Introduction: Conventional multielectrode mapping is not sufficient to reveal subsurface intramural activation. Thus, atrial fibrillation (AF) driver identification remains challenging. To overcome these limitations we utilized machine learning (ML) to identify AF drivers based on the combination of electrogram (EGM) and 3D structural magnetic resonance imaging (MRI) features. Hypothesis: Detailed electrogram features analysis, including minor deflections, combined with local structural features, can be used to define AF driver. Methods: Sustained AF was mapped in coronary perfused explanted human atria (n=7) with near-infrared optical mapping (NIOM) (0.3-0.9mm 2 resolution) and 64-electrode mapping catheter (3mm 2 resolution). Unipolar EGMs were analyzed for multiple features of the steepest negative deflection and the 2nd-4th steepest deflections in multicomponent EGMs. Atria underwent 9.4T MRI (154-180μm 3 resolution) with gadolinium enhancement and histology validation of fibrosis. Both 3D structural and EGM data from NIOM defined driver and non-driver regions were processed by ML algorithms (LR; PLSDA; GBM; CRF; PSVM; RSVM) using double cross-validation. Results: AF drivers’ reentrant tracks were defined by NIOM activation mapping, the gold-standard, and confirmed by targeted ablation. The best performing ML algorithm (PLSDA) correctly classified mapped driver region with 76.1% accuracy on the testing data. The most important features included sub-endocardial fibrosis, sub-epicardial fiber orientation, local wall thickness, beat-to-beat variability of multicomponent EGM deflections. Conclusions: The ML models pre-trained on combined EGM and structural features allow efficient classification of AF driver vs non-driver regions defined by the NIOM gold-standard. The results suggest that AF driver substrates formed by the combination of 3D fibrotic structural features, which correlate with local EGM characteristics.
Due to complex 3D human atrial structure, atrial fibrillation (AF) mapping with multielectrode arrays (MEA) mostly represents surface activation. Therefore, MEA may not properly visualize patient specific AF mechanisms, which impairs ablation outcomes. Conversely, near-infrared optical mapping (NIOM) visualizes subsurface intramural activation and can efficiently reveal reentrant drivers responsible for AF maintenance. Delay between surface activation seen by MEA electrograms (EGMs) vs subsurface activation seen by NIOM optical action potentials (OAPs) occurs due to dyssynchrony between myocardium layers, especially during AF. Coronary perfused explanted human atria (n=7) were mapped with NIOM (0.3-0.9mm 2 resolution) and 64-electrode MEA (3mm 2 resolution). Unipolar EGMs were analyzed for the steepest negative deflection. The delay between [-dV/dtmax] of unipolar EGMs and corresponding optical action potentials (OAPs) was compared in 500ms and 300ms pacing and AF. Subsequent structural analysis was done by 9.4T MRI (154-180μm 3 resolution) with gadolinium enhancement and histology. Delay between EGM and OAP local activation times rate-dependently and heterogeneously increased from 6±3 ms and 10±4 ms during 500ms and 300ms pacing to 15±11 ms (with maximum delay 47±18 ms) during pacing induced AF (average cycle length 124±65ms). Large local OAP-EGM delay, seen during AF, correlates with higher fibrosis percentage and fiber twist (p<0.05). NIOM identified reentrant drivers maintaining AF, which were incorrectly visualized as multiple breakthroughs in 68% of MEA maps (n=22). Higher frequency leads to an increased activation discrepancy between EGM and NIOM caused by increased dyssynchrony in regions of higher fibrosis percentage and fiber twist, which may prevent MEA from proper identification of AF drivers in diseased fibrotic human atria. Reannotation of EGM activation based on NIOM may be required for correct AF mechanisms visualization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.