Paroxysmal Atrial Fibrillation Events Research Articles

A comparative study on neural networks for paroxysmal atrial fibrillation events detection from electrocardiography

ObjectiveThis work conducts a comparative study on the effect of neural networks of different architectures on the detection of paroxysmal atrial fibrillation (PAF) events from dynamic electrocardiography (ECG) recordings, a problem raised in the 4th China Physiological Signal Challenge 2021 (CPSC2021). ApproachWe proposed 3 neural network models and an auxiliary one for QRS detection to tackle the problem. A convolutional recurrent neural network (CRNN) model and a U-Net model that accepts ECG waveform input make sample-wise predictions. This regards the PAF events detection as a segmentation task. A stacked bidirectional long short-term memory (LSTM) model takes the sequence of RR intervals, which is derived from the output of the QRS detection model and makes beat-wise predictions. The QRS detection model also has a CRNN architecture, which is slightly different from the model for the AF segmentation task. Final predictions are merged by outputs from models making sample-wise predictions and making beat-wise predictions. Finally, the locations of QRS complexes are used to filter out segments (both normal and AF) shorter than 5 beats.In order to make the neural network models more sensitive to the critical sample points (onsets and offsets) of the AF events, we proposed a novel masked binary cross-entropy (MaskedBCE) loss function for training the models. This loss function is the conventional BCE loss multiplied by a mask, whose values in a neighbourhood of critical sample points are significantly larger than elsewhere. Main resultsOur method received a score of 1.9972 on the first part of the hidden test set of CPSC2021 and a score of 3.0907 on the second part. The average score was 2.5440, ranked 5th out of 17 teams with successful official entries. SignificanceThis work proposed an effective solution to the problem of the detection of PAF events from dynamic ECGs and validated the efficacy of several neural network architectures on this problem.

Homocysteine as a Predictor of Paroxysmal Atrial Fibrillation-Related Events: A Scoping Review of the Literature

High levels of homocysteine (Hcy) have been linked with adverse cardiovascular outcomes, such as arrhythmias and stroke. In the context of paroxysmal atrial fibrillation (PAF), hyperhomocysteinemia has been demonstrated to be an independent predictor of future events. The aim of this report was to address the potential value of Hcy levels in predicting future paroxysms of atrial fibrillation (AF), as well as to identify the potential mechanisms of action. We searched PubMed and the Cochrane Database on 16 January 2022. Keywords used were homocysteine or hyperhomocysteinemia paired with a total of 67 different keywords or phrases that have been implicated with the pathogenesis of AF. We included primary reports of clinical and non-clinical data in the English language, as well as systematic reviews with or without meta-analyses. We placed no time constraints on our search strategy, which yielded 3748 results. Following title review, 3293 reports were excluded and 455 reports were used for title and abstract review, after which 109 reports were finally used for full-text review. Our review indicates that Hcy levels seem to hold a predictive value in PAF. Herein, potential mechanisms of action are presented and special considerations are made for clinically relevant diagnostic procedures that could complement plasma levels in the prediction of future PAF events. Finally, gaps of evidence are identified and considerations for future clinical trial design are presented.

Nonlinear Heart Rate Dynamics Before and After Paroxysmal Atrial Fibrillation Events.

Heart rate complexity, derived from nonlinear heart rate variability (HRV), has been shown to help predict the outcomes of various diseases. Changes in heart rate complexity before and after paroxysmal atrial fibrillation (PAF) events are unclear. To evaluate changes in heart rate complexity through nonlinear HRV before and after PAF events. We enrolled 65 patients (72 ± 12.34 years old, 31 females) with 99 PAF events who received 24-hour Holter recording, and analyzed nonlinear HRV variables including Poincaré plot analysis, sample entropy (SampEn), and multiscale entropy (MSE). HRV analyses were applied to a 20-minute window before the onset and after the termination of PAF events. HRV parameters were evaluated and compared based on eight different 5-minute time segments, as we divided each 20-minute window into four segments of 5 minutes each. SampEn and MSE1~5 significantly decreased before the onset of PAF events, whereas SampEn, MSE1~5 and MSE6~20 significantly increased after the termination of PAF events. SD1 and SD2, which are nonlinear HRV parameters calculated via Poincaré plot analysis, did not significantly change before the PAF events, however they both decreased significantly after termination. Heart rate complexity significantly decreased before the initiation and increased after the termination of PAF events, which indicates the crucial role of nonlinear heart rate dynamics in the initiation and termination of PAF.

A Multistep Paroxysmal Atrial Fibrillation Scanning Strategy in Long-Term ECGs

Atrial fibrillation (AF) is a progressive disease often initially manifested by intermittent episodes spontaneously terminating and is an insidious disease. The previous work trained the support vector machine (SVM) classifier on multiple RR interval features. The trained AF detector was tested on the fourth China Physiological Signal Challenge (CPSC 2021) database, achieving 97.59% and 89.83% for sensitivity and specificity on dataset 1, respectively. The test results were 96.46% and 78.64% on dataset 2, respectively. The results show that the AF detector based on rhythm is insufficient for the recognition of non-AF. Therefore, this work developed AF scanning algorithm integrating rhythm and P-wave information for long-term ECGs. The proposed algorithm is divided into three steps. First, utilize <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$a$ </tex-math></inline-formula> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">priori</i> knowledge to locate suspected AF, and then, employ a trained rhythm-based AF detector to detect AF. Finally, adopt the dynamic time warping (DTW) and an autoencoding (AE) network to quantize the P-wave information to identify the non-AF signal from AF. The results on dataset 1 were 97.44% and 98.50% and on dataset 2 were 96.13% and 87.42%. This work scanned 11 patients with 24-h paroxysmal AF (PAF). The best result is that the detection accuracy is 99.33%, and the false detection is 0.01%, and the worst outcome is that the detection accuracy is 88.75%, and the false detection is 14.06%. The results proved that the proposed method could provide reliable scanning for PAF events.

Prediction of paroxysmal atrial fibrillation using new heart rate variability features

Paroxysmal atrial fibrillation (PAF) is a cardiac arrhythmia that can eventually lead to heart failure or stroke if left untreated. Early detection of PAF is therefore crucial to prevent any further complications and avoid fatalities. An implantable defibrillator device could be used to both detect and treat the condition though such devices have limited computational capability. With this constraint in mind, this paper presents a novel set of features to accurately predict the presence of PAF. The method is evaluated using ECG signals from the widely used atrial fibrillation prediction database (AFPDB) from PhysioNet. We analysed 106 signals from 53 pairs of ECG recordings. Each pair of signals contains one 5-min ECG segment that ends just before the onset of a PAF event and another 5-min ECG segment at least 45 min distant from the PAF event, to represent a non-PAF event. Seven novel features are extracted through the Poincaré representation of R-R interval signals, and are prioritised through feature ranking schemes. The features are used with four standard classification techniques for PAF prediction and compared to the existing state of the art from the literature. Using only the seven proposed features, classification performance outperforms those of the classical state-of-the-art feature set, registering sensitivity and specificity measurements of over 96%. The results further improve when the features are combined with several of the classical features, with an accuracy increasing to 98% using a linear kernel SVM. The results show that the proposed features provide a useful representation of the PAF condition and achieve good prediction with off-the-shelf classification techniques that would be suitable for ICU deployment.

Methodology for detection of paroxysmal atrial fibrillation based on P-Wave, HRV and QR electrical alternans features

The detection of Paroxysmal Atrial Fibrillation (PAF) is a fairly complex process performed manually by cardiologists or electrophysiologists by reading an electrocardiogram (ECG). Currently, computational techniques for automatic detection based on fast Fourier transform (FFT), Bayes optimal classifier (BOC), k-nearest neighbors (K-NNs), and artificial neural network (ANN) have been proposed. In this study, six features were obtained based on the morphology of the P-Wave, the QRS complex and the heart rate variability (HRV) of the ECG. The performance of this methodology was validated using clinical ECG signals from the Physionet arrhythmia database MIT-BIH. A feedforward neural network was used to detect the presence of PAF reaching a general accuracy of 97.4%. The results obtained show that the inclusion of the information of the P-Wave, HRV and QR Electrical alternans increases the accuracy to identify the PAF event compared to other works that use the information of only one or at most two of them.

Autonomic modulation before and after paroxysmal atrial fibrillation events in patients with ischemic heart disease.

The autonomic activity plays a critical role in generating paroxysmal atrial fibrillation (PAF). This study aimed to evaluate the changes in the autonomic nerve activity before and after PAF events in patients with and without ischemic heart disease (IHD). The study included 49 patients (71.43±12.24years old, 26 males) with PAF events lasting more than 30s during 24-hr ambulatory Holter monitoring. The 20-min intervals before and after PAF events were divided into eight segments of 5min each. Heart rate variability (HRV) analyses of the time and frequency domains were applied to each time segment. Patients with IHD had significant increases in the root mean square successive differences (r-MSSD, p=.008) and HF component (p=.04), followed by a significant increase in the LF/HF ratio (p=.02) preceding the onset of PAF. Patients without IHD had only a significant increase in the r-MSSD (p=.045) preceding the onset of PAF. During the termination of PAF events, patients in both the IHD and control groups had a significantly decreased r-MSSD and HF, respectively. Ischemic heart disease causes a sympathovagal imbalance in the initiation of PAF. Decreased parasympathetic activity regulated the termination of PAF in both the IHD and control groups. The modification of the autonomic nervous system (ANS) activity should be individualized due to the autonomic complexity in AF arrhythmogenesis and termination.

An efficient approach for Paroxysmal Atrial Fibrillation events prediction using Extreme Learning Machine

Paroxysmal Atrial Fibrillation (PAF) is a special class of Atrial Fibrillation. Predicting PAF events from electrocardiogram (ECG) signal streams plays a vital role in generating real-time alerts for cardiac disorders. These alerts are extremely important to cardiologists in taking precautions to prevent their patients from having a stroke. In this study, an effective predictive approach to PAF events using the Extreme Learning Machine classification technique is proposed. Besides, we propose a feature extraction method that integrates new ECG signal features to its time-domain ones. The new features are based on the construction of sparse vectors for peaks in ECG signals that provide high overlap between similar ECGs. The proposed prediction approach with the new ECG features representation were evaluated on a real PAF dataset using the five-fold cross-validation method. Experiments show promising results for predicting PAF in terms of accuracy and execution time compared to other existing studies. The proposed approach achieved classification accuracy of 97% for non-streaming ECG signals mode and 94.4% for streaming mode.

Prediction of PAF Attacks using Time-Domain Measures of Heart Rate Variability

Paroxysmal atrial fibrillation (PAF) is the mainly encountered type of arrhythmia and there is no validated method to predict a PAF attack before it occurs. In this study, predicting the PAF event was aimed using time-domain heart rate variability (HRV) measures in k- nearest neighbor (k-nn) classifier. Traditional time-domain HRV measures were analyzed in every 5-minute segments from 49 normal subjects, 25 patients with PAF attack and 25 patients with no attack within 45 minutes. All features were investigated whether they showed statistically significance. Significant features were classified by k-nn for odd numbers of neighbors between 1 and 19. This setup was run with two different configurations as study 1 to discriminate patients with PAF attack from normals and patients with no attack, and study 2 to discriminate patients with PAF attack from patients with no attack. SDNN, RMSSD and pNN50 measures were found to show statistically significant differences with p less than 0.05 in segments of 0-5 min, 2.5-7.5 min and 5-10 min intervals only. The maximum classification accuracy was obtained in the time interval of 2.5-7.5 minutes with %79 for Study 1 and just before attack with %80 for Study 2 in the time interval of 0-5 minutes. Results showed that the prediction of PAF events was possible when the classification between normal subjects from PAF patients was accurate. PAF attack can be determined 2.5 minutes earlier by simple classifier algorithms.

Paroxysmal atrial fibrillation detection in patients with acute ischemic stroke through prolonged Holter: prospective study.

The detection of paroxysmal atrial fibrillation (PAF) is crucial in the etiological study of an acute ischemic stroke (AIS), although this type of arrhythmia is often under-diagnosed. This prospective study aims to (1) evaluate the new-onset PAF detection rate among elderly patients with AIS in an acute setting, and (2) to assess the applicability of the STAF score (Score for the Targeting of Atrial Fibrillation) for such patients. An observational and prospective study was performed over a period of 11months. Patients with acute ischemic stroke who had been admitted to the stroke unit were included. Exclusion criteria included prior AF, AF readings on ECG during admission, or stroke mimic. The patients were monitored with a bedside ECG monitor throughout the first 48h, then simultaneously with an extended Holter recorder for a maximum of 6days. The occurrence and duration of PAF events was evaluated. The STAF risk score for PAF was calculated and compared to the detection rate of PAF for each patient. The sample population consisted of 67 patients, whose median age was 76years (IQR 71-84) and who were 57% males. The median duration of Holter recording was 3.5days per patient (IQR 2-5). We detected new PAF cases in 16% of patients, and a total of 31% had supraventricular arrhythmia episodes lasting 10s or longer. Among the patients in which this arrhythmia was detected, 10% had it detected by the bedside ECG monitor in the first 48h. The median risk score was 5 (IQR 4-6). There was no association between the risk score used and PAF. In elderly patients with AIS, the use of an extended Holter recorder led to the detection of more cases of PAF, offering them the chance to initiate hypocoagulant therapy. Among this population, the STAF score was non-discriminative and did not prove useful in predicting PAF.

Early prediction of paroxysmal atrial fibrillation based on short-term heart rate variability

Atrial fibrillation (AF) is the most common arrhythmia type and its early stage is paroxysmal atrial fibrillation (PAF). PAF affects negatively the quality of life by causing dyspnea, chest pain, feeling of excessive fatigue, and dizziness. In this study, our aim is to predict the onset of paroxysmal atrial fibrillation (PAF) events so that patients can take precautions to prevent PAF events. We use an open data from Physionet, Atrial Fibrillation Prediction Database. We construct our approach based on the heart rate variability (HRV) analysis. Short-term HRV analysis requires 5-minute data so that each dataset was divided into 5-minute data segments. HRV features for each segment are calculated from time-domain measures and frequency-domain measures using power spectral density estimations of fast Fourier transform, Lomb–Scargle, and wavelet transform methods. Different combinations of these HRV features are selected by Genetic Algorithm and then applied to k-nearest neighbors classification algorithm. We compute the classifier performances by the 10-fold cross-validation method. The proposed approach results in 92% sensitivity, 88% specificity and 90% accuracy in the 2.5–7.5 min time interval priors to PAF event. The proposed method results in better classification performance than the similar studies in literature. Comparing the existing studies, we propose that our approach provide better tool to predict PAF events.

Paroxysmal atrial fibrillation prediction based on HRV analysis and non-dominated sorting genetic algorithm III

This paper presents a method that able to predict the paroxysmal atrial fibrillation (PAF). The method uses shorter heart rate variability (HRV) signals when compared to existing methods, and achieves good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to electrically stabilize and prevent the onset of atrial arrhythmias with different pacing techniques. We propose a multi-objective optimization algorithm based on the non-dominated sorting genetic algorithm III for optimizing the baseline PAF prediction system, that consists of the stages of pre-processing, HRV feature extraction, and support vector machine (SVM) model. The pre-processing stage comprises of heart rate correction, interpolation, and signal detrending. After that, time-domain, frequency-domain, non-linear HRV features are extracted from the pre-processed data in feature extraction stage. Then, these features are used as input to the SVM for predicting the PAF event. The proposed optimization algorithm is used to optimize the parameters and settings of various HRV feature extraction algorithms, select the best feature subsets, and tune the SVM parameters simultaneously for maximum prediction performance. The proposed method achieves an accuracy rate of 87.7%, which significantly outperforms most of the previous works. This accuracy rate is achieved even with the HRV signal length being reduced from the typical 30 min to just 5 min (a reduction of 83%). Furthermore, another significant result is the sensitivity rate, which is considered more important that other performance metrics in this paper, can be improved with the trade-off of lower specificity.

ANN-based Classifier for PAF Prediction

paper we propose an artificial neural network as a based classifier for prediction of Paroxysmal Atrial Fibrillation (PAF). PAF is a really life threatening disease and it is the result of irregular and repeated depolarization of the atria. We used PAF prediction data base which include 30-min. period of 100 ECG recorded signals. We divide the 30-min preceding the PAF into 6 periods with 5-min each. In each suggested period we get the classification result using ANN. The results show that we can predict the PAF accurately in 5-min & 20-min prior the PAF. In these two periods, the measured sensitivity, specificity, positive predictivity and accuracy show better and significant results comparable to the other periods. Also the results outperform the obtained results in the same field in the literature. 1. INRODUCTION Classification of ECG signal is an important area in biomedical signal processing. Paroxysmal atrial fibrillation (PAF) of the heart muscle is defined as short duration episodes of AF lasting from 2min. to less than 7 days, while chronic AF is defined as lasting more than 7 days. The main reason for this is not the immediate effect of the onset of atrial fibrillation over the patient's health (AF detection) but the long-term effects: increase in heart muscle fatigue, increase in thromboembolic and stroke events due to the formation of blood clots and an irregular onset that makes it hard to detect on normal ECG tests. Thus it is necessary for cardiologists to benefit from a robust and precise tool that could predict the onset of such events, in order to prevent them by defibrillation, drug treatment and anti- tachycardia pacing techniques. Chronic AF is usually preceded by (PAF). Therefore, in addition to use anti-arrhythmic drugs, the physicians are trying to develop pacing devices in order to surpass the onset of AF. The automated method to predict the onset PAF is interesting topic to help treating this problem. During recent years several researchers proposed many techniques to predict the onset of PAF. Useful reviews describing different techniques for PAF or chronic AF prediction, from technical to clinical points of view (1-4). The Computers in Cardiology Challenge 2001 revealed a maximum obtained accuracy of about 80% (5-7). Hariton, et al., (8) proposed a new method for PAF automatic prediction based on heart rate variability (HRV) metrics and morphologic variability (MV), and (HRV+MV) decision rule, the obtained specificity and sensitivity are between (83.93%- 89.29%), (84.51%-89,44%) respectively. Artificial neural network (ANN) in recent years has proved to be an advanced tool in solving classification (9-11), wavelets proved usefulness in feature extraction from non-stationary signal like ECG (12-13). In general, these above prediction models are able to detect the transition to PAF events with accuracies of 70-90%, by means of records of at least tens of minutes and rather complex analysis procedures. In the present work, two set of features are extracted: Feature set-1 (FS-1), directly from ECG signal and feature set-2 (FS-2) with the aid of continuous wavelet transform(CWT), which converts the time domain signal to time-frequency domain where several features can be carefully extracted, the extracted features are then applied to ANN to classify the normal object from that one who suffers from PAF.

Atrial fibrillation: a spectrum of risk with a uniform treatment effect of novel anticoagulants?

This editorial refers to ‘Outcomes of apixaban vs. warfarin by type and duration of atrial fibrillation: results from the ARISTOTLE trial,’ by S. Al-Khatib et al. , doi:10.1093/eurheartj/eht135 The last several years have seen the completion of five pivotal outcomes trials evaluating three novel oral anticoagulants (NOACs) in > 55 000 patients with atrial fibrillation (AF) from around the world.1–5 Each of these studies has shown that the respective new agent is at least as efficacious as, if not superior to, warfarin in reducing stroke or non-central nervous system embolism; all three NOACs were shown to be superior to warfarin in reducing intracranial haemorrhage. The large, diverse populations enrolled across broad geographic regions and practice settings provide an opportunity to explore questions about the specific cohorts of patients with AF of clinical interest, the natural history of the disease, and the pragmatic challenges physicians confront each day in clinical practice. The analyses from the ARISTOTLE study database by Al-Khatib and colleagues6 provide important information about outcomes in groups with different subtypes of AF and about treatment effects with apixaban compared with placebo in the same subtypes. We agree with the authors' two primary conclusions: (i) patients with persistent or permanent AF have higher event rates (including rates of systemic embolus and bleeding complications) compared with patients with paroxysmal AF events after adjusting for baseline differences; and (ii) the effects of apixaban compared with warfarin in patients defined by AF subtype are consistent …

Detection of Paroxysmal Atrial Fibrillation by 30-Day Event Monitoring in Cryptogenic Ischemic Stroke

Patients with cryptogenic ischemic stroke may have undetected paroxysmal atrial fibrillation (PAF). We established the Stroke and Monitoring for PAF in Real Time (SMART) Registry to determine the yield of 30-day outpatient PAF monitoring in cryptogenic ischemic stroke. The SMART Registry was a 3-year, prospective multicenter registry of 239 patients with cryptogenic ischemic stroke undergoing 30-day outpatient autotriggered PAF detection in Kaiser Permanente Northern California. In intention-to-monitor analysis, PAF was detected in 29 of 239 patients (12.1%; 95% CI, 8.6%-16.9%). After retrospective chart review was performed, a new diagnosis of PAF was confirmed in 26 of 236 patients (11.0%; 95% CI, 7.6%-15.7%). The majority of detected PAF events were asymptomatic; only 6 of 98 recorded PAF events (6.1%) were patient-triggered or associated with symptoms. -Approximately 1 in every 9 patients with cryptogenic ischemic stroke was found to have new PAF within 30 days. Routine monitoring in this population should be strongly considered.

Prediction of paroxysmal atrial fibrillation using recurrence plot-based features of the RR-interval signal

Atrial fibrillation (AF) is the most common cardiac arrhythmia and increases the risk of stroke. Predicting the onset of paroxysmal AF (PAF), based on noninvasive techniques, is clinically important and can be invaluable in order to avoid useless therapeutic intervention and to minimize risks for the patients. In this paper, we propose an effective PAF predictor which is based on the analysis of the RR-interval signal. This method consists of three steps: preprocessing, feature extraction and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the RR-interval signal is extracted. In the next step, the recurrence plot (RP) of the RR-interval signal is obtained and five statistically significant features are extracted to characterize the basic patterns of the RP. These features consist of the recurrence rate, length of longest diagonal segments (Lmax ), average length of the diagonal lines (Lmean), entropy, and trapping time. Recurrence quantification analysis can reveal subtle aspects of dynamics not easily appreciated by other methods and exhibits characteristic patterns which are caused by the typical dynamical behavior. In the final step, a support vector machine (SVM)-based classifier is used for PAF prediction. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database (AFPDB) which consists of both 30 min ECG recordings that end just prior to the onset of PAF and segments at least 45 min distant from any PAF events. The obtained sensitivity, specificity, positive predictivity and negative predictivity were 97%, 100%, 100%, and 96%, respectively. The proposed methodology presents better results than other existing approaches.

Structures of the recurrence plot of heart rate variability signal as a tool for predicting the onset of paroxysmal atrial fibrillation

This paper aims to propose an effective paroxysmal atrial fibrillation (PAF) predictor which is based on the analysis of the heart rate variability (HRV) signal. Predicting the onset of PAF, based on non-invasive techniques, is clinically important and can be invaluable in order to avoid useless therapeutic interventions and to minimize the risks for the patients. This method consists of four steps: Preprocessing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In the next step, the recurrence plot (RP) of HRV signal is obtained and six features are extracted to characterize the basic patterns of the RP. These features consist of length of longest diagonal segments, average length of the diagonal lines, entropy, trapping time, length of longest vertical line, and recurrence trend. In the third step, these features are reduced to three features by the linear discriminant analysis (LDA) technique. Using LDA not only reduces the number of the input features, but also increases the classification accuracy by selecting the most discriminating features. Finally, a support vector machine-based classifier is used to classify the HRV signals. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database which consists of both 30-minutes ECG recordings end just prior to the onset of PAF and segments at least 45 min distant from any PAF events. The obtained sensitivity, specificity, and positive predictivity were 96.55%, 100%, and 100%, respectively.

Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal

In this paper, an effective paroxysmal atrial fibrillation (PAF) prediction algorithm is presented, which is based on analysis of the heart rate variability (HRV) signal. The proposed method consists of a preprocessing step for QRS detection and HRV signal extraction. In the next step, several features which can be used as markers for the prediction of PAF are extracted from the HRV signal. These features consist of spectrum features, bispectrum features, and non-linear features including sample entropy and Poincaré plot-extracted features. The spectrum features are able to discriminate the sympathetic and parasympathetic contents of the HRV signal, which are affected before PAF attacks. The bispectrum features are used in order to reveal information not presented on the spectral domain, and to detect quadratic phase coupled harmonics arising from non-linearities of the HRV signal. Moreover, the non-linear analysis can map the heart rate irregularities in the feature space and it leads to better understanding of the system dynamics before PAF attacks. In the final step, a support vector machine (SVM)-based classifier has been used for PAF prediction. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database (AFPDB). The obtained sensitivity, specificity, and positive predictivity were 96.30%, 93.10%, and 92.86%, respectively. The proposed methodology presents better results than the other existing approaches. The other important advantage of the proposed method when compared to the other approaches is that we do not need the both records of a subject to specify which episode preceding PAF events.

Intrinsic Cardiac Nerve Activity and Paroxysmal Atrial Tachyarrhythmia in Ambulatory Dogs

Little is known about the relationship between intrinsic cardiac nerve activity (ICNA) and spontaneous arrhythmias in ambulatory animals. We implanted radiotransmitters to record extrinsic cardiac nerve activity (ECNA; including stellate ganglion nerve activity and vagal nerve activity) and ICNA (including superior left ganglionated plexi nerve activity and ligament of Marshall nerve activity) in 6 ambulatory dogs. Intermittent rapid left atrial pacing was performed to induce paroxysmal atrial fibrillation or atrial tachycardia. The vast majority (94%) of ligament of Marshall nerve activity were preceded by or coactivated with ECNA (stellate ganglion nerve activity or vagal nerve activity), whereas 6% of episodes were activated alone without concomitant stellate ganglion nerve activity or vagal nerve activity. Paroxysmal atrial fibrillation and atrial tachycardia were invariably (100%) preceded (<5 seconds) by ICNA. Most paroxysmal atrial tachycardia events (89%) were preceded by ICNA and sympathovagal coactivation, whereas 11% were preceded by ICNA and stellate ganglion nerve activity-only activation. Most paroxysmal atrial fibrillation events were preceded only by ICNA (72%); the remaining 28% were preceded by ECNA and ICNA together. Complex fractionated atrial electrograms were observed during ICNA discharges that preceded the onset of paroxysmal atrial tachycardia and atrial fibrillation. Immunostaining confirmed the presence of both adrenergic and cholinergic nerve at ICNA sites. There is a significant temporal relationship between ECNA and ICNA. However, ICNA can also activate alone. All paroxysmal atrial tachycardia and atrial fibrillation episodes were invariably preceded by ICNA. These findings suggest that ICNA (either alone or in collaboration with ECNA) is an invariable trigger of paroxysmal atrial tachyarrhythmias. ICNA might contaminate local atrial electrograms, resulting in complex fractionated atrial electrogram-like activity.

Complexity and spectral analysis of the heart rate variability dynamics for distant prediction of paroxysmal atrial fibrillation with artificial intelligence methods

Paroxysmal atrial fibrillation (PAF) is a serious arrhythmia associated with morbidity and mortality. We explore the possibility of distant prediction of PAF by analyzing changes in heart rate variability (HRV) dynamics of non-PAF rhythms immediately before PAF event. We use that model for distant prognosis of PAF onset with artificial intelligence methods. We analyzed 30-min non-PAF HRV records from 51 subjects immediately before PAF onset and at least 45min distant from any PAF event. We used spectral and complexity analysis with sample (SmEn) and approximate (ApEn) entropies and their multiscale versions on extracted HRV data. We used that features to train the artificial neural networks (ANNs) and support vector machine (SVM) classifiers to differentiate the subjects. The trained classifiers were further tested for distant PAF event prognosis on 16 subjects from independent database on non-PAF rhythm lasting from 60 to 320 min before PAF onset classifying the 30-min segments as distant or leading to PAF. We found statistically significant increase in 30-min non-PAF HRV recordings from 51 subjects in the VLF, LF, HF bands and total power (p<0.0001) before PAF event compared to PAF distant ones. The SmEn and ApEn analysis provided significant decrease in complexity (p<0.0001 and p<0.001) before PAF onset. For training ANN and SVM classifiers the data from 51 subjects were randomly split to training, validation and testing. ANN provided better results in terms of sensitivity (Se), specificity (Sp) and positive predictivity (Pp) compared to SVM which became biased towards positive case. The validation results of the ANN classifier we achieved: Se 76%, Sp 93%, Pp 94%. Testing ANN and SVM classifiers on 16 subjects with non-PAF HRV data preceding PAF events we obtained distant prediction of PAF onset with SVM classifier in 10 subjects (58+/-18 min in advance). ANN classifier provided distant prediction of PAF event in 13 subjects (62+/-21 min in advance). From the results of distant PAF prediction we conclude that ANN and SVM classifiers learned the changes in the HRV dynamics immediately before PAF event and successfully identified them during distant PAF prognosis on independent database. This confirms the reported in the literature results that corresponding changes in the HRV data occur about 60 min before PAF onset and proves the possibility of distant PAF prediction with ANN and SVM methods.