Leire Moriones

Ms. Leire Moriones

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 August 2025 in Biomedicines
Verified
Journal Article
Open access
PDF file
JIJavier Ibero
Javier Ibero
IGIgnacio García-Bolao
Ignacio García-Bolao
GBGabriel Ballesteros
Gabriel Ballesteros
PRPablo Ramos
Pablo Ramos
RARamon Albarran
Ramon Albarran
IDInes Diaz-Dorronsoro
Ines Diaz-Dorronsoro
Background: Atrial fibrosis is a key contributor to atrial cardiomyopathy and can be assessed invasively using mean left atrial voltage (MLAV) from electroanatomical mapping. However, the invasive nature of this procedure limits its clinical applicability. Machine learning (ML), particularly regression tree-based models, may offer a non-invasive approach for predicting MLAV using clinical and echocardiographic data, improving non-invasive atrial fibrosis characterisation beyond current dichotomous classifications. Methods: We prospectively included and followed 113 patients with paroxysmal or persistent atrial fibrillation (AF) undergoing pulmonary vein isolation (PVI) with ultra-high-density voltage mapping (uHDvM), from whom MLAV was estimated. Standardised two-dimensional transthoracic echocardiography was performed before ablation, and clinical and echocardiographic variables were analysed. A regression tree model was constructed using the Classification and Regression Trees—CART-algorithm to identify key predictors of MLAV. Results: The regression tree model exhibited moderate predictive accuracy (R2 = 0.63; 95% CI: 0.55–0.71; root mean squared error = 0.90; 95% CI: 0.82–0.98), with indexed minimum LA volume and passive emptying fraction emerging as the most influential variables. No significant differences in AF recurrence-free survival were found among MLAV tertiles or model-based generated groups (log-rank p = 0.319 and p = 0.126, respectively). Conclusions: We present a novel ML-based regression tree model for non-invasive prediction of MLAV, identifying minimum LA volume and passive emptying fraction as the most significant predictors. This model offers an accessible, non-invasive tool for refining atrial cardiomyopathy characterisation by reflecting the fibrotic substrate as a continuum, a crucial advancement over existing dichotomous approaches to guide tailored therapeutic strategies.

26 June 2026 in European Journal of Radiology
Verified
Journal Article
Open access
LMLeire Moriones
Leire Moriones
Pablo LamataPablo Lamata
Pablo Lamata
BEBlas Echebarria
Blas Echebarria
DLDavid Laroze
David Laroze
JIJavier Ibero
Javier Ibero
JBJean Bragard
Jean Bragard
Atrial fibrillation (AF) involves heterogeneous remodelling of the left atrium (LA), making accurate geometric quantification clinically relevant. CT is the reference standard for anatomical assessment, whereas electroanatomical mapping (EAM) provides intraprocedural reconstruction with electrophysiological information. However, agreement between both modalities remains incompletely characterized. We retrospectively analyzed 211 patients undergoing first-time catheter ablation with pre-procedural CT imaging. LA volume, surface area, and sphericity were derived from CT and EAM. A common ellipsoidal model was fitted to both datasets for comparison via semi-axes (a, b, c). Agreement was assessed using Pearson correlation and Bland-Altman analysis. Geometric differences were quantified using RMS radial differences and Dice similarity on both original meshes and ellipsoidal approximations. EAM correlated with CT for volume (r = 0.58), area (r = 0.56), and sphericity (r = 0.49) (all p < 0.001). Bland-Altman analysis demonstrated systematic overestimation of volume (11.1 cm3, 13.2 %) and surface area (8.9 cm2, 9.6 %), with slight underestimation of sphericity (-0.01). RMS radial differences were higher for original meshes than ellipsoidal approximations (0.14 vs 0.08), while Dice similarity was higher for ellipsoids than original geometries (0.89 IQR [0.85-0.91] vs 0.81 IQR [0.77-0.83]). EAM provides a rapid intraprocedural approximation of left atrial geometry but does not fully reproduce CT-derived anatomy. While global shape is partially preserved, systematic scale differences and local discrepancies persist, supporting its role as a complementary rather than substitute modality.