Atrial activity extraction based on blind source separation as an alternative to QRST cancellation for atrial fibrillation analysis

Atrial fibrillation (AF) characterization from electrocardiogram (ECG) recordings requires the elimination of ventricular activity (VA). The present contribution demonstrates the potential of blind source separation (BSS) in atrial activity (AA) extraction from AF episodes. The applicability of BSS techniques relies on the assumption that AA and VA are decoupled, and hence can be regarded as generated by independent bioelectric sources. In the comparative experiments, a multi-lead AF signal model is synthesized by adding real AA from AF episodes to ECGs recorded from healthy patients. Two direct QRST-cancellation methods are also considered: template matching and subtraction, and adaptive noise cancellation. Further experiments are performed on real multi-lead recordings from 20 patients with AF episodes. The BSS approach shows a superior performance, thus manifesting the suitability of BSS techniques for AA extraction. As a favourable by-product, BSS arises as a novel technique for QRST-complex cancellation.