Assessment of Intraprocedural Automated Arrhythmia Origin Localization System for Localizing Pacing Sites in 3D Space

The Automated Arrhythmia Origin Localization (AAOL) algorithm was developed for real-time prediction of early ventricular activation origins on a patient-specific electroanatomic (EAM) surface using a 3-lead electrocardiogram (AAOL-Surface). It has not been evaluated in 3-dimensional (3D) space (AAOL-3D), however, which may be important for predicting the arrhythmia origin from intramural or intracavity sites.

This study sought to assess the accuracy of AAOL for localizing earliest ventricular activation in 3D space.

This was a retrospective study of 3 datasets (BWH [Brigham and Women's Hospital], JHH [Johns Hopkins Hospital], and QEII [Queen Elizabeth II Health Sciences Centre]) involving 47 patients and 48 procedures, with an average of 19 ± 10 pacing sites each. In each patient, individual pacing sites were identified as target sites; the remaining pacing sites served as a training set (including QRS integrals from leads III, V₂, and V₆ with associated 3D coordinates). The AAOL-3D was then used to predict 3D coordinates of the pacing site. Localization error was assessed as the distance between known and predicted site coordinates, considering different EAM resolutions.

The AAOL-3D achieved a localization accuracy of 7.2 ± 3.1 mm, outperforming the AAOL-Surface (7.2 vs 7.8 mm; P < 0.05), with greater localization error for epicardial than endocardial pacing sites (8.7 vs 7.1 mm; P < 0.05). Cohort-specific analysis consistently favored AAOL-3D over AAOL-Surface in terms of accuracy. Exploration of AAOL-Surface accuracy across varying EAM resolutions showed optimal performance at the original and 75% resolution, with performance declining as resolution decreased.

The AAOL approach accurately identifies early ventricular activation origins in 3D and on EAM surfaces, potentially useful for identifying intramural arrhythmia origins.