Search

El desarrollo de técnicas de extracción de las ondas fibrilatorias (ondas-f) del electrocardiograma (ECG) de superficie ha posibilitado su análisis para detectar y mejorar el tratamiento de la fibrilación auricular (FA). Sin embargo, estas técnicas tienen un rendimiento limitado por la presencia de artefactos y complejos QRST de morfología variable. Por ello, se propone una metodología para optimizar la selección de tramos de ondas-f libres de residuos de la cancelación ventricular. Primeramente, la detección de valores atípicos fuera del margen comprendido entre 2,5 veces los percentiles de 5 y 95% de la señal de ondas-f extraída del ECG preoperatorio al procedimiento de ablación por catéter (AC) de 148 pacientes de FA persistente permitió la detección de los artefactos registrados. Seguidamente, se caracterizaron los intervalos QRST cancelados para estimar la actividad ventricular remanente en las ondas-f mediante diferentes métricas. RuVR fue la más capacitada para tal fin (71,66% de exactitud), obtenida del producto del valor cuadrático medio de las ondas-f en el intervalo QRST por su valor máximo. No obstante, su combinación con otras métricas mediante un modelo de ensamblado de árboles de decisión mejoró la exactitud en la detección de residuos ventriculares hasta alcanzar casi un 82%. Finalmente, esta metodología demostró la relevancia de asegurar la calidad de los tramos de ondas-f extraídos del ECG de superficie, mejorando la capacidad discriminatoria de la frecuencia dominante de las ondas-f para predecir el resultado del procedimiento de AC.

La apnea obstructiva del sueno (AOS) es un síndrome respiratorio estrechamente relacionado con múltiples enfermedades cardiovasculares. La AOS se encuentra muy infradiagnosticada debido al coste prohibitivo de la polisomnografía, el estándar de oro para su detección. Ante este escenario, se han propuesto numerosas alternativas basadas en una derivación de ECG y la variabilidad del ritmo cardiaco (VRC), junto con diversas técnicas de aprendizaje automático (AA). Sin embargo, no existen muchos trabajos basados en el análisis de recurrencia de la VRC. Por ello, el presente estudio propone evaluar métodos tradicionales de AA y enfoques modernos de aprendizaje profundo (AP) para mejorar la detección de AOS por métodos alternativos a la PSG. En particular, se evaluara el diagrama de recurrencia general (DRG) de la VRC y se comparara su rendimiento de clasificación con su homónimo tradicional basado en el análisis de cuantificación de recurrencia (ACR). Asimismo, se emplearan bases de datos publicas del repositorio Physionet, con grabaciones de ECG divididas en intervalos de un minuto. Por ultimo, a través de buenas practicas de validación, se describir a y discutir´ a la forma en la que los modelos de AP con DRG superan a los modelos AA tradicionales basados en ACR en términos de exactitud, sensibilidad y especificidad.

[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.

[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.

[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 is an author-created, un-copyedited versíon of an article published in Physiological Measurement. IOP Publishing Ltd is not responsíble for any errors or omissíons in this versíon of the manuscript or any versíon derived from it. The Versíon of Record is available online at http://doi.org/10.1088/1361-6579/aae8b1, [EN] Objective: The electrocardiogram (ECG) is currently the most widely used recording to diagnose cardiac disorders, including the most common supraventricular arrhythmia, such as atrial fibrillation (AF). However, different types of electrical disturbances, in which power-line interference (PLI) is a major problem, can mask and distort the original ECG morphology. This is a significant issue in the context of AF, because accurate characterization of fibrillatory waves (f-waves) is unavoidably required to improve current knowledge about its mechanisms. This work introduces a new algorithm able to reduce high levels of PLI and preserve, simultaneously, the original ECG morphology. Approach: The method is based on stationary wavelet transform shrinking and makes use of a new thresholding function designed to work successfully in a wide variety of scenarios. In fact, it has been validated in a general context with 48 ECG recordings obtained from pathological and non-pathological conditions, as well as in the particular context of AF, where 380 synthesized and 20 long-term real ECG recordings were analyzed. Main results: In both situations, the algorithm has reported a notably better performance than common methods designed for the same purpose. Moreover, its effectiveness has proven to be optimal for dealing with ECG recordings affected by AF, sincef-waves remained almost intact after removing very high levels of noise. Significance: The proposed algorithm may facilitate a reliable characterization of thef-waves, preventing them from not being masked by the PLI nor distorted by an unsuitable filtering applied to ECG recordings with AF.

The analysis of P-wave variability from the electrocardiogram (ECG) has been suggested as an early predictor of the onset of paroxysmal atrial fibrillation (PAF). Hence, a preventive treatment could be used to avoid the loss of normal sinus rhythm, thus minimising health risks and improving the patient's quality of life. In these previous studies the variability of different temporal and morphological P-wave features has been only analysed in a linear fashion. However, the electrophysiological alteration occurring in the atria before the onset of PAF has to be considered as an inherently complex, chaotic and non-stationary process. This work analyses the presence of non-linear dynamics in the P-wave progression before the onset of PAF through the application of the central tendency measure (CTM), which is a non-linear metric summarising the degree of variability in a time series. Two hour-length ECG intervals just before the arrhythmia onset belonging to 46 different PAF patients were analysed. In agreement with the invasively observed inhomogeneous atrial conduction preceding the onset of PAF, CTM for all the considered P-wave features showed higher variability when the arrhythmia was closer to its onset. A diagnostic accuracy around 80% to discern between ECG segments far from PAF and close to PAF was obtained with the CTM of the metrics considered. This result was similar to previous P-wave variability methods based on linear approaches. However, the combination of linear and non-linear methods with a decision tree improved considerably their discriminant ability up to 90%, thus suggesting that both dynamics could coexist at the same time in the fragmented depolarisation of the atria preceding the arrhythmia.

Atrial fibrillation (AF) is today the most common sustained arrhythmia, its treatment being not completely satisfactory. Electrical activity organization analysis within the atria could play a key role in the improvement of current AF therapies. The application of a nonlinear regularity index, such as sample entropy (SampEn), to the atrial activity (AA) fundamental waveform has proven to be a successful noninvasive AF organization estimator. However, the use of alternative nonlinear metrics within this context is a pending issue. The present work analyzes the ability of several nonlinear indices to assess regularity of patterns and, thus, organization, in the AA signal and its fundamental waveform, defined as the main atrial wave (MAW). Precisely, Fuzzy Entropy, Spectral Entropy, Lempel-Ziv Complexity and Hurst Exponents were studied, achieving more robust and accurate AF organization estimates than SampEn. Results also provided better AF organization estimates from the MAW than from the AA signal for all the tested nonlinear metrics, which agrees with previous works only focused on SampEn. Furthermore, some of these indices reported a discriminant ability close to 95% in the classification of AF organization-dependent events, thus outperforming the diagnostic accuracy of SampEn and other widely used noninvasive estimators, such as the dominant atrial frequency (DAF). As a conclusion, these nonlinear metrics could be considered as promising estimators of noninvasive AF organization and could be helpful in making appropriate decisions on the patients' management.

Atrial fibrillation (AF) is the most common form of arrhythmia encountered in clinical practice. Its presence causes a rapid and irregular ventricular response, being the topic of intensive research in rate control therapies of AF. To this respect, recent studies suggest that ventricular response is notably influenced by atrial activity (AA) temporal organization. However, the interdependency between atrial and ventricular activations has not been adequately explored to date in real-life AF patients. The present work introduces a novel methodology to quantitatively assess synchronization and coupling between real atrial and ventricular activation series. Furthermore, the method operates on surface ECG recordings, thus providing an easy and cost-effective way to be applied. The method is based on a nonlinear index, such as cross-sample entropy (CSE), which estimates the conditional probability to find similar patterns within both activation series. The study has been carried out on patients with paroxysmal and persistent AF in order to be applied over atrial activation series with different properties in their organization. Results showed a statistically significant positive correlation between AA organization and the synchronization between atrial and ventricular activations (R = 0.53, p < 0.01). Furthermore, higher CSE values were observed for persistent (0.759 ± 0.053) than for paroxysmal AF episodes (0.662 ± 0.091), thus suggesting more synchronization between atrial and ventricular activations in paroxysmal AF. As a consequence, CSE provided findings consistent with previous works and could be used to reveal clinically useful information in the improvement of current rate control therapies, which are mainly focused on controlling ventricular rate without paying much attention to the atrial fibrillatory process.

Ectopic beats are early heart beats remarkably different to the normal beat morphology that provoke serious disturbances in electrocardiographic analysis. These beats are very common in atrial fibrillation (AF), causing important residua when ventricular activity has to be removed for atrial activity (AA) analysis. In this work, a method is proposed to cancel out ectopics by discriminating between normal and abnormal beats, with an accuracy higher than 99%, through QRS morphological delineation and characterization. The most similar ectopics to the one under cancellation are clustered to provide a very precise cancellation template. Simulated and real AF recordings were used to validate the method. A new index, able to estimate the presence of ventricular residue after ectopics cancellation, was defined. Results by using the 2, 4, 6, , 30 most similar ectopics to the one under study yielded optimal cancellation for templates composed of 10 beats. Furthermore, these beats were very likely located close to the ectopic under cancellation, which could facilitate the algorithm implementation. As conclusion, the proposed method is an effective way to remove ectopics from long term AF recordings and get them ready for the application of any QRST cancellation technique able to extract the AA in optimal conditions. Moreover, it could also detect, characterize and remove ectopics in any other type of non-AF recordings.