Skip to main content

ESTUDIO MULTICENTRICO PARA LA EVALUACION DEL SUSTRATO ARRITMOGENICO EN PACIENTES CON FIBRILACION AURICULAR. APLICACION A LA ABLACION POR CATETER

DPI2017-83952-C3-1-R

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 65
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Short-Time Estimation of Fractionation in Atrial Fibrillation with Coarse-Grained Correlation Dimension for Mapping the Atrial Substrate

  • Vraka, Aikaterini
  • Hornero, Fernando
  • Bertomeu-Gonzalez, Vicente
  • Osca, Joaquin
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial ¿brillation (AF) is currently the most common cardiac arrhythmia, with catheter ablation (CA) of the pulmonary veins (PV) being its ¿rst line therapy. Ablation of complex fractionated atrial electrograms (CFAEs) outside the PVs has demonstrated improved long-term results, but their identi¿cation requires a reliable electrogram (EGM) fractionation estimator. This study proposes a technique aimed to assist CA procedures under real-time settings. The method has been tested on three groups of recordings: Group 1 consisted of 24 highly representative EGMs, eight of each belonging to a different AF Type. Group 2 contained the entire dataset of 119 EGMs, whereas Group 3 contained 20 pseudo-real EGMs of the special Type IV AF. Coarse-grained correlation dimension (CGCD) was computed at epochs of 1 s duration, obtaining a classi¿cation accuracy of 100% in Group 1 and 84.0¿85.7% in Group 2, using 10-fold cross-validation. The receiver operating characteristics (ROC) analysis for highly fractionated EGMs, showed 100% speci¿city and sensitivity in Group 1 and 87.5% speci¿city and 93.6% sensitivity in Group 2. In addition, 100% of the pseudo-real EGMs were correctly identi¿ed as Type IV AF. This method can consistently express the fractionation level of AF EGMs and provides better performance than previous works. Its ability to compute fractionation in short-time can agilely detect sudden changes of AF Types and could be used for mapping the atrial substrate, thus assisting CA procedures under real-time settings for atrial substrate modi¿cation., This research has been supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from JCCM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Atrial Fibrillation Surgical Ablation Long-term Outcome Prediction Just with One Lead of the Preoperative Surface Electrocardiogram

  • García, Manuel
  • Escribano, Pilar
  • Ródenas, Juan
  • Martínez-Iniesta, Miguel
  • Hornero, Fernando
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] To revert atrial fibrillation (AF) in patients requiring concomitant open-heart surgery, surgical ablation (SA) is one of the most effective procedures. However, this intervention is as- sociated with major side effects. Considering this limitation together with the benefits of anticipating antiarrhythmic treatment decisions, preoperative prediction of long-term outcome of SA is an interesting challenge. In the present work a novel algorithm to anticipate SA outcome after a follow-up of 12 months is introduced by just analyzing one lead from a preoperative electrocardiogram (ECG). Precisely, fibrillatory waves reflected on lead V1 are extracted using a QRST cancellation method. The obtained signal is divided into 1 s-length segments, which are decomposed into 8 time scales by making use a Wavelet transform. Finally, relative wavelet energy for each segment and scale is computed and the standard deviation of the time series for the 7th scale is obtained as a measure of organization of the fibrillatory waves. This index obtained statistically significant differences between the patients who maintained sinus rhythm and relapsed to AF during the follow-up. Moreover, it also yielded a discriminant ability about 75%, thus improving between 13 and 29% the one showed by other well-established parameters., This research has been supported by grants DPI2017-83952- C3 from MINECO/AEI/FEDER EU, SBPLY/17/ 180501/000411 from Junta de Comunidades de Castilla-la Mancha, and AICO/2019/036 from Generalitat Valenciana. Moreover, Pilar Escribano holds a graduate research scholarship from University of Castilla-La Mancha.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Study on the Stability of CFAEs to Characterize the Atrial Substrate in Atrial Fibrillation

  • Finotti, Emanuela
  • Ciaccio, Edward J.
  • Garan, Hasan
  • Hornero, Fernando
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] A variety of indexes has been applied to complex fractionated atrial electrograms (CFAEs) of atrial fibrillation (AF) aimed at characterizing the atrial substrate. However, often the reported results miss the assessment of intra-recording and intra-patient stability of the analyzed data, as well as CFAEs signal quality. This work introduces a study in which Determinism (DET) of Recurrence Quantification Analysis (RQA) and Sample Entropy (SE) have been applied to assess intra-recording and intrapatient stability of 1, 2 and 4 s-length segments CFAEs recorded from patients with paroxysmal and persistent AF using the coefficient of variation (CV). Furthermore, the analyses verified changes introduced by discarding artifacted and noisy CFAE segments. The intra-recording analysis pointed out that discarding segments provoked a significant variation of CV(%) in any segment length both for DET and SE, with deeper decreases for longer segments. Intra-patient stability provided large variations in CV(%) for DET and even bigger for SE at any segment length. In this case discarding segments was useless and CV provided limited variations. Kruskal-Wallis test revealed significant differences in DET and SE values among channels, independently from the discarding process., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Assisting Electrophysiological Substrate Quantification in Atrial Fibrillation Ablation

  • Vraka, Aikaterini
  • Hornero, Fernando
  • Osca, Joaquín
  • Faes, Luca
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Catheter ablation (CA) is the most popular treatment of atrial fibrillation (AF) with good results in paroxysmal AF, while its efficiency is significantly reduced in persistent AF. With the equipment used for CA strongly depending on electro-gram (EGM) fractionation quantification, the use of a reliable fractionation estimator is crucial to reduce the high recurrence rates in persistent AF. This work introduces a non-linear EGM fractionation quantification technique, which is based on coarse-grained correlation dimension (CGCD) computed over epochs of 1 second. Recordings were firstly normalized, denoised and lowpass filtered. The final CGCD value was calculated by the median CGCD value of all the epochs that a recording consisted of. Results were evaluated on three groups. Groups 1 and 2 contained 24 high-quality and 119 mid-range EGMs, respectively, manually pre-classified by AF types following Wells' criteria, then classified according to their CGCD values. 20 pseudo-real Type IV EGMs formed group 3 that was also automatically classified by AF type. In Groups 1 and 2, classification accuracy was 100% and 84-85.7%, respectively, using 10-fold cross-validation. The receiver-operating characteristics (ROC) analysis for highly fractionated EGMs, showed 100% specificity and sensitivity in Group 1 and 87.5% specificity and 93.6% sensitivity in Group 2. CGCD was always consistent with the fractionation degree of EGMs. 100% of the EGMs in Group 3 were correctly identified as Type IV AF. High accuracy results indicate that the method can estimate precisely the AF Type and detect the existence of AF Type IV cases. Both things are crucial in assisting improved substrate mapping during CA procedures of persistent AF., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Are Coronary Sinus Features Reflecting the Effect of Catheter Ablation of Atrial Fibrillation as P-waves Do?

  • Vraka, Aikaterini
  • Bertomeu-González, Vicente
  • Hornenro, Fernando
  • Langley, Philip
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial substrate alteration due to catheter ablation (CA) of atrial fibrillation (AF) is primarily assessed from P-waves. Nonetheless, how CA affects critical structures is ignored. The aim of the current study is to investigate if CA effect on CS, the principal CA reference, is related to that observed from P-waves analysis. Five-minute lead II and bipolar CS recordings of 29 paroxysmal AF patients were obtained before, during and after CA. Duration, amplitude, area and heart-rate (HR) variability (HRV) features were calculated for P-waves and local activation waves (LAWs). Normalization mitigated the effect of HR fluctuations. Linear correlations between each P-wave and LAW were tested with linear regression (LR) and Pearson correlation (PC) and nonlinear correlations with cross-quadratic sample entropy (CQSE). Correlation between the CA effect on P-waves and LAWs was investigated with PC. Negligent statistical correlations were found by PC and LR for amplitude and area (¿3.30%< corr < +18.36%, p < 0.0142). After normalization, correlation in duration increased from non-significant to significant and from low to moderate (up to 47.25%, p < 0.0001). CQSE values were from 0.6 to 1.2. The effect of CA on P-waves and LAWs duration showed a moderate/high concordance after normalization (from 50% to 89%, p < 0.0210) and a highly tuned HRV (> 90%, p < 0.0297). Apart from HRV, no significant correlations between CS LAWs and P-waves have been found. HR fluctuations mask any possible tuning and normalization should be applied prior to the analysis., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Is Short-Term Heart Rate Variability Good Enough to Predict Vascular Events in Hypertensive Patients?

  • Tornero, Roberto
  • Fácila, Lorenzo
  • Bertomeu-González, Vicente
  • Zangróniz, Roberto
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Vascular events are the main cause of premature death and disability in the developed countries, where there is great interest in the development of computational tools for their early detection. A very relevant variable for their study is the heart rate, that can be analyzed through heart rate variability (HRV). Furthermore, high blood pressure is an important risk factor for most cardiovascular diseases. In fact, small reductions in blood pressure are known to markedly reduce cardiovascular morbidity and mortality. This study evaluates the predictive value of short-term HRV (STHRV) by developing models based on data mining algorithms to stratify the risk of vascular events from hypertensive patients. For this specific framework, the performance of various machine learning models (Random Forest, Support Vector Machines, Gaussian Naive Bayes, K-N Nearest Neighbours and Logistic regression), trained with different time lengths of 5, 30 and 60 minutes of HRV features during sleep stage was compared. The analyzed HRV parameters were associated to time, frequency and nonlinear features. A total of 139 Holter recordings from hypertensive patients of whom 17 developed a vascular event were analyzed. Results indicated that classification models developed using STHRV, with only 5 minutes length, provided similar or even better results than those developed with longer time series. Furthermore, the STHRV models provided a higher sensitivity and a slightly higher F1 score. The best one, based on Support Vector Machines, yielded 88.2% sensitivity and 75% F1 score. Thus, this research suggests the feasibility of STHRV analysis for risk stratification of hypertensive patients to anticipate serious vascular events., Research supported by grants DPI2017¿83952¿C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Obstructive Sleep Apnea Detection Methods Based on Heart Rate Variability Analysis: Opportunities for a Future Cinc Challenge

  • Padovano, Daniele
  • Martinez-Rodrigo, Arturo
  • Pastor, Jose M.
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] The effects of sleep-related disorders, such as obstructive sleep apnea (OSA), can be devastating either in children or adults. Misdiagnosis may lead to severe cardiovascular diseases. Besides, OSA consequences are often related to bad job performance, and road accidents. Nowadays, polysomnography (PSG) is still considered the gold standard for OSA diagnosis, but the required facilities are extremely high, thus reducing availability worldwide. For this reason, simpler and cost-effective diagnosing methods have been proposed in the late years. In this regard, the heart rate variability (HRV) has been demonstrated to strongly reflect apnea episodes during sleep. Hence, this work reviews the latest advances in the evaluation of OSA from the HRV perspective to consider its potentialities for a future revisited CinC Challenge., This research has been supported by grants DPI201783952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-la Mancha and AICO/2019/036 from Generalitat Valenciana. Moreover, Daniele Padovano has held graduate research scholarships from Escuela Polit ' ecnica de Cuenca and Instituto de Tecnolog ' ias Audiovisuales, University of CastillaLa Mancha
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Análisis de la variabilidad temporal de la onda P para predecir el resultado de la ablación por catéter en fibrilación auricular paroxística

  • Ruiz Moreno, A.
  • Arias Palomares, M.A.
  • Puchol Calderón, A.
  • Pachón Iglesias, M.I.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[EN] El aislamiento de las venas pulmonares es el principal tratamiento de la fibrilacion auricular (FA) paroxistica. Sin embargo, presenta una alta tasa de recurrencia y el desarrollo de predictores no invasivos de esta cuestion, es esencial para permitir un tratamiento mas personalizado de cada paciente. Para tal proposito, se han analizado varias caracteristicas de la onda P a partir de registros de electrocardiografia (ECG), pero, aun no se ha estudiado su variabilidad a lo largo del tiempo. Por tanto, este trabajo explora la capacidad de la variabilidad temporal de la duracion y la amplitud de la onda P, para anticipar el fallo de la crioablacion. Paea este estudio antes de la ablacion, se registro un ECG de 5 minutos en 45 pacientes con FA paroxistica. Las ondas P en la derivacion II se delinearon con un algoritmo automatico y se calcularon la duracion y amplitud de todas ellas. A continuacion, se obtuvieron la media, la desviacion estandar y el coeficiente de variacion (CV) para ambos parametros y se correlacionaron con el resultado de la ablacion despues del seguimiento de 9 meses. El CV para ambas caracteristicas de las ondas P presento la capacidad predictiva mas alta de la recurrencia de la FA. Ademas, obtuvo mejoras de alrededor del 10 % en la clasificacion con respecto a la media, alcanzando valores del 70 %. Estos resultados sugieren que la variabilidad temporal de la onda puede proporcionar nueva informacion sobre la heterogeneidad de la conduccion auricular, lo cual podria ser util para mejorar la estrategia de seleccion de candidatos para ser sometidos a crioablacion., Esta investigacion ha sido apoyada por los fondos DPI2017-83952-C3 de MINECO/AEI /FEDER EU,SBPLY/17/180501/000411 de la Junta de Comunidades de Castilla-la Mancha y AICO/2019/036 de la Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Fuzzy and Sample Entropies as Predictors of Patient Survival Using Short Ventricular Fibrillation Recordings during out of Hospital Cardiac Arrest

  • Chicote, Beatriz
  • Irusta, Unai
  • Aramendi, Elisabete
  • Alcaraz, R.
  • Isasi, Iraia
  • Alonso, Daniel
  • Baqueriza, María del Mar
  • Ibarguren, Karlos
  • Rieta, J J|||0000-0002-3364-6380
[EN] Optimal defibrillation timing guided by ventricular fibrillation (VF) waveform analysis would contribute to improved survival of out-of-hospital cardiac arrest (OHCA) patients by minimizing myocardial damage caused by futile defibrillation shocks and minimizing interruptions to cardiopulmonary resuscitation. Recently, fuzzy entropy (FuzzyEn) tailored to jointly measure VF amplitude and regularity has been shown to be an efficient defibrillation success predictor. In this study, 734 shocks from 296 OHCA patients (50 survivors) were analyzed, and the embedding dimension (m) and matching tolerance (r) for FuzzyEn and sample entropy (SampEn) were adjusted to predict defibrillation success and patient survival. Entropies were significantly larger in successful shocks and in survivors, and when compared to the available methods, FuzzyEn presented the best prediction results, marginally outperforming SampEn. The sensitivity and specificity of FuzzyEn were 83.3% and 76.7% when predicting defibrillation success, and 83.7% and 73.5% for patient survival. Sensitivities and specificities were two points above those of the best available methods, and the prediction accuracy was kept even for VF intervals as short as 2s. These results suggest that FuzzyEn and SampEn may be promising tools for optimizing the defibrillation time and predicting patient survival in OHCA patients presenting VF., This work received financial support from Spanish Ministerio de Economia y Competitividad and jointly with the Fondo Europeo de Desarrollo Regional (FEDER), projects TEC2015-64678-R and DPI2017-83952-C3; from UPV/EHU through the grant PIF15/190 and through project GIU17/031; from the Basque Government through grant PRE-2016-1-0012; and from Junta de Comunidades de Castilla-La Mancha through SBPLY/17/180501/000411.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Distinción Entre Electrogramas de Fibrilación Auricular Paroxística Frente a Persistente para Evaluación del Sustrato Auricular en Procedimientos de Ablación por Catéter

  • Finotti, E.
  • Bertomeu González, V.
  • Hornero Sos, F.
  • Quesada Dorador, A.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] Para contribuir a un abordaje optimizado de la ablacion por cateter (AC) de fibrilacion auricular (FA), durante los ultimos anos se han introducido complicados indices destinados a discriminar FA paroxistica de persistente (FApar vs. FAper) aplicados sobre electrogramas auriculares fraccionados complejos(CFAE). Sin embargo, los electrofisiologos exigen el uso de metodos de clasificacion simples y de comprension directa. Por ello, el presente trabajo explota la longitud de ciclo de FA (AFCL), la frecuencia dominante (DF), la entropia muestral (SE) y el determinismo (DET) del analisis de cuantificacion recurrente, aplicado a registros de FA con CFAEs, para crear modelos sencillos de discriminacion entre FApar y FAper. El AFCL y la DF se calcularon sobre los registros enteros, mientras que SE y DET secalcularon utilizando segmentos de 1, 2 y 4 s. La informacion redundante se elimino umbralizando sucesivamente matrices de correlacion y el algoritmo de Random Forests ordeno las variables por relevancia. A continuacion, un arbol de clasificacion combino de manera optima los indices con alto nivel clasificatorio y se probaron con validacion cruzada dejando uno fuera. Despues de analizar todas las combinaciones posibles, el mejor resultado obtuvo una Precision (Acc) del 88,2 % para discriminar FApar de FAper, mientras que DET proporciono la mejor Acc individual de 82,4 %. Como conclusion, una seleccion cuidada y reducida de caracteristicas puede facilitar un modelo de clasificacion sencillo capaz de discriminar con precision entre CFAEs de FApar y FAper para mejorar el abordaje terapeutico de la FA., El presente trabajo ha sido cofinanciado por los proyectos de investigacion competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM y AICO/2019/036 de la GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Detection of Dominant Reentries in Multichannel Electrograms of Atrial Fibrillation

  • Vraka, Aikaterini
  • Osorio, Diego
  • Bertomeu-González, Vicente
  • Ravelli, Flavia
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Algorithms developed so far for the detection of local activation waves (LAWs) in electrograms (EGMs) of atrial fibrillation (AF) analyze each channel of the catheter separately, while dominant reentries of AF are captured by most of the catheter channels simultaneously. This encompasses the risk of losing or oversensing activations in the case of complex fractionated atrial electrograms (CFAEs). The proposed method analyzes multichannel recordings of AF from the least to the most fractionated. Activations are manually annotated and then EGMs are denoised, band-pass filtered by an alternative Bot-teron approach and thresholded. LAW detection is performed sequentially on all the channels by ascending fractionation order. Activations in the first EGM are found by an amplitude-based search, followed by a cycle length (CL) based search. Detection algorithm in the remaining signals is based on the previously detected LAWs, applying a varying search window according to the repetition rate of each activation. A CL-based search is also applied and activation time is computed from the barycenter of each LAW. The final step contains a secondary control that deletes all the low amplitude activations showing low repetition rate, so that any bias regarding the LAW detection of the first EGM is avoided. The method was compared with the equivalent sequential single-channel analysis, with the former showing better accuracy (90.82%) and positive predictive value (96.52%) than the single-channel approach (89.65% and 92.70%, respectively). Multichannel analysis performed a more selective analysis, ignoring some obvious but not repeated LAWs. Consequently, it can localize AF triggers and propagation phenomena more robustly than single channel method., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

The Relevance of Heart Rate Fluctuation When Evaluating Atrial Substrate Electrical Features in Catheter Ablation of Paroxysmal Atrial Fibrillation

  • Vraka, Aikaterini
  • Moreno-Arribas, José
  • Gracia-Baena, Juan M.
  • Hornero, Fernando
  • Alcaraz, Raúl
  • Rieta, J J
[EN] Coronary sinus (CS) catheterization is critical during catheter ablation (CA) of atrial fibrillation (AF). However, the association of CS electrical activity with atrial substrate modification has been barely investigated and mostly limited to analyses during AF. In sinus rhythm (SR), atrial substrate modification is principally assessed at a global level through P-wave analysis. Cross-correlating CS electrograms (EGMs) and P-waves' features could potentiate the understanding of AF mechanisms. Five-minute surface lead II and bipolar CS recordings before, during, and after CA were acquired from 40 paroxysmal AF patients. Features related to duration, amplitude, and heart-rate variability of atrial activations were evaluated. Heart-rate adjustment (HRA) was applied. Correlations between each P-wave and CS local activation wave (LAW) feature were computed with cross-quadratic sample entropy (CQSE), Pearson correlation (PC), and linear regression (LR) with 10-fold cross-validation. The effect of CA between different ablation steps was compared with PC. Linear correlations: poor to mediocre before HRA for analysis at each P-wave/LAW (PC: max. +18.36%, p = 0.0017, LR: max. +5.33%, p = 0.0002) and comparison between two ablation steps (max. +54.07%, p = 0.0205). HRA significantly enhanced these relationships, especially in duration (P-wave/LAW: +43.82% to +69.91%, p < 0.0001 for PC and +18.97% to +47.25%, p < 0.0001 for LR, CA effect: +53.90% to +85.72%, p < 0.0210). CQSE reported negligent correlations (0.6-1.2). Direct analysis of CS features is unreliable to evaluate atrial substrate modification due to CA. HRA substantially solves this problem, potentiating correlation with P-wave features. Hence, its application is highly recommended., This research received partial financial support from public grants DPI2017-83952-C3, PID2021-00X128525-IV0, PID2021-123804OB-I00. and TED2021-129996B-I00 of the Spanish Government 10.13039/501100011033 jointly with the European Regional Development Fund (EU), SB-PLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha. and AICO/2021/286 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

A Deep Learning Solution for Automatized Interpretation of 12-Lead ECGs

  • Huerta, Alvaro
  • Martinez-Rodrigo, Arturo
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] A broad variety of algorithms for detection and classification of rhythm and morphology abnormalities in ECG recordings have been proposed in the last years. Although some of them have reported very promising results, they have been mostly validated on short and non-public datasets, thus making their comparison extremely difficult. PhysioNet/CinC Challenge 2020 provides an interesting opportunity to compare these and other algorithms on a wide set of ECG recordings. The present model was created by ¿ELBIT¿ team. The algorithm is based on deep learning, and the segmentation of all beats in the 12-lead ECG recording, generating a new signal for each one by concatenating sequentially the information found in each lead. The resulting signal is then transformed into a 2- D image through a continuous Wavelet transform and inputted to a convolutional neural network. According to the competition guidelines, classification results were evaluated in terms of a class-weighted F-score (Fß) and a generalization of the Jaccard measure (Gß). In average for all training signals, these metrics were 0.933 and 0.811, respectively. Regarding validation on the testing set from the first phase of the challenge, mean values for both performance indices were 0.654 and 0.372, respectively, This research has been supported by the grants DPI2017¿83952¿C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha, AICO/2019/036 from Generalitat Valenciana and FEDER 2018/11744
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Time Variability of P-wave Features from the Preoperative Electrocardiogram Predicts Recurrence After Catheter Cryoablation of Atrial Fibrillation

  • Ruiz, Antonio
  • Arias, Miguel A.
  • Puchol, Alberto
  • Pachón, Marta I.
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Pulmonary vein isolation is nowadays the cornerstone for the treatment of paroxysmal atrial fibrillation (AF). However, its success rate is not as high as clinically desirable, and repeated procedures are often required. In this context, the development of noninvasive, pre-ablation predictors of the procedure failure is essential to enable tailored approaches. For that purpose several P-wave features have been analyzed from short electrocardiogram (ECG) recordings, but their time variability has not been studied yet. Hence, this work explores the ability of time variability of two common P-wave parameters, such as duration and amplitude, to anticipate cryoablation failure. Before ablation, a standard 12-lead ECG was recorded continuously for 5 minutes from 45 paroxysmal AF patients. All P-waves in lead II were delineated with an automatic algorithm. Duration and amplitude of all waves were computed, and then mean, standard deviation (std), and coefficient of variation (CV) were obtained for both parameters and correlated with ablation outcome after a follow-up of 9 months. The CV for both P-waves features reported the best separation between the patients who maintained sinus rhythm and those who relapsed to AF. Moreover, improvements about 10% in diagnostic ability were obtained by the CV with regards to the mean, reaching values about 70%. These results suggest that time variability of the P-wave can provide new insights about atrial conduction heterogeneity, which could be helpful in improving the selection strategy of optimal candidates for cryoablation., This research has been supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-la Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Catheter Ablation Outcome Prediction With Advanced Time-Frequency Features of the Fibrillatory Waves From Patients in Persistent Atrial Fibrillation

  • Escribano, Pilar
  • Ródenas, Juan
  • Arias, Miguel A.
  • Langley, Philip
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Although catheter ablation (CA) is still the first-line treatment for persistent atrial fibrillation (AF) patients, its limited long-term success rate has motivated clinical interest in preoperative prediction on the procedure¿s outcome to provide optimized patient selection, limit repeated procedures, hospitalization rates, and treatment costs. To this respect, dominant frequency (DF) and amplitude of fibrillatory waves (f-waves) reflected on the ECG have provided promising results. Hence this work explores the ability of a novel set of frequency and amplitud f-waves features, such as spectral entropy (SE), spectral flatness measure (SFM), and amplitud spectrum area (AMSA), along with DF and normalized f-wave amplitude (NFWA), to improve CA outcome prediction. Despite all single indices reported statistically significant differences between patients who relapsed to AF and those who maintained sinus rhythm after a follow-up of 9 months for 204 6 s-length ECG intervals extracted from 51 persistent AF patients, they obtained a limited discriminant ability ranging between 55 and 62%, which was overcome by 15¿23% when NFWA, SE and AMSA were combined. Consequently, this combination of frequency and amplitude features of the fwaves seems to provide new insights about the atrial substrate remodeling, which could be helpful in improving preoperative CA outcome prediction., This research has been supported by grants DPI201783952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-la Mancha and AICO/2019/036 from Generalitat Valenciana. Moreover, Pilar Escribano holds a graduate research scholarship from University of Castilla-La Mancha
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

An Experimental Review on Obstructive Sleep Apnea Detection Based on Heart Rate Variability and Machine Learning Techniques

  • Padovano, Daniele
  • Martinez-Rodrigo, Arturo
  • Pastor, Jose M.
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Obstructive sleep apnea (OSA) is a respiratory syndrome of high incidence in the general population and correlated with some cardiovascular diseases. Several techniques have been proposed in the last decades to find a surrogate method to polysomnography (PSG), the gold standard for the diagnosis of OSA. The present study comprises an experimental review on the state-of-the-art methods for OSA detection through the public Apnea-ECG database, which is available at PhysioNet. Precisely, traditional time-frequency domain features were extracted from the heart rate variability (HRV) signal, together with some common complexity measures. Given their ability to deal with real-world time series, two additional entropy-based measures were also tested, i.e., Rènyi and Tsallis entropies. Moreover, univariate and multivariate classifiers were applied, including diagnostic test, support vectors machine, and k-nearest neighbors. Ultimately, two sequential feature selection (SFS) algorithms were employed to reduce the computational cost of the resulting discriminant models. The major findings reported that multivariate classifiers reached similar results to those found in the literature. Moreover, univariate classification results suggested that the frequency domain features provided the best OSA detection, although a well-known entropy index also obtained a good performance., This research has been supported by grants DPI2017-83952- C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/ 000411 from Junta de Comunidades de Castilla-la Mancha and AICO/2019/036 from Generalitat Valenciana. Moreover, Daniele Padovano has held graduate research scholarships from Escuela Politecnica de Cuenca and Instituto de Tecnolog ¿ ¿¿as Audiovisuales, University of Castilla-La Mancha
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

The Dissimilar Impact in Atrial Substrate Modification of Left and Right Pulmonary Veins Isolation after Catheter Ablation of Paroxysmal Atrial Fibrillation

  • Vraka, Aikaterini
  • Bertomeu-González, Vicente
  • Fácila, Lorenzo
  • Moreno-Arribas, José
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Since the discovery of pulmonary veins (PVs) as foci of atrial fibrillation (AF), the commonest cardiac arrhythmia, investigation revolves around PVs catheter ablation (CA) results. Notwith-standing, CA process itself is rather neglected. We aim to decompose crucial CA steps: coronary sinus (CS) catheterization and the impact of left and right PVs isolation (LPVI, RPVI), separately. We recruited 40 paroxysmal AF patients undergoing first-time CA and obtained five-minute lead II and bipolar CS recordings during sinus rhythm (SR) before CA (B), after LPVI (L) and after RPVI (R). Among others, duration, amplitude and atrial-rate variability (ARV) were calculated for P-waves and CS local activation waves (LAWs). LAWs features were compared among CS channels for reliability analysis. P-waves and LAWs features were compared after each ablation step (B, L, R). CS channels: amplitude and area were different between distal/medial (p <= 0.0014) and distal/mid-proximal channels (p <= 0.0025). Medial and distal showed the most and least coherent values, respectively. Correlation was higher in proximal (>= 93%) than distal (<= 91%) areas. P-waves: duration was significantly shortened after LPVI (after L: p = 0.0012, -13.30%). LAWs: insignificant variations. ARV modification was more prominent in LAWs (L: >+73.12%, p <= 0.0480, R: <-33.94%, p <= 0.0642). Medial/mid-proximal channels are recommended during SR. CS LAWs are not significantly affected by CA but they describe more precisely CA-induced ARV modifications. LPVI provokes the highest impact in paroxysmal AF CA, significantly modifying P-wave duration., This research has received partial financial support from public grants DPI2017-83952-C3, PID2021-00X128525-IV0, PID2021-123804OB-I00 and TED2021-129996B-I00 of the Spanish Government 10.13039/501100011033 jointly with the European Regional Development Fund (EU), SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2021/286 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Novel Photoplethysmographic and Electrocardiographic Features for Enhanced Detection of Hypertensive Individuals

  • Cano, Jesús
  • Quesada, Aurelio
  • Ravelli, Flavia
  • Zangróniz, Roberto
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Hypertension is a major risk factor for many cardiovascular diseases, which are the leading cause of death worldwide. Regular monitoring is essential to provide early diagnosis since most patients with elevated blood pressure (BP) have asymptomatic hypertension. This work presents a method for BP classification using simultaneous electrocardiographic (ECG), photoplethysmographic (PPG) and BP signals. 86 recordings were used, being 35 normotensive, 26 prehypertensive and 25 hypertensive. It has been proposed 23 novel features to improve the discrimination between healthy and hypertensive individuals based on pulse arrival times (PAT) and morphological features from PPG, VPG and APG signal. Moreover, alternative classification models as Support Vector Machines (SVM), Naive Bayes or Coarse Trees were trained with the defined features to compare the classification performance. The classifier that provided the highest results comparing normotensive with prehypertensive and hypertensive subjects were Coarse Tree, providing an F1 score of 85.44% (Se of 86.27% and Sp of 77.14%). The use of new PPG and ECG features has successfully improved the discrimination between healthy and hypertensive individuals, around 7% of F1 score, so this machine learning methodology would be of high interest to detect HT introducing these techniques in wearable devices., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Improved Discrimination Between Healthy and Hypertensive Individuals Combining Photoplethysmography and Electrocardiography

  • Cano, Jesús
  • Hornero, Fernando
  • Quesada, Aurelio
  • Martínez-Rodrigo, Arturo
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Cardiovascular disease is one of the leading causes of death, with hypertension (HT) being its main risk factor. Its complications can be avoided with early treatment, but since these patients do not present any symptoms, HT is often detected at very advanced stages. This work presents a model for estimating blood pressure (BP) from electrocardiographic (ECG) and photoplethysmographic (PPG) signals, which can be easily obtained by means of wearable continuous monitoring devices. ECG, PPG and BP recordings from 86 patients were analyzed.A total of 34 standard and new features based on previous works were defined, such as pulse arrival times (PAT), and morphological characteristics of PPG signal. 37 classification models, ranging from Logistic Regression, Support Vector Machines (SVM), Nearest Neighbors, Naive Bayes or Coarse Trees were trained to compare discrimination results. The classifier that provided the highest performance when comparing normotensive patients with prehypertensive and hypertensive patients were Coarse Tree, providing an F1 score of 85.44% (Se of 86.27% and Sp of 77.14%). The use of PPG and ECG features has successfully discriminated between healthy and hypertensive individuals and, thus, could be used to detect HT by embedding these techniques in wearable devices., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Predicción del fracaso temprano de la cardioversión eléctrica en fibrilación auricular sobre las 12 derivaciones del ECG estándar

  • Cirugeda Roldan, E.M.
  • Calero Núñez, S.
  • Quesada Dorador, A.
  • Hidalgo Olivares, V.M.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] Dentro de las tecnicas existentes para el control del ritmo cardiaco en fibrilacion auricular (FA), una de las mas extendidas es la cardioversion electrica (CVE). Esta tecnica, de aplicacion sencilla y bajo coste, resulta muy efectiva en la restauracion del ritmo sinusal (RS) en pacientes con FA persistente. Aunque es capaz de restaurar el RS en la gran mayoria, un alto numero de pacientes, alrededor del 40 %, todavia revierten a FA durante las 4 primeras semanas. Asi pues, resulta de gran interes clinico la prediccion del exito de la CVE para poder tratar de la mejor forma a cada paciente. Con dicho objetivo, se han propuesto distintos indices para caracterizar las ondas fibrilatorias (f), generalmente considerando solo la derivacion V1 del ECG, dada su proximidad a la auricula derecha, y asi descartando otra informacion relevante que pudiera obtenerse desde otras derivaciones. Este trabajo extiende dicha caracterizacion de las ondas f a las 12 derivaciones del ECG estandar para evaluar la capacidad de prediccion del fracaso temprano de la CVE. Se han evaluado tres de los indices mas conocidos, es decir, la amplitud de las ondas f, la frecuencia dominante y la regularidad, y su rendimiento se ha comparado con el obtenido sobre V1. Los resultados obtenidos indican que, mediante la caracterizacion de las ondas f sobre la derivacion II, la prediccion del resultado de la CVE aumenta hasta un 12 % con respecto a V1, sugiriendo que esta derivacion es la mejor eleccion para evaluar la condicion proarritmica de un paciente tras la CVE., Este trabajo ha sido cofinanciado por los proyectos de investigacion competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM y AICO/2019/036 de la GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

The Relevance of Calibration in Machine Learning-Based Hypertension Risk Assessment Combining Photoplethysmography and Electrocardiography

  • Cano, Jesús
  • Fácila, Lorenzo
  • Gracia-Baena, Juan M.
  • Zangróniz, Roberto
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] The detection of hypertension (HT) is of great importance for the early diagnosis of cardiovascular diseases (CVDs), as subjects with high blood pressure (BP) are asymptomatic until advanced stages of the disease. The present study proposes a classification model to discriminate between normotensive (NTS) and hypertensive (HTS) subjects employing electrocardiographic (ECG) and photoplethysmographic (PPG) recordings as an alternative to traditional cuff-based methods. A total of 913 ECG, PPG and BP recordings from 69 subjects were analyzed. Then, signal preprocessing, fiducial points extraction and feature selection were performed, providing 17 discriminatory features, such as pulse arrival and transit times, that fed machine-learning-based classifiers. The main innovation proposed in this research uncovers the relevance of previous calibration to obtain accurate HT risk assessment. This aspect has been assessed using both close and distant time test measurements with respect to calibration. The k-nearest neighbors-classifier provided the best outcomes with an accuracy for new subjects before calibration of 51.48%. The inclusion of just one calibration measurement into the model improved classification accuracy by 30%, reaching gradually more than 96% with more than six calibration measurements. Accuracy decreased with distance to calibration, but remained outstanding even days after calibration. Thus, the use of PPG and ECG recordings combined with previous subject calibration can significantly improve discrimination between NTS and HTS individuals. This strategy could be implemented in wearable devices for HT risk assessment as well as to prevent CVDs., This research received financial support from grants PID2021-00X128525-IV0, PID2021123804OB-I00 and TED2021-129996B-I00 of the Spanish Government 10.13039/501100011033 jointly with the European Regional Development Fund (EU), SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2021/286 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Predicción del Éxito de la Ablación por Catéter en Fibrilación Auricular Persistente Mediante Características Tiempo-Frecuencia de las Ondas Fibrilatorias

  • Escribano Cano, P.
  • Ródenas García, J.
  • Arias Palomares, M.A.
  • Langley, P.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] A pesar de su limitada tasa de éxito a largo plazo, la ablación por catéter (AC) es el tratamiento de primera línea de la fibrilación auricular (FA) persistente. La predicción preoperatoria del resultado de este procedimiento permitiría optimizar la selección de pacientes, entre otras ventajas clínicas y económicas. Con este fin, la frecuencia dominante (FD) y la amplitud de las ondas fibrilatorias (ondas f) normalizada (AOFn) reflejadas en el registro electrocardiográfico (ECG) ya han proporcionado resultados prometedores, pero insuficientes desde un punto de vista clínico. Este trabajo explora la capacidad de un conjunto de características frecuenciales y de amplitud de las ondas f para mejorar la predicción del resultado de la AC. Asi pues, además de los dos índices anteriormente indicados, se han analizado: la entropía espectral (EE), la medida de la planicidad espectral (MPE) y la suma ponderada de la amplitud espectral (SPAE). Los resultados obtenidos para 204 intervalos de ECG, extraídos de 51 pacientes con FA persistente, muestran para todos los índices diferencias estadísticamente significativas entre los pacientes que mantuvieron ritmo sinusal (RS) y los que recayeron a FA tras un seguimiento de 9 meses, pero una capacidad discriminante limitada, entre un 55 y un 62 %. Este resultado se mejoro en un 15-23 % cuando se combinaron mediante un análisis lineal discriminante AOFn, EE y SPAE, obteniendo un valor del 77,2 %. En consecuencia, esta combinación de características de frecuencia y amplitud parece proporcionar nueva información sobre el remodelado del sustrato auricular, la cual podría ser útil para mejorar la predicción del resultado de la AC., Trabajo financiado por los proyectos DPI2017-83952-C3 MINECO/AEI/FEDER, EU, SBPLY/17/180501000411 de la Junta de Comunidades de Castilla-La Mancha y AICO/2019/036 de la Generalitat Valenciana. Ademas, Pilar Escribano Cano tiene una beca de investigacion de posgrado y un posterior contrato predoctoral 2020-PREDUCLM15540, ambos por la Universidad de Castilla-La Mancha.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Discriminación Mejorada Entre Personas Sanas e Hipertensas Combinando Fotopletismografía y Electrocardiografía

  • Cano Serrano, J.
  • Alcaraz Martinez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] Las enfermedades cardiovasculares son una de las principales causas de muerte, siendo la hipertensión arterial (HTA) su principal factor de riesgo. Sus complicaciones pueden evitarse con un tratamiento temprano, pero dado que estos pacientes no presentan ninguna sintomatología, a menudo la HTA se detecta en estadios muy avanzados. Este trabajo presenta un modelo de estimación de la presión arterial (PA) a partir de señales de electrocardiografía (ECG) y fotopletismografía (PPG), que pueden obtenerse del paciente con facilidad mediante dispositivos llevables de monitorización continua. Se han analizado señales de 86 pacientes con registros de ECG, PPG y PA, siendo 35 normotensos, 26 prehipertensos y 25 hipertensos. Los registros fueron limpiados de ruido para mejorar la obtención de sus puntos característicos. A partir de ellos se obtuvieron parámetros discriminatorios como los tiempos de llegada de pulso (PAT) y características morfológicas de la señal PPG como el ancho del pulso e intervalo entre picos sistólicos, con los que se entrenarán modelos de clasificación buscando mejorar los resultados de discriminación entre pacientes. Los resultados obtenidos fueron del 85,44 % de F1 score comparando a pacientes normotensos con prehipertensos e hipertensos, logrando una mejora del 7 % respecto a la utilización de parámetros predictivos y clasificadores propuestos en estudios previos. La utilización de las señales PPG y ECG ha demostrado ser capaz de discriminar entre personas sanas e hipertensas y, por tanto, podría ser usada para la prevención de la hipertensión implementando esta técnica en dispositivos llevables., El presente trabajo ha sido cofinanciado por los proyectos de investigación competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM y AICO/2019/036 de la GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Reference database and performance evaluation of methods for extraction of atrial fibrillatory waves in the ECG

  • Alcaraz, Raul
  • SORNMO, LEIF
  • Rieta, J J|||0000-0002-3364-6380
[EN] Objective: This study proposes a reference database, composed of a large number of simulated ECG signals in atrial fibrillation (AF), for investigating the performance of methods for extraction of atrial fibrillatory waves (f -waves). Approach: The simulated signals are produced using a recently published and validated model of 12-lead ECGs in AF. The database is composed of eight signal sets together accounting for a wide range of characteristics known to represent major challenges in f -wave extraction, including high heart rates, high morphological QRST variability, and the presence of ventricular premature beats. Each set contains 30 5 min signals with different f -wave amplitudes. The database is used for the purpose of investigating the statistical association between different indices, designed for use with either real or simulated signals. Main results: Using the database, available at the PhysioNet repository of physiological signals, the performance indices unnormalized ventricular residue (uVR), designed for real signals, and the root mean square error, designed for simulated signals, were found to exhibit the strongest association, leading to the recommendation that uVR should be used when characterizing performance in real signals. Significance: The proposed database facilitates comparison of the performance of different f -wave extraction methods and makes it possible to express performance in terms of the error between simulated and extracted f -wave signals., This work was supported by project DPI2017-83952-C3 of the Spanish Ministry of Economy, Industry and Competitiveness, project SBPLY/17/180501/000411 of the Junta de Comunidades de Castilla-La Mancha, Grant 'Jose Castillejo' (CAS17/00436) from the Spanish Ministry of Education, Culture and Sport, Grant No. BEST/2017/028 from the Education, Research, Culture and Sports Department of Generalitat Valenciana, European Regional Development Fund, and Grant No. 03382/2016 from the Swedish Research Council.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Refined Multiscale Entropy Predicts Early Failure in Electrical Cardioversion of Atrial Fibrillation

  • Cirugeda, Eva M.
  • Calero, Sofia
  • Hidalgo, Victor M.
  • Enero, Jose
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Electrical cardioversion (ECV) is a well-established strategy for atrial fibrillation (AF) management. Despite its high initial effectiveness, a high relapsing rate is also found. Hence, identification of patients at high risk of early AF recurrence is crucial for a rationale therapeutic strategy. For that purpose, a set of indices characterizing fibrillatory (f-) waves have been proposed, but they have not considered nonlinear dynamics present at different timescales within the cardiovascular system. This work thus explores whether a multiscale entropy (MSE) analysis of the f-waves can improve preoperative predictions of ECV outcome. Thus, two MSE approaches were considered, i.e., traditional MSE and a refined version (RMSE). Both algorithms were applied to the main f-waves component extracted from lead V1 and entropy values were computed for the first 20 time-scales. As a reference, dominant frequency (DF) and f-wave amplitude (FWA) were also computed. A total of 70 patients were analyzed, and all parameters but FWA showed statistically significant differences between those relapsing to AF and maintaining sinus rhythm during a follow-up of 4 weeks. RMSE reported the best results for the scale 19, improving predictive ability up to an 8% with respect to DAF and FWA. Consequently, investigation of nonlinear dynamics at large time-scales can provide useful insights able to improve predictions of ECV failure, This research was funded by the projects DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from "Junta de Castilla La Mancha" and AICO/2019/036 from "Generalitat Valenciana".
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Predicción a Largo Plazo del Resultado de la Ablación Quirúrgica en Fibrilación Auricular Mediante el Uso de una Única Derivación del Electrocardiograma Preoperatorio

  • Martínez Iniesta, M.
  • Escribano Cano, P.
  • García Teruel, M.
  • Ródenas García, J.
  • Hornero Sos, F.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] La ablación quirúrgica (AQ), realizada concomitantemente en pacientes que requieren cirugía a corazón abierto, es el procedimiento más eficaz para controlar la fibrilación auricular (FA). Considerando los importantes efectos secundarios de esta técnica, junto a los beneficios de anticipar una decisión sobre el tratamiento antiarrítmico, la predicción preoperatoria de su resultado a largo plazo supone un interesante reto clínico. Este trabajo introduce un novedoso algoritmo de predicción del resultado de la AQ, transcurrido un año de seguimiento, basado en el análisis de la derivación V1 del electrocardiograma (ECG) preoperatorio. El método extrae de éste las ondas fibrilatorias, segmenta la señal resultante en tramos de 1 s y calcula la desviación estándar de la energía wavelet relativa para la séptima escala (EWR7_DE) contenida en cada uno de ellos. Este índice consiguió una capacidad discriminatoria del 75% entre los pacientes que mantuvieron un ritmo sinusal y aquellos que recayeron a FA durante el seguimiento, superando así en casi un 20% la habilidad de otros parámetros clásicos y convirtiéndose en un prometedor predictor de recurrencia de la FA tras la AQ., Trabajo financiado por los proyectos DPI2017-83952-C3 MINECO/AEI/FEDER, UE, SBPLY/17/180501/000411 de la Junta de Comunidades de Castilla-La Mancha y AICO/2019/036 de la Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Quality Assessment of Very Long-Term ECG Recordings Using a Convolutional Neural Network

  • Huerta, A.
  • Martínez-Rodrigo, A.
  • Bertomeu González, V.
  • Quesada, A.
  • Alcaraz, R.
  • Rieta, J J|||0000-0002-3364-6380
[EN] The electrocardiogram (ECG) is a physiological signal highly sensitive to disturbances during its acquisition. To palliate this issue, many works have described preprocessing algorithms operating in 12-lead, short-term ECG recordings. However, only a few methods have been introduced to detect noisy segments in single-lead, long-term ECG signals, this being a pending challenge to be resolved. Hence, this work proposes a novel technique to automatically detect low-quality segments in single-lead, long-term ECG recordings. The method is based on the high learning capability of a convolutional neural network (CNN), which has been trained with 2D images obtained when turning ECG recordings into scalograms using a continuous Wavelet transform (CWT). To validate the method, a publicly available dataset containing single-lead, long-term ECG intervals from patients with different cardiac rhythms has been used. These signals have been annotated by experts, who identified noisy intervals and those with sufficient quality to be clinically interpreted. The results have shown that the proposed method discriminates correctly between low and high-quality ECG segments with an accuracy greater than 90%, and with sensitivity slightly larger than specificity., This work has been funded by projects DPI2007-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501000411 from Junta de Castilla la Mancha, AICO/2019/036 from Generalitat Valenciana, and grand 2018/11744 from European Regional Development Fund (FEDER, UE).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Novel Time-Frequency Features of the Fibrillatory Waves Improve Catheter Ablation Outcome Prediction of Persistent Atrial Fibrillation

  • Escribano, Pilar
  • Ródenas, Juan
  • Arias, Miguel A.
  • Langley, Philip
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Despite its limited long-term success rate, catheter ablation (CA) is still the first-line treatment for patients suffering from persistent atrial fibrillation (AF). Preoperative prediction on the procedure¿s outcome is gaining clinical interest to provide optimized patient selection, limit repeated procedures, hospitalization rates, and treatment costs. To this respect, dominant frequency (DF) and amplitude of fibrillatory waves (f-waves) reflected on the electrocardiogram (ECG) recording have provided promising results. Hence, this work explores the ability of a novel set of frequency and amplitude features of the f-waves to improve CA outcome prediction. More precisely, in addition to DF and normalized f-wave amplitude (NFWA), three indices such as spectral entropy (SE), spectral flatness measure (SFM), and amplitude spectrum area (AMSA) were also analyzed. The results obtained for 204 6 s-length ECG intervals extracted from 51 persistent AF patients showed that all indices found statistically significant differences between the patients who maintained sinus rhythm and those who relapsed to AF after a follow-up of 9 months. However, they only obtained limited a discriminant ability ranging between 55 and 62%, which was overcome by 15¿23% when NFWA, SE and AMSA were combined. Consequently, this combination of frequency and amplitude features of the f-waves seems to provide new insights about the atrial substrate remodeling, which could be helpful in improving preoperative CA outcome prediction. Nonetheless, further studies are required in the future, This research has been supported by grants DPI2007-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501000411 from Junta de Comunidades de Castilla-la Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Comparative Study of Convolutional Neural Networks for ECG Quality Assessment

  • Huerta, Alvaro
  • Martinez-Rodrigo, Arturo
  • Puchol, Alberto
  • Pachon, Marta, I
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] In the last years, convolutional neural networks (CNNs) have become popular in ECG analysis, since they do not require pre-processing stages, nor specific pre-training. However, their ability for ECG quality assessment has still not been thoroughly assessed. Hence, this work introduces a comparison about the ability of several CNN algorithms to classify between high and low-quality ECGs. Taking advantage of the concept of transfer learning, five common pre-trained CNNs were analyzed, such as AlexNet, GoogLeNet, VGG16, ResNet18 and InceptionV3. They were fed with 2-D images obtained by turning 5 second-length ECG segments into scalograms through a continuous Wavelet transform. To train and validate the algorithms, 1,168 noisy ECG intervals, along with other 1,200 ECG excerpts with sufficient quality for their further interpretation, were extracted from a public database. The obtained results showed that all CNNs provided mean values of accuracy between 89 and 91%, but notable difference in terms of computational load were noticed. Thus, AlexNet was the fastest algorithm, requiring notably less CPU usage and memory than the remaining methods. Consequently, this CNN exhibited the best trade-off between high-quality ECG identification accuracy and computational load, and it could be considered as the most convenient algorithm for ECG quality assessment., This research has been supported by the grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

A Straightforward Methodology to Distinguish Complex Fractionated Atrial Electrograms of Paroxysmal from Persistent Atrial Fibrillation

  • Finotti, Emanuela
  • Ciaccio, Edward J.
  • Garan, Hasan
  • Bertomeu-González, Vicente
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Many indices aimed at discriminating between paroxysmal and persistent atrial fibrillation (ParAF vs. PerAF) have been previously studied and assessed via statistical tests in order to suggest optimized approaches to catheter ablation (CA) of AF. However, clinicians demand the use of simple classification methods of straightforward comprehension. The present work exploits AF cycle length (AFCL), dominant frequency (DF), sample entropy (SE) and determinism (DET) of recurrent quantification analysis, applied to AF recordings of complex fractionated atrial electrograms (CFAEs), aimed at creating straightforward models to discriminate between ParAF and PerAF. AFCL and DF were calculated on the full AF recordings, whereas SE and DET were computed on segments of 1, 2 and 4s. First, correlation matrix filters removed redundant information and Random Forests made a ranking of variables by relevance. Next, coarse tree classificators were created, combining optimally high-ranked indexes which were tested with leave-one-out cross-validation. After analyzing all the possible combinations of highly ranked features, the best classification performance provided an Accuracy (Acc) of 88.2% to discriminate ParAF from PerAF, while DET provided the highest single Acc of 82.4%. As conclusion, the careful selection of limited sets of indices feeding straightforward classificators are able to discriminate accurately between CFAEs of ParAF and PerAF., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Confiabilidad de las Ondas de Activación Local para Evaluar el Sustrato Auricular de Pacientes con Fibrilación Auricular Paroxística

  • Vraka, A.
  • Hornero Sos, F.
  • Bertomeu-González, V.
  • Osca Asensi, J.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] El análisis de electrogramas (EGMs) del seno coronario (SC) durante la ablación por catérer (AC) de fibrilación auricular (FA) es clave para la evaluación del sustrato auricular. No obstante, los canales del catéter de registro suelen verse afectados por mal contacto y por el movimiento cardíaco. Este trabajo estudia los canales más fiables para preservar las dinámicas de la FA durante el ritmo sinusal (RS). Se han empleado 44 registros bipolares multicanal del SC de 60-300 segundos de 28 pacientes con FA paroxística sometidos a AC. Cada registro contenía cinco canales: distal, medio-distal, medio, medio-proximal, proximal. En cada canal se calcularon características de las ondas de activación local (OALs): duración, área y correlación entre morfologías dominantes. Se han utilizado los tests de KruskalWallis, Mann-Whitney y Mann-Whitney con corrección de Bonferroni para la comparación multicanal, por pares y uno frente a los demás, respectivamente. El canal distal presentó resultados menos fiables, con OALs de duración larga (p = 0,047), amplitud baja (pmax < 0,003) y menos área (pmax < 0,020) y con correlación entre sus OALs y las OALs del canal proximal relativamente baja (85,57 %). Las OALs entre los canales medio y medio-próximal fueron más consistentes, con correlación entre sus OALs muy altas (95,02 %), presentando además duración más corta (p = 0,084) y amplitud (pmax < 0,050) y áreas mayores (pmax < 0,070). En consecuencia, los canales medios y medio-proximales son más robustos, preservando al máximo las dinámicas de la FA, por ello se aconseja su empleo para evaluar el sustrato auricular de pacientes con FA durante el RS., Trabajo cofinanciado por los proyectos de investigación competitiva DPI2017-83952-C3 de MINECO-AEIFEDER-UE, SBPLY/17/180501/000411 de la JCCLM y AICO/2019/036 de la GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Hypertension Risk Assessment from Photoplethysmographic Recordings Using Deep Learning Classifiers

  • Cano, Jesús
  • Bertomeu-González, Vicente
  • Fácila, Lorenzo
  • Zangróniz, Roberto
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Regular monitoring of blood pressure (BP) is essential for early detection of cardiovascular diseases caused by hypertension, a potentially deadly condition without symptoms in its first stages. This study investigates whether deep learning techniques can assess risk levels of BP using only photoplethysmographic (PPG) recordings without the need of electrocardiographic (ECG) recordings, as in many previous studies. 15.240 segments from 50 different patients containing simultaneous PPG and arterial blood pressure (ABP) signals were analysed. GoogleNet and ResNet pretrained convolutional neural networks (CNN) with the scalogram of PPG signals obtained by continuous wavelet transform (CWT) used as input images were employed for the classification. The highest F1 score was achieved by discriminating normotensive (NT) patients from prehypertensive (PH) and hypertensive (HT), being 92.10% for GoogleNet and 93.91% for ResNet, respectively. In addition, intra-patient classification using different data segments for training and validation provided an F1 score of 90.28% with GoogleNet and 89.04% with ResNet. Time frequency transformation of PPG recordings to feed deep learning classifiers has been able to provide outstanding results in hypertension risk assessment without requiring either ECG recordings or feature extraction., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Application of Deep Neural Network Models for Blood Pressure Classification based on Photoplethysmograpic Recordings

  • Cano, Jesús
  • Fácila, Lorenzo
  • Langley, Philip
  • Zangróniz, Roberto
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] The measurement of blood pressure (BP) in an uninterrupted and comfortable way for the subject is essential for early diagnosis and monitoring of cardiovascular diseases (CVD). In fact, hypertension is the main risk factor for CVD because, being a hidden health problem with no symptoms until late stages of the disease are reached. This work investigates whether deep neural network models are able to discriminate between healthy and hypertensive subjects based on photoplethysmographic (PPG) recordings, without the need of electrocardiographic (ECG) recordings as well as avoiding manual morphological feature extraction, as has been popularly used in many previous studies. Recordings analyzed consisted of 635 simultaneous PPG and arterial blood pressure (ABP) signals from 50 different patients. The classification was performed with GoogLeNet, ResNet-18 and ResNet-50 pretrained convolutional neural networks (CNN) using as input images the scalogram of PPG segments obtained by continuous wavelet transformation (CWT). Additionally, Adam and SGDM training solvers were used to compare classification performance. After applying early stopping to avoid overfitting, training was performed with more than half of the epochs using Adam optimizer. ResNet-18 CNN provided the highest classification performance with sensitivity of 95.68%, specificity of 93.65%, F1-score of 95.61% an Area under the Roc area of 98.77%. Hence, the application of deep neural network classification models using time frequency transformation of PPG recordings has been able to provide outstanding results in blood pressure classification without requiring neither morphological feature extraction nor ECG features., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Thorough Assessment of a P-wave Delineation Algorithm Through the Use of Diverse Electrocardiographic Databases

  • Ruiz, Antonio
  • Arias, Miguel A.
  • Pachón, María Inmaculada
  • Langley, Philip
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Detailed analysis of the electrocardiogram (ECG) recording allows to obtain relevant information about the heart state and its behavior. Indeed, the P-wave study has proven to be helpful in diagnosing many atrial electrical conduction disorders. However, manual delineation of this wave is a very time-consuming task, and a wide variety of automatic algorithms have been proposed for that purpose. The performance of these methods has been mostly validated on the QT database, since it contains manual annotations from clinical experts and is freely available at PhysioNet. Unfortunately, in the last years several authors have shown some major limitations of this database and this work hence presents a more robust validation of a previously published P-wave delineator. Thus, two novel databases which have been very recently made available to the scienti¿c community have been analyzed. The results show that the methods ability to detect P-waves is close to 100% in stable sinus rhythm episodes, but it decreases to 94% when the heart rhythm is irregular or consecutive P-waves exhibit notable morphological variations. Regarding the error between the annotations obtained automatically and those available as a reference, no relevant differences have been observed in terms of standard deviation, thus suggesting that the algorithm achieves a consistent delineation of the P-waves. Contrarily, a notable error has been noticed in average values, thus highlighting the need of a more extensive training for the P-wave delineator than that offered by the QT database., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Limb Versus Precordial ECG Leads as Improved Predictors of Electrical Cardioversion Outcome in Persistent Atrial Fibrillation

  • Cirugeda, Eva M.
  • Calero, Sofia
  • Quesada, Aurelio
  • Hidalgo, Victor M.
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Electrical cardioversion (ECV) is an effective and low-cost rhythm control strategy for persistent atrial fibrillation (AF). Because of its limited mid- and long-term success rates, prediction of early failure could avoid patients with reduced chance to maintain sinus rhythm (SR). To this end and due to its proximity to the right atrium, several indices characterizing atrial activity have been proposed based on lead V1. However, information from other leads has been discarded to date. Hence, this work studies how effective some common indices computed over the whole set of 12 standard ECG leads are in predicting ECV outcome. Precisely, amplitude, dominant frequency, and sample entropy were computed from the fibrillatory (f-) waves extracted for each one of 12 standard leads acquired before ECV from 58 patients in persistent AF. The classification between the patients who relapsed to AF and maintained sinus rhythm after a follow-up of 4 weeks achieved by these parameters was better from limb lead II than from V1, thus reporting improvements about 6 and 12%. As a consequence, characterization of f-waves from the more accessible limb lead II has proven to be the best choice to improve AF ECV outcome prediction from the ECG., This research was funded by the projects DPI2017-83952C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from "Junta de Castilla La Mancha" and AICO/2019/036 from "Generalitat Valenciana".
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Comparison of Pre-Trained Deep Learning Algorithms for Quality Assessment of Electrocardiographic Recordings

  • Huerta, Álvaro
  • Martínez-Rodrigo, Arturo
  • Puchol, Alberto
  • Pachón, Marta I.
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Convolutional neural networks (CNNs) have recently become popular for electrocardiogram (ECG) analysis. However, their ability for ECG quality assessment has still not been thoroughly assessed. This challenging topic, aimed at identifying poor-quality ECG intervals, could facilitate more accurate decisions on cardiac disorders, especially from wearable long-term ECG monitoring systems. Hence, this work introduces a comparative study about how several CNN algorithms discern between high and low-quality ECGs. Because no many datases with large amount of annotated ECG signals are freely available, three pretrained CNNs, such as AlexNet, VGG16 and GoogLeNet, have been compared. For that purpose, 2,000 5 second-length ECG excerpts were extracted from a public database and classified into two groups. Thus, 1,000 ECG intervals were annotated as noisy and other 1,000 segments presented sufficient quality for further analysis. For robust validation of the algorithms, five learningtesting cycles with random 80/20 splits of the dataset were conducted. Whereas all CNN models achieved mean accuracies about 90%, remarkable differences were seen in terms of computational time and memory usage. Thus, AlexNet was the fastest method classifying ECG excerpts, but GoogLeNet required the lowest memory content for its performance. Consequently, both algorithms reported an interesting trade-off between poor-quality ECG identification accuracy and computational load.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Efecto de la Ablación por Catéter Sobre Ciertas Estructuras Auriculares de Pacientes con Fibrilación Auricular Paroxística: El Caso del Seno Coronario

  • Vraka, A.
  • Bertomeu-González, V.
  • Hornero Sos, F.
  • Quesada Dorador, A.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] Numerosos estudios previos han reportado alteraciones significativas de varias características de la onda P en el electrocardiograma (ECG) de superficie tras un procedimiento de ablacion por cateter (AC) de fibrilación auricular paroxística (FAP). Sin embargo, no se ha reportado resultado alguno sobre una de las estructuras auriculares mas empleada como referencia en el registro de señales invasivas durante procedimientos de AC, como es el seno coronario (SC). Para indagar en este asunto, este estudio utiliza registros bipolares del SC de 26 pacientes sometidos a AC de FAP. Los registros fueron grabados en ritmo sinusal (RS) y duraron 5 minutos. El trabajo incluye la deteccion y el analisis de las siguiente características de ondas de activacion local (OALs): duracion, amplitud, ¿ area positiva y negativa, variabilidad morfologica (VM), dispersión y el número de tramos crecientes y decrecientes (NTCD). Las características mencionadas se compararon antes y despues de la AC usando el test U de Mann-Whitney, calculando tambien sus valores medianos. Duracion, amplitud y áreas positivas y negativas marcaron un moderado decrecimiento (de ¿1,42 % a ¿14,28 %). La VM y la dispersion se incrementaron (de +1,20 % a +64,81 %). No se encontro ninguna alteracion en el NTCD. En consecuencia, los resultados obtenidos coincidieron en su mayor parte con hallazgos similares reportados sobre la onda P del ECG en trabajos previos. No obstante, las características de las OALs en registros bipolares del SC no sufrieron una alteracion significativa por causa de la AC (p > 0,05). En consecuencia, las mayores alteraciones observadas en estudios sobre la onda P del ECG deben provenir, posiblemente, de otras areas auriculares alejadas del SC o son ¿ una superposicion de alteraciones de menor nivel que tienen lugar en multiples zonas auriculares., El presente trabajo ha sido cofinanciado por los proyectos de investigacion competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM y AICO/2019/036 de la GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Practical Considerations for the Application of Nonlinear Indices Characterizing the Atrial Substrate in Atrial Fibrillation

  • Finotti, Emanuela
  • Quesada, Aurelio
  • Ciaccio, Edward J.
  • Garan, Hasan
  • Hornero, Fernando
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial fibrillation (AF) is the most common cardiac arrhythmia, and in response to increasing clinical demand, a variety of signals and indices have been utilized for its analysis, which include complex fractionated atrial electrograms (CFAEs). New methodologies have been developed to characterize the atrial substrate, along with straightforward classification models to discriminate between paroxysmal and persistent AF (ParAF vs. PerAF). Yet, most previous works have missed the mark for the assessment of CFAE signal quality, as well as for studying their stability over time and between different recording locations. As a consequence, an atrial substrate assessment may be unreliable or inaccurate. The objectives of this work are, on the one hand, to make use of a reduced set of nonlinear indices that have been applied to CFAEs recorded from ParAF and PerAF patients to assess intra-recording and intra-patient stability and, on the other hand, to generate a simple classification model to discriminate between them. The dominant frequency (DF), AF cycle length, sample entropy (SE), and determinism (DET) of the Recurrence Quantification Analysis are the analyzed indices, along with the coefficient of variation (CV) which is utilized to indicate the corresponding alterations. The analysis of the intra-recording stability revealed that discarding noisy or artifacted CFAE segments provoked a significant variation in the CV(%) in any segment length for the DET and SE, with deeper decreases for longer segments. The intra-patient stability provided large variations in the CV(%) for the DET and even larger for the SE at any segment length. To discern ParAF versus PerAF, correlation matrix filters and Random Forests were employed, respectively, to remove redundant information and to rank the variables by relevance, while coarse tree models were built, optimally combining high-ranked indices, and tested with leave-one-out cross-validation. The best classification performance combined the SE and DF, with an accuracy (Acc) of 88.3%, to discriminate ParAF versus PerAF, while the highest single Acc was provided by the DET, reaching 82.2%. This work has demonstrated that due to the high variability of CFAEs data averaging from one recording place or among different recording places, as is traditionally made, it may lead to an unfair oversimplification of the CFAE-based atrial substrate characterization. Furthermore, a careful selection of reduced sets of features input to simple classification models is helpful to accurately discern the CFAEs of ParAF versus PerAF., This research has received partial financial support from public national grants DPI2017-83952-C3, PID2021-00X128525-IV0, and PID2021-123804OB-I00 of the Spanish Government with DOI 10.13039/501100011033 jointly with the European Regional Development Fund (EU), and regional grants SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2021/286 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Análisis multidimensional de las 12 derivaciones del ECG estándar para predecir el éxito de la cardioversión eléctrica en fibrilación auricular persistente

  • Cirugeda Roldan, E.M.
  • Calero Núñez, S.
  • Plancha Burguera, E.
  • Enero Navajo, J.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] La Sociedad Europea de Cardiologia recomienda la cardioversion electrica (CVE) para el control del ritmo cardiaco en situaciones de fibrilacion auricular (FA) persistente. Aunque es capaz de restaurar inicialmente el ritmo sinusal (RS) en la mayoria de los pacientes, su tasa de exito a medio plazo es limitada, presentando la arritmia una alta probabilidad de recurrencia. En este contexto, es de gran interes poder prever el resultado de la CVE, ya que de esta forma se podria tratar individualizadamente a los pacientes. Con este objetivo, durante los ultimos a nos se han propuesto distintos indices que caracterizan la actividad auricular (AA) sobre el electrocardiograma (ECG), tales como la amplitud de las ondas fibrilatorias (f), su frecuencia dominante, o su regularidad. Aunque estos indices han presentado resultados prometedores, solo se han empleado para caracterizar las ondas f en una unica derivacion, generalmente V1, descartando asi la informacion espacial que, registrada en otras derivaciones, puede resultar de gran interes. Asi pues, este trabajo evalua si una extension multidimensional de dichos indices es capaz de incrementar la capacidad de prediccion del resultado de la CVE. En los resultados se observa que las extensiones multidimensionales de los indices propuestos incrementan la prediccion de la CVE hasta casi un 6 %, lo que sugiere que las correlaciones espaciales en la AA de las distintas derivaciones del ECG obtienen informacion predictiva relevante sobre la recurrencia de la FA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Refined Electrical Cardioversion Outcome Prediction with Bipolar Surface Standard Leads for Patients in Persistent Atrial Fibrillation

  • Cirugeda, Eva M.
  • Calero, Sofía
  • Quesada, Aurelio
  • Hidalgo, Víctor M.
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] For persistent atrial fibrillation (AF), a low-cost, simple and effective rhythm control strategy is electrical cardioversion (ECV). This procedure presents high mid- and long-term AF recurrence rates, so anticipation of its outcome could avoid patients with high likelihood of relapsing to AF. To this end and considering the proximity of lead V1 to the right atrium, different parameters assessing fibrillatory (f-) waves reflected on this lead have been recently proposed. However, information from other leads have been mostly discarded. This study hence evaluates the effectiveness of several common parameters computed over the whole set of 12 standard ECG leads to predict ECV outcome with respect to just V1. The results for the amplitude of the f-waves, their dominant frequency and their regularity have shown better predictive abilities from limb lead II than from V1, thus providing improvements between 5 and 12% in the classification rates between patients who relapsed to AF and maintained SR during a follow-up of 4 weeks. Consequently, accessible limb lead II seems to be the best choice to anticipate ECV outcome from the ECG., This research was funded by projects: DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from "Junta de Castilla la Mancha" and AICO/2019/036 from "Generalitat Valenciana".
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Deep Learning Detection of Corrupted Segments in Recordings from Wearable Devices to Improve Atrial Fibrillation Screening

  • Huerta, Álvaro
  • Martínez-Rodrigo, Arturo
  • Arias, Miguel A.
  • Langley, Phillip
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia in clinical practice. It is associated with an increased risk of cardiovascular events, but its early detection is an unresolved challenge. For that purpose, long-term wearable electrocardiogram (ECG) recording systems are being widely used in the last years, because the arrhythmia often starts with asymptomatic and very short episodes. However, these equipments work in highly dynamics and ever-changing environments, thus providing ECG signals strongly corrupted with different kinds of noises. In this context, ECG quality assessment results essential for a precise and robust AF detection. Hence, this work introduces a deep learning-based algorithm to discern between high- and low-quality segments in single-lead ECG recordings obtained from patients with intermittent AF. The method is based on the high learning capability of a convolutional neural network, which has been trained with 2-D images obtained when turning ECG signals into wavelet scalograms. The obtained results have reported a great ability to discern between high- and low-quality ECG excerpts about 95%, only misclassifying around 6% of clean AF intervals as noisy segments. These outcomes have improved by more than 20% performances of most previous ECG quality assessment algorithms also dealing with AF signals., This research has been supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha, AICO/2019/036 from Generalitat Valenciana and FEDER 2018/11744
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Reliable Paroxysmal Atrial Fibrillation Substrate Assessment During Sinus Rhythm Through Optimal Estimation of Local Activation Waves Dynamics

  • Vraka, Aikaterini
  • Hornero, Fernando
  • Quesada, Aurelio
  • Faes, Luca
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] The analysis of coronary sinus (CS) electrograms (EGMs) during catheter ablation (CA) of atrial fibrillation (AF) is highly important for AF substrate evaluation. However, channels of the CS catheter may be affected by vigorous cardiac movement and bad contact. This work investigates the most reliable channels in preserving the AF dynamics during sinus rhythm (SR). Local activation waves (LAWs) were detected in 44 bipolar CS recordings of 60-300 seconds duration in 28 paroxysmal AF patients undergoing CA. Recordings consisted of five channels: distal, mid-distal, medial, mid-proximal and proximal. LAW duration, amplitude, area and correlation between dominant morphologies of each channel were calculated. Multichannel comparison and analysis in pairs of channels were performed using KruskalWallis and Mann-Whitney U-test, respectively. The latter, with Bonferroni correction, was also used for comparison between one and the remaining channels. Median values were calculated. Distal channel presented the longest duration (p = 0.047) and the lowest amplitude LAWs (pmax <; 0.002), with the smallest area (pmax <; 0.020). LAWs in medial were the shortest (p = 0.084) and with the highest amplitude (pmax <; 0.003), followed by LAWs in mid-proximal channel (pmax <; 0.050). The latter, showed the highest area (pmax <; 0.070). LAWs in mid-proximal channel showed the highest correlation with proximal (96.02%) and medial (95.02%) channels, while distal channel contained the least correlated LAWs with medial (85.82%) and proximal (85.57%) channels. Recordings of medial and mid-proximal channels seem to preserve at most the AF dynamics and their analysis is encouraged for studies assessing the AF substrate during SR., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Parallel Study on Surface and Invasive Recordings Across Catheter Ablation Steps of Paroxysmal Atrial Fibrillation

  • Vraka, Aikaterini
  • Hornero, Fernando
  • Quesada, Aurelio
  • Ravelli, Flavia
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Catheter ablation (CA) is the star treatment of atrial fibrillation (AF). However, important issues regarding its procedure have only been superficially explored. While universal CA effect is assessed, the role of right (RPVI) and left pulmonary vein isolation (LPVI) is ignored. Although coronary sinus (CS) is the prevailing CA reference, how CS itself is modified by CA is unknown. This work evaluates the effect of each ablation step on the atrial substrate and CS funtion. Five-minute lead II and bipolar CS recordings of 29 patients undergoing paroxysmal AF CA were acquired before CA, after LPVI and after RPVI (end of CA). Separate lead II and CS analysis was performed. Duration, amplitude, area and slope rate were calculated for each surface and invasive activation, then signal-averaged. Dispersion, morphology variability (MV) and time-domain heart-rate variability (HRV) features were also calculated. Non-parametric tests were recruited to compare each feature among all and in pairs of different ablation steps with Bonferroni correction. Variation of each feature was calculated in percentages. In surface recordings, duration was significantly shortened after LPVI (¿= -13%, p=0.001) and HRV showed a trend for attenuation (¿< -25%, p< 0.069) after RPVI. In CS recordings, HRV showed an increasing trend after LPVI (¿>+73%, p<0.04S), tending to decrease after RPVI (¿< -33%, p<0.064). Higher dispersion in variations was observed in CS than surface recordings. LPVI causes major alterations in atrial substrate, more prominently observed from lead II analysis. Notwithstanding, HRV variations are better illustrated in CS recordings. A combined analysis of both is recommended., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Multi-scale Entropy Evaluates the Proarrhythmic Condition of Persistent Atrial Fibrillation Patients Predicting Early Failure of Electrical Cardioversion

  • Cirugeda Roldan, Eva María
  • Calero, Sofía
  • Hidalgo, Víctor Manuel
  • Enero, José
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial fibrillation (AF) is nowadays the most common cardiac arrhythmia, being associated with an increase in cardiovascular mortality and morbidity. When AF lasts for more than seven days, it is classified as persistent AF and external interventions are required for its termination. A well-established alternative for that purpose is electrical cardioversion (ECV). While ECV is able to initially restore sinus rhythm (SR) in more than 90% of patients, rates of AF recurrence as high as 20-30% have been found after only a few weeks of follow-up. Hence, new methods for evaluating the proarrhythmic condition of a patient before the intervention can serve as efficient predictors about the high risk of early failure of ECV, thus facilitating optimal management of AF patients. Among the wide variety of predictors that have been proposed to date, those based on estimating organization of the fibrillatory (f-) waves from the surface electrocardiogram (ECG) have reported very promising results. However, the existing methods are based on traditional entropy measures, which only assess a single time scale and often are unable to fully characterize the dynamics generated by highly complex systems, such as the heart during AF. The present work then explores whether a multi-scale entropy (MSE) analysis of thef-waves may provide early prediction of AF recurrence after ECV. In addition to the common MSE, two improved versions have also been analyzed, composite MSE (CMSE) and refined MSE (RMSE). When analyzing 70 patients under ECV, of which 31 maintained SR and 39 relapsed to AF after a four week follow-up, the three methods provided similar performance. However, RMSE reported a slightly better discriminant ability of 86%, thus improving the other multi-scale-based outcomes by 3-9% and other previously proposed predictors of ECV by 15-30%. This outcome suggests that investigation of dynamics at large time scales yields novel insights about the underlying complex processes generatingf-waves, which could provide individual proarrhythmic condition estimation, thus improving preoperative predictions of ECV early failure., This research has been supported by grants DPI2007-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501000411 from Junta de Comunidades de Castilla la Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Application of Deep Learning for Quality Assessment of Atrial Fibrillation ECG Recordings

  • Huerta, Alvaro
  • Martinez-Rodrigo, Arturo
  • Arias, Miguel A.
  • Langley, Philip
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] In the last years, atrial fibrillation (AF) has become one of the most remarkable health problems in the developed world. This arrhythmia is associated with an increased risk of cardiovascular events, being its early detection an unresolved challenge. To palliate this issue, long-term wearable electrocardiogram (ECG) recording systems are used, because most of AF episodes are asymptomatic and very short in their initial stages. Unfortunately, portable equipments are very susceptible to be contaminated with different kind of noises, since they work in highly dynamics and ever-changing environments. Within this scenario, the correct identification of free-noise ECG segments results critical for an accurate and robust AF detection. Hence, this work presents a deep learning-based algorithm to identify high-quality intervals in single-lead ECG recordings obtained from patients with paroxysmal AF. The obtained results have provided a remarkable ability to classify between high- and low-quality ECG segments about 92%, only misclassifying around 7% of clean AF intervals as noisy segments. These outcomes have overcome most previous ECG quality assessment algorithms also dealing with AF signals by more than 20%., This research has been supported by the grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha, AICO/2019/036 from Generalitat Valenciana and FEDER 2018/11744.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Reliability of Local Activation Waves Features to Characterize Paroxysmal Atrial Fibrillation Substrate During Sinus Rhythm

  • Vraka, Aikaterini
  • Hornero, Fernando
  • Quesada, Aurelio
  • Faes, Luca
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Analysis of coronary sinus (CS) electrograms (EGMs) is vastly used for the assessment of the atrial fibrillation (AF) substrate. As a catheter consists of five dipoles (distal, mid-distal, medial, mid-proximal, proximal), results may vary upon the employed channel: myocardial contraction and bad contact are unavoidable factors affecting the recording. This work aims to specify the most reliable channels in catching AF dynamics, using 44 multichannel bipolar CS recordings in sinus rhythm (SR) of paroxysmal AF with 1-5 minutes duration. Local activation waves (LAWs) were detected and main features obtained: duration, amplitude, area and correlation between dominant morphologies of each channel. Analysis was performed with Kruskal-Wallis test for multichannel comparison and Mann-Whitney U-test for pairs of channels and comparison between one and the remaining channels, using Bonferroni correction. Median values were calculated. Distal channel presented the highest alteration in LAWs features, being the least correlated channel (82.84 - 88.31%) with the lowest amplitude and area (p(max) < 0.01). Contrastly, medial and mid-proximal channels showed the most robust LAW characteristics, with very high correlation (94.53%) and high area and amplitude values (p(max) < 0.02 and p(max) < 0.07, respectively) and their analysis is recommended for AF substrate characterization during SR, Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Multidimensional Fibrillatory Waves Analysis for Improved Electrical Cardioversion Outcome Prediction in Persistent Atrial Fibrillation

  • Cirugeda, Eva M.
  • Calero, Sofía
  • Plancha, Eva
  • Enero, José
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] The European Society of Cardiology guidelines recommend electrical cardioversion (ECV) as a rhythm control strategy in persistent atrial fibrillation (AF). Although being able to initially restore sinus rhythm in most patients, mid- and long-term AF recurrence rates are high. In this context, anticipation of ECV outcome is interesting to rationalize the management of AF patients. To this end, several parameters have been recently proposed for atrial activity (AA) characterization, such as fibrillatory wave amplitude (FWA), dominant frequency (DF) and sample entropy (SEn). These indices have revealed promising results, but have been mainly computed from lead V1, thus discarding spatial information from the remaining leads. Hence, this work explores whether a multidimensional extension of these parameters can improve ECV outcome prediction. Results showed that multidimensional parameters provided more balanced values of sensitivity and specificity than unidimensional ones. While FWA and DF showed similar discriminant ability among both approaches, multivariate SEn improved the discriminant ability of its univariate version by 5%, thus predicting 80% of the ECV procedures correctly. Consequently, whereas multivariate extension of linear parameters did not reveal new predictive information, multidimensional entropy analysis was able to quantify novel AA dynamics, which have been helpful in improving ECV outcome prediction., This research was funded by projects DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from "Junta de Castilla la Mancha" and AICO/2019/036 from "Generalitat Valenciana".
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Comparación de Redes Neuronales Preentrenadas para la Evaluación de la Calidad en Registros Electrocardiográficos

  • Huerta Herraiz, A.
  • Martínez Rodrigo, A.
  • Puchol Calderón, A.
  • Pachón Iglesias, M.I.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] Actualmente, es habitual el uso de las redes neuronales convolucionales para el analisis del registro electrocardiografico (ECG). Sin embargo, su capacidad para evaluar la calidad con la que se registra esta senal fisiologica todavia no se ha examinado a fondo. Esta dificil tarea, cuyo objetivo es identificar los intervalos de ECG de baja calidad, podria ayudar a un diagnostico mas preciso de enfermedades cardiacas, especialmente si el ECG se ha registrado con un sistema de monitorizacion a largo plazo portatil o vestible. Asi pues, en este trabajo se introduce un estudio comparativo en el que se analizan varios modelos de redes neuronales en la tarea de discernir entre intervalos de ECG de alta y de baja calidad. Al no existir bases de datos suficientemente extensas, anotadas, y con acceso publico, se comparan tres redes neuronales preentrenadas, las cuales son AlexNet, GoogLeNet y VGGNet. Para ello, se han utilizado 2.000 segmentos de ECG de 5 segundos de duracion, y clasificados en dos grupos de 1.000 segmentos cada uno. Se ha obtenido una validacion robusta de los algoritmos realizando cinco procesos de entrenamiento y dividiendo el conjunto de datos de manera aleatoria, con un 80 % para entrenamiento y un 20 % para test. Los resultados muestran una exactitud generalizada en todos los modelos en torno a un 90 %. Sin embargo, en cuanto al tiempo de calculo y memoria utilizada se han observado importantes diferencias. AlexNet ha mostrado ser el metodo mas rapido para clasificar los segmentos de ECG, mientras que GoogLeNet ha requerido menos memoria. Por lo tanto, ambos algoritmos han demostrado un buen equilibrio entre la identificacion de intervalos de ECG y carga computacional., Este trabajo ha sido cofinanciado por los proyectos de investigacion competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM, AICO/2019/036 de la GVA y FEDER 2018/11744.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Deep Learning Approach for Featureless Robust Quality Assessment of Intermittent Atrial Fibrillation Recordings from Portable and Wearable Devices

  • Huerta Herraiz, Álvaro
  • Martínez-Rodrigo, Arturo
  • Bertomeu-González, Vicente
  • Quesada, Aurelio
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial fibrillation (AF) is the most common heart rhythm disturbance in clinical practice. It often starts with asymptomatic and very short episodes, which are extremely difficult to detect without long-term monitoring of the patient's electrocardiogram (ECG). Although recent portable and wearable devices may become very useful in this context, they often record ECG signals strongly corrupted with noise and artifacts. This impairs automatized ulterior analyses that could only be conducted reliably through a previous stage of automatic identification of high-quality ECG intervals. So far, a variety of techniques for ECG quality assessment have been proposed, but poor performances have been reported on recordings from patients with AF. This work introduces a novel deep learning-based algorithm to robustly identify high-quality ECG segments within the challenging environment of single-lead recordings alternating sinus rhythm, AF episodes and other rhythms. The method is based on the high learning capability of a convolutional neural network, which has been trained with 2-D images obtained when turning ECG signals into wavelet scalograms. For its validation, almost 100,000 ECG segments from three different databases have been analyzed during 500 learning-testing iterations, thus involving more than 320,000 ECGs analyzed in total. The obtained results have revealed a discriminant ability to detect high-quality and discard low-quality ECG excerpts of about 93%, only misclassifying around 5% of clean AF segments as noisy ones. In addition, the method has also been able to deal with raw ECG recordings, without requiring signal preprocessing or feature extraction as previous stages. Consequently, it is particularly suitable for portable and wearable devices embedding, facilitating early detection of AF as well as other automatized diagnostic facilities by reliably providing high-quality ECG excerpts to further processing stages., This research has been supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Study on How Catheter Ablation Affects Atrial Structures in Patients with Paroxysmal Atrial Fibrillation: The Case of the Coronary Sinus

  • Vraka, Aikaterini
  • Bertomeu-González, Vicente
  • Osca, Joaquín
  • Ravelli, Flavia
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] It has been shown that substrate modification due to catheter ablation (CA), the first-line treatment of paroxysmal atrial fibrillation (PAF), provokes alterations in P-wave features of the surface electrocardiogram. The absence of knowledge on whether invasive recordings acquired during CA can track similar modifications, creates nevertheless a significant void in the thorough understanding of CA effect on PAF. By analyzing 5-minute bipolar coronary sinus (CS) recordings from 26 PAF patients in sinus rhythm (SR) undergoing CA, this study aims to shed light on whether CA affects local activation waves (LAWs) features recorded in the CS, which is a widely used reference point to assess AF substrate. Recordings were obtained before and after CA. The analysis consisted of LAWs detection and processing of features such as duration, amplitude, positive and negative area, morphology variability (MV), dispersion and number of deflections and inflections (NODI). These features were defined similarly as with previous studies made with surface P-waves. Statistical analysis contained median calculation and comparison with Mann-Whitney U-test. Although some variations in line with previously reported results on P-wave analysis have been observed, none of them was statistically significant (p>0.05). Duration, amplitude, positive and negative area marked a minor decrease (- 1.4% to - 14.3%). MV and dispersion showed a minor to moderate increase + 64.8%). NODI showed no alteration. CA in PAF does not lead to significant variations on LAWs features of bipolar CS recordings. The alterations reported by previous studies on the P-waves may be the product of substrate modification of other atrial regions or the superposition of less significant alterations occurring at each atrial site., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Linear and Nonlinear Correlations Between Surface and Invasive Atrial Activation Features in Catheter Ablation of Paroxysmal Atrial Fibrillation

  • Vraka, Aikaterini
  • Bertomeu-González, Vicente
  • Hornero, Fernando
  • Ravelli, Flavia
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] P-waves are vastly used to assess the outcome of catheter ablation (CA) of atrial fibrillation (AF). It remains unknown, however, if coronary sinus (CS), the key reference structure in CA procedures, follows similar patterns. This study¿s objective is to detect any correlations between the behavior of P-waves and CS local activation waves (LAWs) with regard to CA procedure. Duration, amplitude, area and slope rate were studied in P-waves and LAWs of five-minute recordings from 29 patients undergoing paroxysmal AF CA. Normalization (N) due to heart rate (HR) fluctuations was performed. Pearson¿s correlation (PC) between CA-induced variations (¿) of P-waves and LAWs was calculated. Linear correlations between each P-wave/LAW were studied with PC and linear regression with 10¿fold cross-validation. Cross-quadratic sample entropy (CQSE) assessed nonlinear correlations. PC (¿ : ¿ < 52.27%, p = 0.015, P-wave/LAW: ¿ < 40.37%, p = 0.001) and linear regression analysis (R2 ¿ adj < 16.02%, p = 0.015 ) showed low/mediocre linear correlations. CQSE ( 0.8 ¿ 1.3) also suggested weak nonlinear relationships. P-waves and LAWs are poorly correlated and do not describe to the same degree the substrate modification after CA. It is possible that P-waves reflect the cumulative CA-induced modifications of various atrial sites, with CS being one of them but not the dominant., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Prediction of Early Failure in Electrical Cardioversion of Atrial Fibrillation Using Refined Multiscale Entropy

  • Cirugeda, Eva M.
  • Calero, Sofía
  • Hidalgo, Víctor M.
  • Enero, José
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] In the management of atrial fibrillation (AF), electrical cardioversion (ECV) is a common treatment. Although its initial success rate is high, many patients present AF recurrence after some weeks or months. Hence, being able to identify patients at low chance of mid-term sinus rhythm maintenance is important for a rationale therapeutic strategy. To this end, several parameters assessing fibrillatory (f-) waves have been introduced, however, with limited predictive ability. Moreover, the cardiovascular system exhibits nonlinear dynamics at different time-scales that these indices do not account for. Hence, the present work evaluates the ability of the multiscale entropy (MSE) analysis of the f-waves to improve preoperative forecasts of ECV outcome. Both traditional MSE and a refined version (RMSE) were applied to the main f waves component obtained for standard lead V1. As a reference, previously proposed predictors were also computed. Results revealed that RMSE was able to anticipate AF recurrence after 1 month of ECV with an accuracy around 78%. Moreover, a Naive Bayes model combining previous parameters and RMSE indices reported a discriminant ability 10% higher than single metrics. It could then be concluded that analysis of nonlinear dynamics at large time-scales can enhance ECV outcome predictions., This research was funded by projects: DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501000411 from Junta de Castilla la Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

The stationary wavelet transform as an efficient reductor of powerline interference for atrial bipolar electrograms in cardiac electrophysiology

  • Martinez-Iniesta, Miguel
  • RÓDENAS, JUAN
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Objective :The most relevant source of signal contamination in the cardiac electrophysiology (EP) laboratory is the ubiquitous powerline interference (PLI). To reduce this perturbation, algorithms including common fixed-bandwidth and adaptive-notch filters have been proposed. Although such methods have proven to add artificial fractionation to intra-atrial electrograms (EGMs), they are still frequently used. However, such morphological alteration can conceal the accurate interpretation of EGMs, specially to evaluate the mechanisms supporting atrial fibrillation (AF), which is the most common cardiac arrhythmia. Given the clinical relevance of AF, a novel algorithm aimed at reducing PLI on highly contaminated bipolar EGMs and, simultaneously, preserving their morphology is proposed. Approach: The method is based on the wavelet shrinkage and has been validated through customized indices on a set of synthesized EGMs to accurately quantify the achieved level of PLI reduction and signal morphology alteration. Visual validation of the algorithm¿s performance has also been included for some real EGM excerpts. Main results: The method has outperformed common filtering-based and wavelet-based strategies in the analyzed scenario. Moreover, it possesses advantages such as insensitivity to amplitude and frequency variations in the PLI, and the capability of joint removal of several interferences. Significance: The use of this algorithm in routine cardiac EP studies may enable improved and truthful evaluation of AF mechanisms., Research supported by grants DPI2017-83952-C3 MINECO/AEI/FEDER, UE and SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Multidimensional Characterization of the Atrial Activity to Predict Electrical Cardioversion Outcome of Persistent Atrial Fibrillation

  • Cirugeda, Eva M.
  • Calero, Sofia
  • Plancha, Eva
  • Enero, Jose
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] European Society of Cardiology guidelines recommend electrical cardioversion (ECV) as a rhythm control strategy in persistent atrial fibrillation (AF). Although ECV initially restores sinus rhythm (SR) in almost every patient, mid- and long-term AF recurrence rates are high, so that additional research is needed to anticipate ECV outcome and rationalize the management of AF patients. Although indices characterizing fibrillatory (f -) waves from surface lead V1, such as dominant frequency (DF), amplitude (FWA), and entropy, have reported good results, they discard the spatial information from the remaining leads. Hence, this work explores whether a multidimensional characterization approach of these parameters can improve ECV outcome prediction. The obtained results have shown that multidimensional FWA reported more balanced values of sensitivity and specificity, although the discriminant ability was similar in both cases. For DF, a similar outcome was also obtained. In contrast, multivariate entropy overcome discriminant ability of its univariate version by 5%, rightly anticipating result in more than 80% of ECV cases. Therefore, multidimensional entropy analysis seems to be able to quantify novel dynamics in the f-waves, which lead to a better ECV outcome prediction, This research was funded by the projects DPI2017-83952C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from "Junta de Castilla La Mancha" and AICO/2019/036 from "Generalitat Valenciana"
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Time Variability of Fibrillatory Waves Energy Predicts Long-Term Outcome of Atrial Fibrillation Concomitant Surgical Ablation

  • Ródenas, Juan
  • Escribano, Pilar
  • Martinez-Iniesta, Miguel
  • Garcia, Manuel
  • Hornero, Fernando
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Surgical ablation (SA) is the most effective procedure to terminate atrial fibrillation (AF) in patients requiring concomitant open-heart surgery. However, considering the great stress provoked in the patient¿s heart, along with the benefits of anticipating antiarrhythmic therapeutical decisions, preoperative prediction of long-term failure of the procedure is an interesting clinical challenge. Hence, the present work introduces a novel algorithm to anticipate SA outcome after one year of follow-up by just analyzing the surface ECG. The method firstly extracts fibrillatory waves reflected on standard lead V1 using an adaptive QRST cancellation approach. The resulting signal is then segmented into 1 s-length intervals and wavelet energy is computed for all of them. Finally, the coefficient of variation of the time series obtained for the 7th scale is computed. Analyzing 20 second-length preoperative ECG excerpts from 53 persistent AF patients undergoing concomitant openheart surgery, only the proposed method reported statistically significant differences between the patients who relapsed to AF and those who maintained sinus rhythm during the follow-up. The algorithm also provided values of sensitivity, specificity, and accuracy between 10 and 20% better than the well-established dominant atrial frequency and fibrillatory waves amplitude, thus suggesting to be a promising predictor of AF recurrence after SA., This research has been supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-la Mancha and AICO/2019/036 from Generalitat Valenciana. Moreover, Pilar Escribano holds a graduate research scholarship from University of Castilla-La Mancha.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Discrimination Between CFAEs of Paroxysmal and Persistent Atrial Fibrillation With Simple Classification Models of Reduced Features

  • Finotti, Emanuela
  • Ciaccio, Edward J.
  • Garan, Hasan
  • Bertomeu-Gonzalez, Vicente
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] A significant number of variables to discriminate between paroxysmal and persistent atrial fibrillation (ParAF vs. PerAF) has been widely exploited, mostly assessed with statistical tests aimed to suggest adequate approaches for catheter ablation (CA) of AF. However, in practice, it would be desirable to utilize simple classification models readily understandable. In this work dominant frequency (DF), AF cycle length (AFCL), sample entropy (SE) and determinism (DET) of recurrent quantification analysis were applied to recordings of complex fractionated atrial electrograms (CFAEs) of AF patients, aimed to create simple models to discriminate between ParAF and PerAF. Correlation matrix filters removed redundant information and Random Forests ranked the variables by relevance. Next, coarse tree models were built, optimally combining high-ranking indexes, and tested with leave-one-out cross-validation. The best classification performance combined SE and DF with an Accuracy (Acc) of 88.2% to discriminate ParAF from PerAF, while the highest single Acc was provided by DET reaching 82.4%. Hence, careful selection of reduced sets of features feeding simple classification models is able to discriminate accurately between CFAEs of ParAF and PerAF
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Predicting Electrical Cardioversion Outcome in Persistent Atrial Fibrillation Through Multiscale Entropy Analysis

  • Cirugeda, E.
  • Plancha, E.
  • Hidalgo, V.M.
  • Calero, S.
  • Alcaraz, R.
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial Fibrillation (AF) is the most commonly sustained cardiac arrhythmia and the major cause of cardiovascular morbidity and mortality. Because of its wide availability and initial effectiveness, electrical cardioversion (ECV) is the primary method used for reverting this arrhythmia to normal sinus rhythm (NSR). However, this procedure presents some collateral effects, and barely 80% of the patients prevail in NSR after 1 month. Thus, being able to predict the outcome of ECV before its application is of great interest in clinical practice, so cardiac complications in patients with high probability of early AF recurrence could be prevented. For that purpose, this work characterizes atrial activity (AA) in patients with persistent AF, before ECV, by means of nonlinear multiscale dynamics, particularly composite multiscale entropy (CMSE), and compares its performance with other recently used parameters, such as, dominant atrial frequency, AA¿s amplitude and sample entropy. The results show that characterizing AA by means of CMSE predicts ECV outcome with an accuracy above 90%, whereas the remaining parameters only forecast correctly about 70% of the analyzed patients. As a conclusion, using complexity techniques at different time scales for AA characterization increases the probability of correctly predicting AF recurrence., This work has been funded by projects: DPI2007-83952-C3 from MINECO/AEI/FEDER EU, SBPLY/17/180501000411 from Junta de Castilla la Mancha and AICO/2019/036 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Evaluación de la Calidad en Registros Electrocardiográficos Procedentes de Pacientes con Fibrilación Auricular Mediante una Red Neuronal Convolucional

  • Huerta Herraiz, A.
  • Martínez Rodrigo, A.
  • Arias Palomares, M.A.
  • Langley, P.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] La fibrilacion auricular (FA) es la arritmia cardiaca mas comun en la practica clinica. Su aparicion se asocia con un mayor riesgo de eventos cardiovasculares, siendo su deteccion temprana un reto todavia sin resolver. Esta arritmia suele comenzar con episodios asintomaticos y muy breves, necesitandose por tanto para su deteccion sistemas de registro electrocardiografico (ECG) con capacidad para la monitorizacion de largos periodos de tiempo. El principal problema que presentan estos sistemas es su fuerte exposicion al ruido, por ser adquiridos en entornos no controlados. Por lo tanto, es necesario disponer de sistemas automaticos que evaluen la calidad del registro de ECG adquirido, como primer paso para una deteccion precisa y temprana de la FA. Asi pues, en este trabajo se introduce un algoritmo basado en aprendizaje profundo, con el objetivo de discernir entre segmentos ECG de alta y baja calidad en registros de ECG de una sola derivacion, adquiridos en pacientes con FA. El metodo se basa en la alta capacidad de aprendizaje de una red neuronal convolucional, la cual se ha entrenado con senales de ECG sin preprocesar convertidas a imagen. Los resultados muestran una gran capacidad del metodo para discernir entre los segmentos de ECG de alta y baja calidad, alcanzando una exactitud del 95 %. Ademas, el metodo solo confunde el 6 % de los segmentos con FA como intervalos de baja calidad. Estos resultados mejoran en mas de un 20 % el rendimiento de la mayoria de los algoritmos previamente publicados para la evaluacion de la calidad del ECG que tambien tratan con señales de FA., Este trabajo ha sido cofinanciado por los proyectos de investigación competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM, AICO/2019/036 de la GVA y FEDER 2018/11744.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

ECG Quality Assessment via Deep Learning and Data Augmentation

  • Huerta, Álvaro
  • Martínez-Rodrigo, Arturo
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Quality assessment of ECG signals acquired with wearable devices is essential to avoid misdiagnosis of some cardiac disorders. For that purpose, novel deep learning algorithms have been recently proposed. However, training of these methods require large amount of data and public databases with annotated ECG samples are limited. Hence, the present work aims at validating the usefulness of a well-known data augmentation approach in this context of ECG quality assessment. Precisely, classification between high- and low-quality ECG excerpts achieved by a common convolutional neural network (CNN) trained on two databases has been compared. On the one hand, 2,000 5 second-length ECG excerpts were initially selected from a freely available database. Half of the segments were extracted from noisy ECG recordings and the other half from high-quality signals. On the other hand, using a data augmentation approach based on time-scale modification, noise addition, and pitch shifting of the original noisy ECG experts, 1,000 additional low-quality intervals were generated. These surrogate noisy signals and the original highquality ones formed the second dataset. The results for both cases were compared using a McNemar test and no statistically significant differences were noticed, thus suggesting that the synthesized noisy signals could be used for reliable training of CNN-based ECG quality indices.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Assessing the Stability of Complex Fractionated Atrial Electrograms for the Characterization of Atrial Substrate in Atrial Fibrillation

  • Finotti, Emanuela
  • Ciaccio, Edward J.
  • Garan, Hasan
  • Hornero, Fernando
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Aimed at characterizing the atrial substrate in atrial fibrillation (AF), a wide number of indexes has been investigated on complex fractionated atrial electrograms (CFAEs). However, many times the assessment of CFAEs signal quality as well as intra-recording and intra-patient stability of CFAEs is missing. The present work introduces the application of nonlinear metrics to assess intra-recording and intra-patient stability on a total of 204 AF bipolar CFAEs, of 16 seconds in length from patients with paroxysmal ( n=15) and persistent ( n=19) AF. To estimate differences between intra-recording and intra-patient CFAEs, the coefficient of variation (CV) has been used on Sample Entropy (SE) and on the Determinism (DET) of Recurrence Quantification Analysis (RQA) of the data. In addition, the variations introduced by discarding artifacted and noisy CFAE segments were also analyzed. Intra-recording analysis indicated a significant variation of CV(%) in any segment length both for DET and SE when discarding segments, with larger decreases for longer segments. Large variations of CV(%) for DET and SE at any segment length were observed in the intra-patient analysis but, in this case, discarding segments did not improve results. The Kruskal-Wallis test reported statistically significant differences for DET and SE among channels, regardless of the discarding process. Therefore, the observed high variability of CFAEs has proved that averaging data in one channel or among different channels may lead to an unfair oversimplification of CFAE-based atrial substrate characterization., Research supported by grants DPI2017¿83952¿C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2019/036 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Predicting Atrial Fibrillation Recurrence After Catheter Ablation Through Time Variability of P-wave Features

  • Ruiz, Antonio
  • Arias, Miguel A.
  • Puchol, Alberto
  • Pachon, Marta, I
  • Alcaraz, Raul
  • Rieta, J J|||0000-0002-3364-6380
[EN] Nowadays, the first-line therapy for paroxysmal atrial fibrillation (PAF) is pulmonary vein isolation through catheter ablation. However, the success rate of this procedure is still not as high as desirable. Thus, preoperative prediction of early AF recurrence after ablation is a challenge to select optimal candidates for the intervention. To this end, some promising predictors based on the P-wave in short ECG signals have been proposed in the last years. However, evolution of the P-wave along the time has still not been analyzed. Hence, the present work studies how time variability of two features of the P-wave predicts midterm cryoablation failure. For 45 PAF patients, a standard 12-lead ECG signal was obtained for 5 minutes before ablation. An automatic algorithm was then used to delineate all P-waves in lead II, and duration and amplitude were computed. The resulting time series were characterized by their mean, standard deviation and coefficient of variation (CV). Correlating these measures with ablation outcome, the CV for both parameters obtained the best discrimination between patients. In fact, compared with the mean value, the CV for both features obtained accuracies 10% greater, thus achieving values of 70%. These outcomes entail that time variability of the P-wave can reveal new information about the proarrhythmic condition of the patients, thus improving predictions of ablation failure.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Alternative Time-Domain P-wave Analysis for Precise Information on Substrate Alteration After Pulmonary Vein Isolation for Atrial Fibrillation

  • Vraka, Aikaterini
  • Bertomeu-González, Vicente
  • Hornero, Fernando
  • Sörnmo, Leif
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] While P-wave duration (PWD) is primarily employed to observe the atrial substrate alterations after pulmonary vein isolation (PVI) on atrial fibrillation (AF) patients, the acquired information corresponds to the entire atria. Left (LA) and right atrium (RA), though, may be differently affected by PVI, implying the need for different after-PVI handling. In order to clarify this assumption, five-minute lead II recordings from 29 paroxysmal AF patients undergoing first-ever PVI were recruited before and after PVI. PWD was analyzed integrally and in parts, with the first part (PWD1) from the onset to the peak corresponding to RA and the second part (PWD2) to LA depolarization. Time from P-wave onset or offset to the R peak were also calculated (P-on - R and P-off - R, respectively). Normalization (N) to mitigate heart-rate effect was applied. Results before and after PVI were compared with Mann-Whitney U-test (MWU). Median values and variations due to PVI were calculated for all features and compared between PWD and the remaining features via Pearson correlation. After PVI, PWD (-9.84%, p = 0.0085, N : -17.96%, p = 0.0442) and PWD2 (-22.03% p = 0.0250, N : -27.77%; p = 0.0268) were significantly decreased. PWD1 did not shorten significantly (up to -8.96%, p > 0.05 at either cases). PWD - PWD1 (rho > 74.5%; p < 0.0001) showed higher correlation than PWD - PWD2 (rho > 41.9%; p < 0.0001) in before and after PVI analysis but not for PVI-related variation (rho(PWD - PWD1) = 54.0%; p = 0.0114 and rho(PWD - PWD2) = 61.4%; p = 0.0031). While RA depolarization time is more in line with PWD analysis, the effect of PVI in PWD is more coherent with LA's findings. Additionally, PWD shortening is only observed in the LA. Therefore, LA is crucial for the assessment of the atrial substrate alteration after PVI and its analysis should be considered by future studies., Research supported by grants DPI2017-83952-C3 from MINECO/AEI/FEDER UE, SBPLY/17/180501/000411 from JCCLM and AICO/2021/286 from GVA.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Splitting the P-Wave: Improved Evaluation of Left Atrial Substrate Modification after Pulmonary Vein Isolation of Paroxysmal Atrial Fibrillation

  • Vraka, Aikaterini
  • Bertomeu-González, Vicente
  • Hornero, Fernando
  • Quesada, Aurelio
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Atrial substrate modification after pulmonary vein isolation (PVI) of paroxysmal atrial fibrillation (pAF) can be assessed non-invasively by analyzing P-wave duration in the electrocardiogram (ECG). However, whether right (RA) and left atrium (LA) contribute equally to this phenomenon remains unknown. The present study splits fundamental P-wave features to investigate the different RA and LA contributions to P-wave duration. Recordings of 29 pAF patients undergoing first-ever PVI were acquired before and after PVI. P-wave features were calculated: P-wave duration (PWD), duration of the first (PWDon-peak) and second (PWDpeak-off) P-wave halves, estimating RA and LA conduction, respectively. P-wave onset (PWon-R) or offset (PWoff-R) to R-peak interval, measuring combined atrial/atrioventricular and single atrioventricular conduction, respectively. Heart-rate fluctuation was corrected by scaling. Pre- and post-PVI results were compared with Mann-Whitney U-test. PWD was correlated with the remaining features. Only PWD (non-scaling: & UDelta;=-9.84%, p=0.0085, scaling: & UDelta;=-17.96%, p=0.0442) and PWDpeak-off (non-scaling: & UDelta;=-22.03%, p=0.0250, scaling: & UDelta;=-27.77%, p=0.0268) were decreased. Correlation of all features with PWD was significant before/after PVI (p < 0.0001), showing the highest value between PWD and PWon-R (rho max=0.855). PWD correlated more with PWDon-peak (rho= 0.540-0.805) than PWDpeak-off (rho= 0.419-0.710). PWD shortening after PVI of pAF stems mainly from the second half of the P-wave. Therefore, noninvasive estimation of LA conduction time is critical for the study of atrial substrate modification after PVI and should be addressed by splitting the P-wave in order to achieve improved estimations., This research received financial support from public grants DPI2017-83952-C3, PID2021-000128525-I00 and PID2021-123804OB-I00 of the Spanish Government 10.13039/501100011033 jointly with the European Regional Development Fund (EU), SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2021/286 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

An Efficient Hybrid Methodology for Local Activation Waves Detection under Complex Fractionated Atrial Electrograms of Atrial Fibrillation

  • Osorio, Diego
  • Vraka, Aikaterini
  • Quesada, Aurelio
  • Hornero, Fernando
  • Alcaraz, Raúl
  • Rieta, J J|||0000-0002-3364-6380
[EN] Local activation waves (LAWs) detection in complex fractionated atrial electrograms (CFAEs) during catheter ablation (CA) of atrial fibrillation (AF), the commonest cardiac arrhythmia, is a complicated task due to their extreme variability and heterogeneity in amplitude and morphology. There are few published works on reliable LAWs detectors, which are efficient for regular or low fractionated bipolar electrograms (EGMs) but lack satisfactory results when CFAEs are analyzed. The aim of the present work is the development of a novel optimized method for LAWs detection in CFAEs in order to assist cardiac mapping and catheter ablation (CA) guidance. The database consists of 119 bipolar EGMs classified by AF types according to Wells' classification. The proposed method introduces an alternative Botteron's preprocessing technique targeting the slow and small-ampitude activations. The lower band-pass filter cut-off frequency is modified to 20 Hz, and a hyperbolic tangent function is applied over CFAEs. Detection is firstly performed through an amplitude-based threshold and an escalating cycle-length (CL) analysis. Activation time is calculated at each LAW's barycenter. Analysis is applied in five-second overlapping segments. LAWs were manually annotated by two experts and compared with algorithm-annotated LAWs. AF types I and II showed 100% accuracy and sensitivity. AF type III showed 92.77% accuracy and 95.30% sensitivity. The results of this study highlight the efficiency of the developed method in precisely detecting LAWs in CFAEs. Hence, it could be implemented on real-time mapping devices and used during CA, providing robust detection results regardless of the fractionation degree of the analyzed recordings., This research has received partial financial support from public grants DPI2017-83952-C3, PID2021-00X128525-IV0 and PID2021-123804OB-I00 of the Spanish Government 10.13039/501100011033 jointly with the European Regional Development Fund (EU), SBPLY/17/180501/000411 from Junta de Comunidades de Castilla-La Mancha and AICO/2021/286 from Generalitat Valenciana.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Verificación Sobre la Estabilidad de Electrogramas Fragmentados para la Caracterización del Sustrato Auricular en Pacientes con Fibrilación Auricular

  • Finotti, E.
  • Hornero Sos, F.
  • Bertomeu-González, V.
  • Osca Asensi, J.
  • Alcaraz Martínez, R.
  • Rieta, J J|||0000-0002-3364-6380
[ES] Para caracterizar el sustrato auricular en fibrilacion auricular (FA) se ha investigado un amplio numero de indices aplicados a electrogramas auriculares fragmentados complejos (CFAE). Sin embargo, se ha obviado la evaluacion de su calidad, asi como de su estabilidad interna (intra-canal) e intra-paciente. Este trabajo evalua la estabilidad intracanal e intra-paciente de 204 CFAEs bipolares de FA registrados en pacientes con FA paroxistica (n = 15) y persistente (n = 19) aplicando indices no lineales. Para estimar las diferencias entre los CFAEs se ha utilizado el coeficiente de variacion (CV) de la entropia muestral (SE) y el determinismo (DET) del analisis de cuantificacion de recurrencias (RQA) de los datos. Ademas, tambien se analizaron las variaciones introducidas al descartar los segmentos de CFAEs ruidosos y con artefactos. El analisis intra-canal reporto una variacion significativa del CV( %) para cualquier longitud de segmento analizado tanto para DET como para SE al descartar segmentos ruidosos, habiendo mayores disminuciones para segmentos mas largos. Ademas, se observaron grandes variaciones de CV( %) para DET y SE en cualquier longitud de segmento en el analisis intra-paciente, pero en este caso, el descarte de segmentos ruidosos no mejoro resultados. La prueba de Kruskal-Wallis reporto diferencias estadisticamente significativas para DET y SE entre canales, independientemente del proceso de descarte. Por tanto, la alta variabilidad observada de los CFAEs ha demostrado que promediar los datos en un canal o entre diferentes canales puede conducir a una simplificacion excesiva de la caracterizacion del sustrato auricular basada en CFAEs., El presente trabajo ha sido cofinanciado por los proyectos de investigacion competitiva DPI2017-83952-C3 de MINECO-AEI-FEDER-UE, SBPLY/17/180501/000411 de la JCCLM y AICO/2019/036 de la GVA.