Artificial Intelligence-adjudicated Spatio-Temporal Dispersion: A Patient-unique Fingerprint of Persistent Atrial Fibrillation.

BACKGROUND

Spatiotemporal dispersion-guided ablation is a tailored approach for patients in persistent atrial fibrillation (AF). The characterization of dispersion extent and distribution and its association with common clinical descriptors of persistent AF (PsAF) patients have not been studied.

OBJECTIVES

Artificial intelligence-adjudicated dispersion extent and distribution (AI-DED) was obtained with a machine/deep learning classifier (VX1 software, Volta Medical) in PsAF patients undergoing ablation. We tested the hypothesis that AI-DED is unique to each patient and independent of common procedural and clinical parameters.

METHODS

In a sub-analysis of the Ev-AIFib study (NCT03434964), spatiotemporal dispersion maps were built with VX1 software in 78 consecutives persistent and long-standing persistent AF patients and AI-DED was quantified using two distinct approaches (visual regional characterization or automated global quantification of AI-DED).

RESULTS

AI-DED paired-sub-region Euclidean distance measurements between 78 patients (average distance = 5.07 ± 0.60; min = 2.23 and max = 9.75) demonstrate that AI-DED is a patient-unique characteristic of PsAF. Importantly, both AF type and AF history do not correlate with AI-DED levels (R

CONCLUSIONS

The atrial distribution and extent of multipolar electrogram spatio-temporal dispersion follows a non-random, albeit patient-unique, distribution in PsAF patients. As such, AI-DED may represent a procedure-implementable fingerprint of the PsAF substrate.

Informations de copyright

Copyright © 2024. Published by Elsevier Inc.