Classification of electrocardiographic P-wave morphology

Application of artificial intelligence ensemble learning model in early prediction of atrial fibrillation

Background

Atrial fibrillation is a paroxysmal heart disease without any obvious symptoms for most people during the onset. The electrocardiogram (ECG) at the time other than the onset of this disease is not significantly different from that of normal people, which makes it difficult to detect and diagnose. However, if atrial fibrillation is not detected and treated early, it tends to worsen the condition and increase the possibility of stroke. In this paper, P-wave morphology parameters and heart rate variability feature parameters were simultaneously extracted from the ECG. A total of 31 parameters were used as input variables to perform the modeling of artificial intelligence ensemble learning model.

Results

This paper applied three artificial intelligence ensemble learning methods, namely Bagging ensemble learning method, AdaBoost ensemble learning method, and Stacking ensemble learning method. The prediction results of these three artificial intelligence ensemble learning methods were compared. As a result of the comparison, the Stacking ensemble learning method combined with various models finally obtained the best prediction effect with the accuracy of 92%, sensitivity of 88%, specificity of 96%, positive predictive value of 95.7%, negative predictive value of 88.9%, F1 score of 0.9231 and area under receiver operating characteristic curve value of 0.911.

Conclusion

In feature extraction, this paper combined P-wave morphology parameters and heart rate variability parameters as input parameters for model training, and validated the value of the proposed parameters combination for the improvement of the model’s predicting effect. In the calculation of the P-wave morphology parameters, the hybrid Taguchi-genetic algorithm was used to obtain more accurate Gaussian function fitting parameters. The prediction model was trained using the Stacking ensemble learning method, so that the model accuracy had better results, which can further improve the early prediction of atrial fibrillation.

An effective feature extraction method based on GDS for atrial fibrillation detection

Atrial fibrillation (AF) is a common and extremely harmful arrhythmia disease. Automatic detection of AF based on ECG helps accurate and timely detection of the condition. However, the existing AF detection methods are mostly based on complex signal transformation or precise waveform localization. This is a big challenge for complex, variable, and susceptible ECG signals. Therefore, we propose a simple feature extraction method based on gradient set (GDS) for AF detection. The method first calculates the GDS of the ECG segment and then calculates the statistical distribution feature and the information quantity feature of the GDS as the input of the classifier. Experiments on four databases include 146 subjects show that the feature extraction method for detecting AF proposed in this paper has the characteristics of simple calculation, noise tolerance, and high adaptability to all kinds of classifiers, and got the best performance on the DNN classifier we designed. Therefore, it is a good choice for feature extraction in AF detection.

Wavelet Based Method for Congestive Heart Failure Recognition by Three Confirmation Functions

An investigation of the electrocardiogram (ECG) signals and arrhythmia characterization by wavelet energy is proposed. This study employs a wavelet based feature extraction method for congestive heart failure (CHF) obtained from the percentage energy (PE) of terminal wavelet packet transform (WPT) subsignals. In addition, the average framing percentage energy (AFE) technique is proposed, termed WAFE. A new classification method is introduced by three confirmation functions. The confirmation methods are based on three concepts: percentage root mean square difference error (PRD), logarithmic difference signal ratio (LDSR), and correlation coefficient (CC). The proposed method showed to be a potential effective discriminator in recognizing such clinical syndrome. ECG signals taken from MIT-BIH arrhythmia dataset and other databases are utilized to analyze different arrhythmias and normal ECGs. Several known methods were studied for comparison. The best recognition rate selection obtained was for WAFE. The recognition performance was accomplished as 92.60% accurate. The Receiver Operating Characteristic curve as a common tool for evaluating the diagnostic accuracy was illustrated, which indicated that the tests are reliable. The performance of the presented system was investigated in additive white Gaussian noise (AWGN) environment, where the recognition rate was 81.48% for 5 dB.

System light-loading technology for mHealth: Manifold-learning-based medical data cleansing and clinical trials in WE-CARE Project

Cardiovascular disease (CVD) is a major issue to public health. It contributes 41% to the Chinese death rate each year. This huge loss encouraged us to develop a Wearable Efficient teleCARdiology systEm (WE-CARE) for early warning and prevention of CVD risks in real time. WE-CARE is expected to work 24/7 online for mobile health (mHealth) applications. Unfortunately, this purpose is often disrupted in system experiments and clinical trials, even if related enabling technologies work properly. This phenomenon is rooted in the overload issue of complex Electrocardiogram (ECG) data in terms of system integration. In this study, our main objective is to get a system light-loading technology to enable mHealth with a benchmarked ECG anomaly recognition rate. To achieve this objective, we propose an approach to purify clinical features from ECG raw data based on manifold learning, called the Manifold-based ECG-feature Purification algorithm. Our clinical trials verify that our proposal can detect anomalies with a recognition rate of up to 94% which is highly valuable in daily public health-risk alert applications based on clinical criteria. Most importantly, the experiment results demonstrate that the WE-CARE system enabled by our proposal can enhance system reliability by at least two times and reduce false negative rates to 0.76%, and extend the battery life by 40.54%, in the system integration level.

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.

Neural network and wavelet average framing percentage energy for atrial fibrillation classification

ECG signals are an important source of information in the diagnosis of atrial conduction pathology. Nevertheless, diagnosis by visual inspection is a difficult task. This work introduces a novel wavelet feature extraction method for atrial fibrillation derived from the average framing percentage energy (AFE) of terminal wavelet packet transform (WPT) sub signals. Probabilistic neural network (PNN) is used for classification. The presented method is shown to be a potentially effective discriminator in an automated diagnostic process. The ECG signals taken from the MIT-BIH database are used to classify different arrhythmias together with normal ECG. Several published methods were investigated for comparison. The best recognition rate selection was obtained for AFE. The classification performance achieved accuracy 97.92%. It was also suggested to analyze the presented system in an additive white Gaussian noise (AWGN) environment; 55.14% for 0dB and 92.53% for 5dB. It was concluded that the proposed approach of automating classification is worth pursuing with larger samples to validate and extend the present study.

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.

Automated ECG diagnostic P-wave analysis using wavelets

P-wave characteristics in the human ECG are an important source of information in the diagnosis of atrial conduction pathology. However, diagnosis by visual inspection is a difficult task since the P-wave is relatively small and noise masking is often present. This paper introduces novel wavelet characteristics derived from the continuous wavelet transform (CWT) which are shown to be potentially effective discriminators in an automated diagnostic process. Characteristics of the 12-lead ECG P-wave were derived using CWT and statistical methods. A normal control group and an abnormal (atrial conduction pathology) group were compared. The wavelet characteristics captured frequency, magnitude and variance components of the P-wave. The best individual characteristics (i.e. ones that significantly discriminated the groups) were entered into a linear discriminant analysis (LDA) for four different models: two-lead ECG, three-lead ECG, a derived three-lead ECG and a factor analysis solution consisting of wavelet characteristic loadings on the factors. A comparison was also made between wavelet characteristics derived form individual P-waves verses wavelet characteristics derived from a signal-averaged P-wave for each participant. These wavelet models were also compared to standard cardiological measures of duration, terminal force and duration divided by the PR segment. Results for the individual P-wave approach generally outperformed the standard cardiological measures and the signal-averaged P-wave approach. The best wavelet model on the basis of both classification performance and simplicity was the two-lead model that uses leads II and V1. It was concluded that the wavelet approach of automating classification is worth pursuing with larger samples to validate and extend the present study.

New automated detection method of OSA based on artificial neural networks using P-wave shape and time changes

This paper describes a new method for automatic detection of obstructive sleep apnea (OSA) based on artificial neural networks (ANN) using regular electrocardiogram (ECG) recordings. ECG signals were pre-processed and segmented to extract the P-waves; then three P-wave features were extracted: the P-wave duration (T ( p )), the P-wave dispersion (P ( d )), and the time interval from the peak of the P-wave to the R-wave (T ( pr )). Combinations of the three features were used as features for classification using ANN. For each feature combination studied, 70% of the input data was used for training the ANN, 15% for validating, and 15% for testing the results. Perfect agreement between expert's scores and the ANN scores was achieved when the ANN was applied on T ( p ), P ( d ), and T ( pr ) taken together, while substantial agreements were achieved when applying the ANN on the feature combinations T ( p ) and P ( d ), and T ( p ) and T ( pr ).

Detailed ECG analysis of atrial repolarization in humans

INTRODUCTION

Data on human atrial repolarization are scarce since the QRS complex normally obscures its ECG trace. In the present study, consecutive patients with third-degree AV block were studied to better describe the human Ta wave.

METHODS AND RESULTS

Forty patients (mean age 75 years, 17 men) were included. All anti-arrhythmic drugs were discontinued before ECG recording. Standard 12-lead ECGs were recorded, transformed to orthogonal leads and studied using signal-averaged P wave analysis. The average P wave duration was 124 +/- 16 ms. The PTa duration was 449 +/- 55 ms (corrected PTa 512 +/- 60 ms) and the Ta duration (P wave end to Ta wave end) was 323 +/- 56 ms. The polarity of the Ta wave was opposite to that of the P wave in all leads. The Ta peaks were located at 196 +/- 55 ms in Lead Y, 216 +/- 50 ms in Lead X, and 335 +/- 92 in Lead Z. No correlation was found between P wave duration and Ta duration, or between Ta peak amplitude and Ta duration. The morphology of the Ta wave was similar regardless of the interatrial conduction.

CONCLUSIONS

The Ta wave has the opposite polarity, and the duration is generally two to three times that, of the P wave. Although the Ta peak may occasionally be located in the PQ interval during normal AV conduction, it is unlikely that enough information can be obtained from analysis of this segment to differentiate normal from abnormal atrial repolarization. Hence, an algorithm for QRST cancellation during sinus rhythm is needed to further improve analysis.

Time-domain and morphological analysis of the P wave. Part II: effects of atrial pacing on P-wave features

BACKGROUND

The aim of this study was to compare time-domain and morphological descriptors of paced and spontaneous P wave in patients prone to atrial fibrillation (AF).

METHODS

Nineteen patients (nine women, aged 72 +/- 10 years) affected by paroxysmal AF and implanted with dual-chamber pacemakers (PM) were studied. Two 5-minute recordings were performed during spontaneous and paced rhythm. Electrocardiogram (ECG) signals were acquired using a 32-lead mapping system. Patients were grouped into two classes: no previous AF and previous AF groups, according to the number of AF episodes in the 6 months before the analysis.

RESULTS AND CONCLUSION

During atrial pacing P wave appeared prolonged and morphologically more complex with respect to sinus rhythm. We also found that in patients at lower risk for AF, the atrial pacing changes the atrial activation to a greater extent than in patients at higher risk for AF. Finally, all time-domain and morphological descriptors of the P wave except one succeed in discriminating "no previous AF" and "previous AF" patients in spontaneous rhythm, while no significant differences have been observed during pacing for any parameters.

Variable interatrial conduction illustrated in a hypertrophic cardiomyopathy population

BACKGROUND

Patients with hypertrophic cardiomyopathy (HCM) have a high incidence of atrial fibrillation. They also have a longer P-wave duration than healthy controls, indicating conduction alterations. Previous studies have demonstrated orthogonal P-wave morphology alterations in patients with paroxysmal atrial fibrillation. In the present study, the P-wave morphology of patients with HCM was compared with that of matched controls in order to explore the nature of the atrial conduction alterations.

METHODS AND RESULTS

A total of 65 patients (45 men, mean age 49 +/- 15) with HCM were included. The control population (n = 65) was age and gender matched (45 men, mean age 49 +/- 15). Five minutes of 12-lead ECG was recorded. The data were subsequently transformed to orthogonal lead data, and unfiltered signal-averaged P-wave analysis was performed. The P-wave duration was longer in the HCM patients compared to the controls (149 +/- 22 vs 130 +/- 16 ms, P < 0.0001). Examination of the P-wave morphology demonstrated changes in conduction patterns compatible with interatrial conduction block of varying severity in both groups, but a higher degree of interatrial block seen in the HCM population. These changes were most prominent in the Leads Y and Z.

CONCLUSION

The present study suggests that the longer P-wave duration observed in HCM patients may be explained by a higher prevalence of block in one or more of the interatrial conduction routes.

P-Wave Morphology Assessment by a Gaussian Functions-Based Model in Atrial Fibrillation Patients

Aim of this study was to present a P-wave model, based on a linear combination of Gaussian functions, to quantify morphological aspects of P-wave in patients prone to atrial fibrillation (AF). Five-minute ECG recordings were performed in 25 patients with permanent dual chamber pacemakers. Patients were divided into high-risk and low-risk groups, including patients with and without AF episodes in the last 6 mo preceding the study, respectively. ECG signals were acquired using a 32-lead mapping system for high-resolution biopotential measurement (ActiveTwo, Biosemi, The Netherlands, sample frequency 2 kHz, 24-bit resolution). Up to 8 Gaussian models have been computed for each averaged P-wave extracted from every lead. The P-wave morphology was evaluated by extracting seven parameters. Classical time-domain parameters, based on P-wave duration estimation, have been also estimated. We found that the P-wave morphology can be effectively modeled by a linear combination of Gaussian functions. In addition, the combination of time-domain and morphological parameters extracted from the Gaussian function-based model of the P-wave improves the identification of patients having different risks of developing AF.

Morphological analysis of P-wave in patients prone to atrial fibrillation

Aim of this study was to present a P-wave model, based on a linear combination of Gaussian functions, to quantify morphological aspects of Pwave in patients prone to atrial fibrillation. Five minutes ECG recordings were performed in 25 patients with permanent dual chamber pacemakers set at 40/min in order to have spontaneous beats. ECG signals were acquired using a 32-lead mapping system for high-resolution biopotential measurement (ActiveTwo, Biosemi, The Netherlands, sample frequency 2 kHz, 24 bit resolution). Four healthy subjects were also recorded as a control group. Up to 8 Gaussian models have been computed for each averaged P-wave extracted from every lead. The P-wave morphology is then evaluated by the following parameters: best model orders @ degrees of freedom adjusted R-square (AdjRsq) =97.5%; minimum (sigmamin) and maximum (sigmamax) standard deviation of the Gaussians included in the model, number of relative maxima and minima (max+min), and zeroes of the fit. Significant differences in the best model order were obtained between the control group and patients group. Accordingly, the number of relative maxima and minima was higher in the patient group. These parameters might all be markers of the fractionated electrical activity that characterizes paroxysmal AF patients in sinus rhythm.

Analysis of the surface electrocardiogram for monitoring and predicting antiarrhythmic drug effects in atrial fibrillation

Specific antiarrhythmic therapy with class I and III drugs for atrial fibrillation (AF) conversion and prevention of its recurrence is frequently utilized in clinical practice. Besides being only moderate effective, the utilization of antiarrhythmic drugs may be associated with serious side effects. In the clinical setting it is difficult to directly evaluate the effects of antiarrhythmic drugs on the individual patient's atrial electrophysiology, thereby predicting their efficacy in restoring and maintaining sinus rhythm. Analysis of the surface electrocardiogram in terms of P-wave signal averaged ECG during sinus rhythm and spectral characterization of fibrillatory waves during AF for evaluation of atrial antiarrhythmic drug effects is a new field of investigation. Both techniques provide reproducible parameters for characterizing atrial electrical abnormalities and seem to contain prognostic information regarding antiarrhythmic drug efficacy. Further research is needed which elucidates the most challenging clinical questions in AF management whom to place on antiarrhythmic drug treatment and what antiarrhythmic drug to prescribe. Analysis of the surface ECG might have the potential to answer these questions.