Time-Domain and Morphological Analysis of the P-Wave. Part I: Technical Aspects for Automatic Quantification of P-Wave Features

CNN-FWS: A Model for the Diagnosis of Normal and Abnormal ECG with Feature Adaptive

(1) Background and objective: Cardiovascular disease is one of the most common causes of death in today’s world. ECG is crucial in the early detection and prevention of cardiovascular disease. In this study, an improved deep learning method is proposed to diagnose abnormal and normal ECG accurately. (2) Methods: This paper proposes a CNN-FWS that combines three convolutional neural networks (CNN) and recursive feature elimination based on feature weights (FW-RFE), which diagnoses abnormal and normal ECG. F1 score and Recall are used to evaluate the performance. (3) Results: A total of 17,259 records were used in this study, which validated the diagnostic performance of CNN-FWS for normal and abnormal ECG signals in 12 leads. The experimental results show that the F1 score of CNN-FWS is 0.902, and the Recall of CNN-FWS is 0.889. (4) Conclusion: CNN-FWS absorbs the advantages of convolutional neural networks (CNN) to obtain three parts of different spatial information and enrich the learned features. CNN-FWS can select the most relevant features while eliminating unrelated and redundant features by FW-RFE, making the residual features more representative and effective. The method is an end-to-end modeling approach that enables an adaptive feature selection process without human intervention.

Beat-to-beat P-wave morphology as a predictor of paroxysmal atrial fibrillation

BACKGROUND AND OBJECTIVES

Atrial Fibrillation (AF) is the most common cardiac arrhythmia. The initiation and the perpetuation of AF is linked with phenomena of atrial remodeling, referring to the modification of the electrical and structural characteristics of the atrium. P-wave morphology analysis can reveal information regarding the propagation of the electrical activity on the atrial substrate. The purpose of this study is to investigate patterns on the P-wave morphology that may occur in patients with Paroxysmal AF (PAF) and which can be the basis for distinguishing between PAF and healthy subjects.

METHODS

Vectorcardiographic signals in the three orthogonal axes (X, Y and Z), of 3-5 min duration, were analyzed during SR. In total 29 PAF patients and 34 healthy volunteers were included in the analysis. These data were divided into two distinct datasets, one for the training and one for the testing of the proposed approach. The method is based on the identification of the dominant and the secondary P-wave morphology by combining adaptive k-means clustering of morphologies and a beat-to-beat cross correlation technique. The P-waves of the dominant morphology were further analyzed using wavelet transform whereas time domain characteristics were also extracted. Following a feature selection step, a SVM classifier was trained, for the discrimination of the PAF patients from the healthy subjects, while its accuracy was tested using the independent testing dataset.

RESULTS

In the cohort study, in both groups, the majority of the P-waves matched a main and a secondary morphology, while other morphologies were also present. The percentage of P-waves which simultaneously matched the main morphology in all three leads was lower in PAF patients (90.4 ± 7.8%) than in healthy subjects (95.5 ± 3.4%, p= 0.019). Three optimal scale bands were found and wavelet parameters were extracted which presented statistically significant differences between the two groups. Classification between the two groups was based on a feature selection process which highlighted 7 features, while an SVM classifier resulted a balanced accuracy equal to 93.75%. The results show the virtue of beat-to-beat analysis for PAF prediction.

CONCLUSION

The difference in the percentage of the main P-wave-morphology and in the P-wave time-frequency characteristics suggests a higher electrical instability of the atrial substrate in patients with PAF and different conduction patterns in the atria.

Beat-to-beat variability of P-wave in patients suffering from atrial fibrillation

The aim of this paper was to analyze the P-wave variability over time in patients suffering from Atrial Fibrillation (AF). Behind some time-domain and morphological features of the P-wave template, two novel indexes of P-wave variability have been estimated: one based on the cross-correlation coefficients among the P-waves (Correlation Index, CI), and one associated to variation of P-waves amplitude (Amplitude Index, AI). These indexes were estimated in two experimental models: patients suffering from persistent AF respect to control subjects and patients developing post-operative AF (POAF) after coronary artery bypass grafting respect to patients without POAF. The control group resulted to be characterized by shorter P-wave duration and by a less amount of fragmentation and variability, respect to AF patients (with a sensitivity and specificity of 98.4% and 95 % respectively). Also P-wave features resulted to be different for patients with POAF respect to patients without. In conclusion the quantification of the P-wave variability over time can add information in the understanding of the association between the anatomical atrial substrate and atrial arrhythmias.

Application of the relative wavelet energy to heart rate independent detection of atrial fibrillation

BACKGROUND AND OBJECTIVES

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and a growing healthcare burden worldwide. It is often asymptomatic and may appear as episodes of very short duration; hence, the development of methods for its automatic detection is a challenging requirement to achieve early diagnosis and treatment strategies. The present work introduces a novel method exploiting the relative wavelet energy (RWE) to automatically detect AF episodes of a wide variety in length.

METHODS

The proposed method analyzes the atrial activity of the surface electrocardiogram (ECG), i.e., the TQ interval, thus being independent on the ventricular activity. To improve its performance under noisy recordings, signal averaging techniques were applied. The method's performance has been tested with synthesized recordings under different AF variable conditions, such as the heart rate, its variability, the atrial activity amplitude or the presence of noise. Next, the method was tested with real ECG recordings.

RESULTS

Results proved that the RWE provided a robust automatic detection of AF under wide ranges of heart rates, atrial activity amplitudes as well as noisy recordings. Moreover, the method's detection delay proved to be shorter than most of previous works. A trade-off between detection delay and noise robustness was reached by averaging 15 TQ intervals. Under these conditions, AF was detected in less than 7 beats, with an accuracy higher than 90%, which is comparable to previous works.

CONCLUSIONS

Unlike most of previous works, which were mainly based on quantifying the irregular ventricular response during AF, the proposed metric presents two major advantages. First, it can perform successfully even under heart rates with no variability. Second, it consists of a single metric, thus turning its clinical interpretation and real-time implementation easier than previous methods requiring combined indices under complex classifiers.

P-wave Variability and Atrial Fibrillation

The analysis of P-wave template has been widely used to extract indices of Atrial Fibrillation (AF) risk stratification. The aim of this paper was to assess the potential of the analysis of the P-wave variability over time in patients suffering from atrial fibrillation. P-wave features extracted from P-wave template together with novel indices of P-wave variability have been estimated in a population of patients suffering from persistent AF and compared to those extracted from control subjects. We quantify the P-wave variability over time using three algorithms and we extracted three novel indices: one based on the cross-correlation coefficients among the P-waves (Cross-Correlation Index, CCI), one associated to variation in amplitude of the P-waves (Amplitude Dispersion Index, ADI), one sensible to the phase shift among P-waves (Warping Index, WI). The control group resulted to be characterized by shorter P-wave duration and by a less amount of fragmentation and variability, respect to AF patients. The parameter CCI shows the highest sensitivity (97.3%) and a good specificity (95%).

Role of the P-wave high frequency energy and duration as noninvasive cardiovascular predictors of paroxysmal atrial fibrillation

A normal cardiac activation starts in the sinoatrial node and then spreads throughout the atrial myocardium, thus defining the P-wave of the electrocardiogram. However, when the onset of paroxysmal atrial fibrillation (PAF) approximates, a highly disturbed electrical activity occurs within the atria, thus provoking fragmented and eventually longer P-waves. Although this altered atrial conduction has been successfully quantified just before PAF onset from the signal-averaged P-wave spectral analysis, its evolution during the hours preceding the arrhythmia has not been assessed yet. This work focuses on quantifying the P-wave spectral content variability over the 2h preceding PAF onset with the aim of anticipating as much as possible the arrhythmic episode envision. For that purpose, the time course of several metrics estimating absolute energy and ratios of high- to low-frequency power in different bands between 20 and 200Hz has been computed from the P-wave autoregressive spectral estimation. All the analyzed metrics showed an increasing variability trend as PAF onset approximated, providing the P-wave high-frequency energy (between 80 and 150Hz) a diagnostic accuracy around 80% to discern between healthy subjects, patients far from PAF and patients less than 1h close to a PAF episode. This discriminant power was similar to that provided by the most classical time-domain approach, i.e., the P-wave duration. Furthermore, the linear combination of both metrics improved the diagnostic accuracy up to 88.07%, thus constituting a reliable noninvasive harbinger of PAF onset with a reasonable anticipation. The information provided by this methodology could be very useful in clinical practice either to optimize the antiarrhythmic treatment in patients at high-risk of PAF onset and to limit drug administration in low risk patients.

The P Wave Time-Frequency Variability Reflects Atrial Conduction Defects before Paroxysmal Atrial Fibrillation

BACKGROUND

The study of atrial conduction defects associated with the onset of paroxysmal atrial fibrillation (PAF) can be addressed by analyzing the P wave from the surface electrocardiogram (ECG). Traditionally, signal-averaged ECGs have been mostly used for this purpose. However, this alternative hinders the possibility to quantify every single P wave, its variability over time, as well as to obtain complimentary and evolving information about the arrhythmia. This work analyzes the time progression of several time and frequency P wave features as potential indicators of atrial conduction variability several hours preceding the onset of PAF.

METHODS

The longest sinus rhythm interval from 24-hour Holter recordings of 46 PAF patients was selected. Next, the 2 hours before the onset of PAF were extracted and divided into two 1-hour periods. Every single P wave was automatically delineated and characterized by 16 time and frequency metrics, such as its duration, absolute energy in several frequency bands and high-to-low-frequency energy ratios. Finally, the P wave variability over each 1-hour period was estimated from the 16 features making use of a least-squares linear fitting. As a reference, the same parameters were also estimated from a set of 1-hour ECG segments randomly chosen from a control group of 53 healthy subjects age-, gender-, and heart rate-matched.

RESULTS

All the analyzed metrics provided an increasing P wave variability trend as the onset of PAF approximated, being P wave duration and P wave high-frequency energy the most significant individual metrics. The linear fitting slope α associated with P wave duration was (2.48 ± 1.98)×10(-2) for healthy subjects, (23.8 ± 14.1)×10(-2) for ECG segments far from PAF and for (81.8 ± 48.7)×10(-2) ECG segments close to PAF p = 6.96×10(-22) . Similarly, the P wave high-frequency energy linear fitting slope was (2.42 ± 4.97)×10(-9) , (54.2 ± 107.1)×10(-9) and (274.2 ± 566.1)×10(-9) , respectively (p = 2.85×10(-20) ). A univariate discriminant analysis provided that both P wave duration and P wave high-frequency energy could discern among the three ECG sets with diagnostic ability around 80%, which was improved up to 88% by combining these metrics in a multivariate discriminant analysis.

CONCLUSION

Alterations in atrial conduction can be successfully quantified several hours before the onset of PAF by estimating variability over time of several time and frequency P wave features.

Gaussian modeling of the P-wave morphology time course applied to anticipate paroxysmal atrial fibrillation

This paper introduces a new algorithm to quantify the P-wave morphology time course with the aim of anticipating as much as possible the onset of paroxysmal atrial fibrillation (PAF). The method is based on modeling each P-wave with a single Gaussian function and analyzing the extracted parameters variability over time. The selected Gaussian approaches are associated with the amplitude, peak timing, and width of the P-wave. In order to validate the algorithm, electrocardiogram segments 2 h preceding the onset of PAF episodes from 46 different patients were assessed. According to the expected intermittently disturbed atrial conduction before the onset of PAF, all the analyzed Gaussian metrics showed an increasing variability trend as the PAF onset approximated. Moreover, the Gaussian P-wave width reported a diagnostic accuracy around 80% to discern between healthy subjects, patients far from PAF, and patients less than 1 h close to a PAF episode. This discriminant power was similar to those provided by the most classical time-domain approach, i.e., the P-wave duration. However, this newly proposed parameter presents the advantage of being less sensitive to a precise delineation of the P-wave boundaries. Furthermore, the linear combination of both metrics improved the diagnostic accuracy up to 86.69%. In conclusion, morphological P-wave characterization provides additional information to the metrics based on P-wave timing.

Spatial pattern of P waves in paroxysmal atrial fibrillation patients in sinus rhythm and controls

BACKGROUND

Measuring body surface potentials in the assessment of the electrical activity of the heart is the most commonly used noninvasive method for diagnosing cardiac arrhythmias. Paroxysmal atrial fibrillation (PAF) patients have disturbed cardiac electrophysiology but the detailed characteristics of atrial activation on the body surface are unknown.

METHODS

P waves from 60 sites on the body surface were analyzed from 10 PAF patients in sinus rhythm (PAF group) and 10 healthy controls (HC group). Evolution of atrial depolarization was described qualitatively by maps of P-wave amplitudes. P-wave dipole evolution was described quantitatively by measuring the changing location (body site) and amplitude of the dipole positive and negative pole peaks.

RESULTS

Both groups exhibited similar dipolar structure with an area of positive and an area of negative potentials. Over the depolarization cycle, there were significant changes in the location of the dipole with the positive pole rotating anteriorly right to left by two electrode sites (10 cm) (P = 0.001). There were significant differences between groups with the positive pole in PAF offset to the right of the chest by 0.43 (0.38) strips compared to HC (P < 0.007). Compared to controls, the PAF group positive poles reached peak amplitude sooner (49 [11] ms vs 65 [14] ms, P = 0.012) and negative poles reached peak amplitude later (74 [13] ms vs 62 [8] ms, P = 0.019).

CONCLUSION

Atrial depolarization is characterized by a single dipole with time-varying amplitude and orientation with significant differences in dipole trajectory between patients with PAF and HCs.

P-wave characteristics after electrical external cardioversion: predictive indexes of relapse

Atrial fibrillation (AF) is the most common arrhythmia in the western countries and accounts for hundred thousand strokes per year. Electrocardiographic characteristics of AF have been demonstrated to help identify patients at risk of developing AF. Prolonged and highly fragmented P-waves have been observed in patients prone to AF, and time-domain. Morphological characteristics of the P-wave from surface ECG recordings turned out to significantly distinguish patients at risk of AF. The aim of this study is to evaluate the morphological and time-domain characteristics of the P-wave in patients with AF relapse after cardioversion, respect to patients without. 14 patients who underwent successful electrical cardioversion for persistent AF were enrolled. Five minute ECG recordings were performed for each subject, immediately post-successful cardioversion. ECG signals were acquired by using a 16-lead mapping system for high-resolution biopotential measurements (sample frequency 2 kHz, 31 nV resolution, 0-400 Hz bandwidth). From the 16 recordings, a standard 12-lead ECG was derived and analyzed in terms of signal-averaged P-wave. Time-domain and mor-phological characteristics were estimated from the averaged P-waves of each lead. Time-domain features were quantified as: maximum P-wave duration in any of the 12 leads (Pmax), minimum P-wave duration in any of the leads (Pmin), P-wave dispersion (Pdisp=Pmax-Pmin), and Pindex (standard devia-tion of P-wave duration in any of the 12 leads). Morphological characteristics were extracted from a Gaussian function-based model of the P-wave as: average model order (Nav), maximum number of zero-crossing (PCmax), and maximum and average number of maxima and minima (FCImax and FCIav) in any of the leads. The results obtained so far indicate that the morphological and time-domain characteristics distinguish between patients with AF relapse and patients without.