criteria were optimized through a particle swarm optimization algorithm. The results demonstrated superior functionality and performance compared to existing EGM–based rotor detection methods. The novelty of the presented approach lies in evaluating IQ across signal–processing stages, optimizing it through data fusion to extract rotor tip position knowledge.