SPC365

Left atrial wall thickness measured by a machine learning method predicts AF recurrence after pulmonary vein isolation

Session: Comunicações Orais - Sessão 17 - Miscelânea
Speaker: Daniel A. Gomes

Congress: CPC 2024
Topic: P. Other
Theme: 37. Miscellanea
Subtheme: 05.4 Atrial Fibrillation - Treatment
Session Type: Comunicações Orais
FP Number: ---
Authors: Daniel A. Gomes; Ana Rita Bello; Pedro Freitas; Joana Certo Pereira; Daniel Nascimento Matos; Sara Guerreiro; Pedro Carmo; João Abecasis; Diogo Cavaco; Francisco Bello Morgado; António M. Ferreira; Pedro Adragão

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif"><strong>Background:</strong></span></span></p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif">Left atrial (LA) remodeling plays a significant role in the progression of atrial fibrillation (AF). Although LA wall thickness (LAWT) has emerged as an indicator of structural remodeling, its impact on AF outcomes remains unclear. We aimed to determine the association between LAWT and AF recurrence after pulmonary vein isolation (PVI).</span></span></p>

<p style="text-align:justify">&nbsp;</p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif"><strong>Methods:</strong></span></span></p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif">Single-center registry of patients enrolled for radiofrequency PVI from 2016 to 2018. In all cases, a pre-ablation CT scan was performed within less than 48 hours. Mean LAWT was retrospectively measured by a semi-automated machine learning method (ADAS 3D<sup>&reg;</sup>)&nbsp;with minimal human intervention. Additionally, regional tissue thickness was assessed in four different locations: roof, inferior, posterior, and anterior walls. In a subgroup of patients, a pre-ablation cardiac magnetic resonance (CMR) was also performed within the same week. LA functional parameters and fibrosis, using 3D delayed gadolinium enhancement, were analyzed. The primary endpoint was AF recurrence after a 3-month blanking period. </span></span></p>

<p style="text-align:justify">&nbsp;</p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif"><strong>Results:</strong></span></span></p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif">A total of 439 patients (mean age 61&plusmn;12 years, 62% male, 78% with paroxysmal AF) were included. The mean LAWT was 1.4&plusmn;0.2mm (from 0.9 to 1.9mm). Software processing duration was 8.2&plusmn;0.4 min, and the mean human input time was 1.3&plusmn;0.1 min. There was no correlation between LAWT and CT-derived LA volume index (LAVI; Spearman R &ndash;0.01, p=0.845). During a median follow-up of 5.8 (IQR 4.9&ndash;6.6) years, 238 patients (54%) had an AF relapse. After adjusting for known confounders including age, non-paroxysmal AF, LAVI, and chronic kidney disease, LAWT remained an independent predictor of time-to-recurrence (adjusted HR 6.49 [95% CI 2.70-15.49], p&lt;0.001). AF recurrence rates were 11%, 15%, and 21%/ year across terciles of increasing LAWT (log-rank p&lt;0.001) &ndash; Figure panel C. Additionally, annual recurrence rate&nbsp;progressively increased across the spectrum of LA structural remodeling, ranging from 8% (normal LAWT and LAVI) to 30%/ year (LAWT and LAVI both increased) &ndash; see also Figure panel D. The posterior LAWT revealed the strongest association with the study endpoint (HR 2.02 [95% CI 1.29-3.16], p=0.003). </span></span></p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif">In the cohort of 62 patients with both pre-ablation CT and CMR, LAWT showed weak correlations with LA ejection fraction and LA coupling index (Spearman R &lt;0.25; p=0.054 and p=0.093, respectively), and a moderate correlation with LA fibrosis (Spearman R 0.468; p&lt;0.001).</span></span></p>

<p style="text-align:justify">&nbsp;</p>

<p style="text-align:justify"><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif"><strong>Conclusions:</strong></span></span></p>

<p><span style="font-size:16px"><span style="font-family:Arial,Helvetica,sans-serif">Mean LAWT, easily assessed by a&nbsp;commercially available machine learning software, is an independent predictor of AF recurrence after PVI in the long term. This association is mainly driven by the posterior LAWT. Whether patients with increased LAWT should receive tailored therapies&nbsp;deserves further investigation.</span></span></p>