Examinando por Autor "Melgarejo-Meseguer, Francisco M."

Mostrando 1 - 3 de 3

Interpreting frequency evolution in ventricular fibrillation using embeddings and deep learning methods
(Elsevier, 2025-08-15) Lozano-Paredes, Dafne; Sánchez-Muñoz , Juan José; Bote-Curiel, Luis; Melgarejo-Meseguer, Francisco M.; Gil-Izquierdo, Antonio; Gimeno-Blanes, F. Javier; Rojo-Álvarez, José Luis
Recently, the necessity for advanced tools to scrutinize ventricular fibrillation (VF) has been highlighted. Despite progress in the field, applying deep learning techniques and manifold interpretations in clinical settings remains underexplored. This study aims to evaluate the effectiveness of low-dimensional embeddings for distinguishing VF. We analyzed VF from three clinical conditions: patients during cardiopulmonary bypass, dogs administered with different drugs, and implantable cardioverter defibrillator devices with varying offset characteristics. We employed several algorithms, including uniform manifold approximation and projection embeddings, temporal convolutional networks, fully connected networks, and Kolmogorov–Arnold networks. Our experiments revealed that VF dynamics can be categorized based on frequency evolution, and the result can be interpreted based on clinical knowledge. However, each dataset has unique characteristics, leading to variations in the best-performing method. These differences may arise because some VF types are more easily identifiable. Our findings prove that longer signals differentiate VF types more clearly as the frequency evolution becomes clearer over extended periods. Across the same dataset, methods showed only slight differences in performance. Notably, for one dataset, two different drugs in dogs showed similar frequency patterns. For the rest of the datasets and methods, accuracy ranged between 0.68 and 0.86, precision ranged from 0.69 to 0.84, recall ranged from 0.68 to 0.84, and F1 scores ranged from 0.68 to 0.84. We conclude that low-dimensional embeddings are an effective method for characterizing VF types, and these methods can support ongoing research that aims to clarify the mechanisms of VF.
Manifold analysis of the P-wave changes induced by pulmonary vein isolation during cryoballoon procedure
(Elsevier, 2023) Martinez-Mateu, Laura; Melgarejo-Meseguer, Francisco M.; Muñoz-Romero, Sergio; Gimeno-Blanes, Francisco Javier; García-Alberola, Arcadi; Rocher-Ventura, Sara; Saiz, Javier; Rojo-Álvarez, José Luis
Background/Aim: In atrial fibrillation (AF) ablation procedures, it is desirable to know whether a proper disconnection of the pulmonary veins (PVs) was achieved. We hypothesize that information about their isolation could be provided by analyzing changes in P-wave after ablation. Thus, we present a method to detect PV disconnection using P-wave signal analysis. Methods: Conventional P-wave feature extraction was compared to an automatic feature extraction procedure based on creating low-dimensional latent spaces for cardiac signals with the Uniform Manifold Approximation and Projection (UMAP) method. A database of patients (19 controls and 16 AF individuals who underwent a PV ablation procedure) was collected. Standard 12-lead ECG was recorded, and P-waves were segmented and averaged to extract conventional features (duration, amplitude, and area) and their manifold representations provided by UMAP on a 3-dimensional latent space. A virtual patient was used to validate these results further and study the spatial distribution of the extracted characteristics over the whole torso surface. Results: Both methods showed differences between P-wave before and after ablation. Conventional methods were more prone to noise, P-wave delineation errors, and inter-patient variability. P-wave differences were observed in the standard leads recordings. However, higher differences appeared in the torso region over the precordial leads. Recordings near the left scapula also yielded noticeable differences. Conclusions: P-wave analysis based on UMAP parameters detects PV disconnection after ablation in AF patients and is more robust than heuristic parameterization. Moreover, additional leads different from the standard 12-lead ECG should be used to detect PV isolation and possible future reconnections better.
Online automatic detection of phrenic nerve activation during cryoablation procedure for atrial fibrillation treatment
(Elsevier, 2025-03) Gil-Izquierdo, Antonio; Mateos-Gaitán, Roberto; Melgarejo-Meseguer, Francisco M.; Gimeno-Blanes, F. Javier; Lozano-Paredes, Dafne; Sánchez-Muñoz, Juan José; García-Alberola, Arcadi; Rojo-Álvarez, José Luis
Abstract Background and Aim: Cryoballoon ablation is an effective technique for treating Atrial Fibrillation (AF). Its application in the pulmonary vein antrum poses a potential risk of phrenic nerve damage due to its anatomic proximity. Manual protocols are implemented during the ablation procedure to mitigate this risk, although these may be susceptible to subjectivity and variations. In this work, we propose an online system capable of automatically detecting the phrenic nerve integrity during the cryoablation procedure for AF in the pulmonary veins. The system performs digital processing of the ECG signals recorded during the ablation process, detects and segments the ECG signals, and uses a machine learning classifier to infer the risk of damage. Methods: The used dataset consisted of monitoring system signals obtained from the cryoablation procedures of ten AF patients from Virgen de la Arrixaca University Clinical Hospital in Murcia, Spain. The first stage involves signal processing of the ECG leads, using noise filtering and delineation to unmask any residual cellular potential during phrenic nerve stimulation. A comparative analysis was conducted where the electrocatheter was placed near the phrenic nerve to stimulate it and when the electrocatheter was intentionally displaced, resulting in the phrenic nerve not being stimulated despite an electrical pulse being applied. The detection stage used a linear support vector classifier for both scenarios. Results: It was possible to automatically classify the level of muscle activity from the phrenic nerve with high accuracy in this known-solution dataset. An online system was created capable of performing and synchronizing all the described stages to manage the signal extracted from the monitoring system. Conclusion: The system presented here can be a valuable tool for clinical practice, enabling the identification of specific pacing pulses when phrenic nerve involvement occurs, eventually and probably minimizing the use of manual protocols subject to interpretation biases.