Paroxysmal atrial fibrillation prediction method with shorter HRV sequences

Clinical applicability of an artificial intelligence prediction algorithm for early prediction of non-persistent atrial fibrillation

Background and aims

It is difficult to document atrial fibrillation (AF) on ECG in patients with non-persistent atrial fibrillation (non-PeAF). There is limited understanding of whether an AI prediction algorithm could predict the occurrence of non-PeAF from the information of normal sinus rhythm (SR) of a 12-lead ECG. This study aimed to derive a precise predictive AI model for screening non-PeAF using SR ECG within 4 weeks.

Methods

This retrospective cohort study included patients aged 18 to 99 with SR ECG on 12-lead standard ECG (10 seconds) in Ewha Womans University Medical Center for 3 years. Data were preprocessed into three window periods (which are defined with the duration from SR to non-PeAF detection) - 1 week, 2 weeks, and 4 weeks from the AF detection prospectively. For experiments, we adopted a Residual Neural Network model based on 1D-CNN proposed in a previous study. We used 7,595 SR ECGs (extracted from 215,875 ECGs) with window periods of 1 week, 2 weeks, and 4 weeks for analysis.

Results

The prediction algorithm showed an AUC of 0.862 and an F1-score of 0.84 in the 1:4 matched group of a 1-week window period. For the 1:4 matched group of a 2-week window period, it showed an AUC of 0.864 and an F1-score of 0.85. Finally, for the 1:4 matched group of a 4-week window period, it showed an AUC of 0.842 and an F1-score of 0.83.

Conclusion

The AI prediction algorithm showed the possibility of risk stratification for early detection of non-PeAF. Moreover, this study showed that a short window period is also sufficient to detect non-PeAF.

Pathological Heart Rate Regulation in Apparently Healthy Individuals

Cardiovascular diseases are the leading cause of morbidity and mortality in adults worldwide. There is one common pathophysiological aspect present in all cardiovascular diseases-dysfunctional heart rhythm regulation. Taking this aspect into consideration for cardiovascular risk predictions opens important research perspectives, allowing for the development of preventive treatment techniques. The aim of this study was to find out whether certain pathologically appearing signs in the heart rate variability (HRV) of an apparently healthy person, even with high HRV, can be defined as biomarkers for a disturbed cardiac regulation and whether this can be treated preventively by a drug-free method. This multi-phase study included 218 healthy subjects of either sex, who consecutively visited the physician at Gesundheit clinic because of arterial hypertension, depression, headache, psycho-emotional stress, extreme weakness, disturbed night sleep, heart palpitations, or chest pain. In study phase A, baseline measurement to identify individuals with cardiovascular risks was done. Therefore, standard HRV, as well as the new cardiorhythmogram (CRG) method, were applied to all subjects. The new CRG analysis used here is based on the recently introduced LF drops and HF counter-regulation. Regarding the mechanisms of why these appear in a steady-state cardiorhythmmogram, they represent non-linear event-based dynamical HRV biomarkers. The next phase of the study, phase B, tested whether the pathologically appearing signs identified via CRG in phase A could be clinically influenced by drug-free treatment. In order to validate the new CRG method, it was supported by non-linear HRV analysis in both phase A and in phase B. Out of 218 subjects, the pathologically appearing signs could be detected in 130 cases (60%), p < 0.01, by the new CRG method, and by the standard HRV analysis in 40 cases (18%), p < 0.05. Thus, the CRG method was able to detect 42% more cases with pathologically appearing cardiac regulation. In addition, the comparative CRG analysis before and after treatment showed that the pathologically appearing signs could be clinically influenced without the use of medication. After treatment, the risk group decreased eight-fold-from 130 people to 16 (p < 0.01). Therefore, progression of the detected pathological signs to structural cardiac pathology or arrhythmia could be prevented in most of the cases. However, in the remaining risk group of 16 apparently healthy subjects, 8 people died due to all-cause mortality. In contrast, no other subject in this study has died so far. The non-linear parameter which is able to quantify the changes in CRGs before versus after treatment is FWRENYI4 (symbolic dynamic feature); it decreased from 2.85 to 2.53 (p < 0.001). In summary, signs of pathological cardiac regulation can be identified by the CRG analysis of apparently healthy subjects in the early stages of development of cardiac pathology. Thus, our method offers a sensitive biomarker for cardiovascular risks. The latter can be influenced by non-drug treatments (acupuncture) to stop the progression into structural cardiac pathologies or arrhythmias in most but not all of the patients. Therefore, this could be a real and easy-to-use supplemental method, contributing to primary prevention in cardiology.

Atrioventricular Synchronization for Detection of Atrial Fibrillation and Flutter in One to Twelve ECG Leads Using a Dense Neural Network Classifier

This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluated on the test set. Optimal DenseNet architectures with the number of neurons in sequential [1st, 2nd, 3rd] hidden layers were assessed for sensitivity and specificity: DenseNet [16,16,0] with primary leads (I or II) had 87.9-88.3 and 90.5-91.5%; DenseNet [32,32,32] with six limb leads had 90.7 and 94.2%; DenseNet [32,32,4] with six chest leads had 92.1 and 93.2%; and DenseNet [128,8,8] with all 12 leads had 91.8 and 95.8%, indicating sensitivity and specificity values, respectively. Mean SHAP values on the entire test set highlighted the importance of RRi-mean (100%), RR-std (84%), and atrial synchronization (40-60%) for the PQa-mean (aVR, I), PQi-std (V2, aVF, II), and PQi-mean (aVL, aVR). Our focus on finding the strongest AV synchronization predictors of AF in 12-lead ECGs would lead to a comprehensive understanding of the decision-making process in advanced neural network classifiers. DenseNet self-learned to rely on a few ECG behavioral characteristics: first, characteristics usually associated with AF conduction such as rapid heart rate, enhanced heart rate variability, and large PQ-interval deviation in V2 and inferior leads (aVF, II); second, characteristics related to a typical P-wave pattern in sinus rhythm, which is best distinguished from AF by the earliest negative P-peak deflection of the right atrium in the lead (aVR) and late positive left atrial deflection in lateral leads (I, aVL). Our results on lead-selection and feature-selection practices for AF detection should be considered for one- to twelve-lead ECG signal processing settings, particularly those measuring heart rate, AV conduction times, and P-/f-wave amplitudes. Performances are limited to the AF diagnostic potential of these three metrics. SHAP value importance can be used in combination with a human expert's ECG interpretation to change the focus from a broad observation of 12-lead ECG morphology to focusing on the few AV synchronization findings strongly predictive of AF or non-AF arrhythmias. Our results are representative of AV synchronization findings across a broad taxonomy of cardiac arrhythmias in large 12-lead ECG databases.

Using Minimum Redundancy Maximum Relevance Algorithm to Select Minimal Sets of Heart Rate Variability Parameters for Atrial Fibrillation Detection

Heart rate is quite regular during sinus (normal) rhythm (SR) originating from the sinus node. In contrast, heart rate is usually irregular during atrial fibrillation (AF). Complete atrioventricular block with an escape rhythm, ventricular pacing, or ventricular tachycardia are the most common exceptions when heart rate may be regular in AF. Heart rate variability (HRV) is the variation in the duration of consecutive cardiac cycles (RR intervals). We investigated the utility of HRV parameters for automated detection of AF with machine learning (ML) classifiers. The minimum redundancy maximum relevance (MRMR) algorithm, one of the most effective algorithms for feature selection, helped select the HRV parameters (including five original), best suited for distinguishing AF from SR in a database of over 53,000 60 s separate electrocardiogram (ECG) segments cut from longer (up to 24 h) ECG recordings. HRV parameters entered the ML-based classifiers as features. Seven different, commonly used classifiers were trained with one to six HRV-based features with the highest scores resulting from the MRMR algorithm and tested using the 5-fold cross-validation and blindfold validation. The best ML classifier in the blindfold validation achieved an accuracy of 97.2% and diagnostic odds ratio of 1566. From all studied HRV features, the top three HRV parameters distinguishing AF from SR were: the percentage of successive RR intervals differing by at least 50 ms (pRR50), the ratio of standard deviations of points along and across the identity line of the Poincare plots, respectively (SD2/SD1), and coefficient of variation—standard deviation of RR intervals divided by their mean duration (CV). The proposed methodology and the presented results of the selection of HRV parameters have the potential to develop practical solutions and devices for automatic AF detection with minimal sets of simple HRV parameters. Using straightforward ML classifiers and the extremely small sets of simple HRV features, always with pRR50 included, the differentiation of AF from sinus rhythms in the 60 s ECGs is very effective.

Perspectives on Sex- and Gender-Specific Prediction of New-Onset Atrial Fibrillation by Leveraging Big Data

Atrial fibrillation (AF), the most common sustained cardiac arrhythmia, has a large impact on quality of life and is associated with increased risk of hospitalization, morbidity, and mortality. Over the past two decades advances regarding the clinical epidemiology and management of AF have been established. Moreover, sex differences in the prevalence, incidence, prediction, pathophysiology, and prognosis of AF have been identified. Nevertheless, AF remains to be a complex and heterogeneous disorder and a comprehensive sex- and gender-specific approach to predict new-onset AF is lacking. The exponential growth in various sources of big data such as electrocardiograms, electronic health records, and wearable devices, carries the potential to improve AF risk prediction. Leveraging these big data sources by artificial intelligence (AI)-enabled approaches, in particular in a sex- and gender-specific manner, could lead to substantial advancements in AF prediction and ultimately prevention. We highlight the current status, premise, and potential of big data to improve sex- and gender-specific prediction of new-onset AF.

A Heart Rate Variability-Based Paroxysmal Atrial Fibrillation Prediction System

Atrial fibrillation (AF) is characterized by totally disorganized atrial depolarizations without effective atrial contraction. It is the most common form of cardiac arrhythmia, affecting more than 46.3 million people worldwide and its incidence rate remains increasing. Although AF itself is not life-threatening, its complications, such as strokes and heart failure, are lethal. About 25% of paroxysmal AF (PAF) patients become chronic for an observation period of more than one year. For long-term and real-time monitoring, a PAF prediction system was developed with four objectives: (1) high prediction accuracy, (2) fast computation, (3) small data storage, and (4) easy medical interpretations. The system takes a 400-point heart rate variability (HRV) sequence containing no AF episodes as the input and outputs whether the corresponding subject will experience AF episodes in the near future (i.e., 30 min). It first converts an input HRV sequence into four image matrices via extended Poincaré plots to capture inter- and intra-person features. Then, the system employs a convolutional neural network (CNN) to perform feature selection and classification based on the input image matrices. Some design issues of the system, including feature conversion and classifier structure, were formulated as a binary optimization problem, which was then solved via a genetic algorithm (GA). A numerical study involving 6085 400-point HRV sequences excerpted from three PhysioNet databases showed that the developed PAF prediction system achieved 87.9% and 87.2% accuracy on the validation and the testing datasets, respectively. The performance is competitive with that of the leading PAF prediction system in the literature, yet our system is much faster and more intensively tested. Furthermore, from the designed inter-person features, we found that PAF patients often possess lower (~60 beats/min) or higher (~100 beats/min) heart rates than non-PAF subjects. On the other hand, from the intra-person features, we observed that PAF patients often exhibit smaller variations (≤5 beats/min) in heart rate than non-PAF subjects, but they may experience short bursts of large heart rate changes sometimes, probably due to abnormal beats, such as premature atrial beats. The other findings warrant further investigations for their medical implications about the onset of PAF.

Advances in Cardiac Pacing: Arrhythmia Prediction, Prevention and Control Strategies

Cardiac arrhythmias constitute a tremendous burden on healthcare and are the leading cause of mortality worldwide. An alarming number of people have been reported to manifest sudden cardiac death as the first symptom of cardiac arrhythmias, accounting for about 20% of all deaths annually. Furthermore, patients prone to atrial tachyarrhythmias such as atrial flutter and fibrillation often have associated comorbidities including hypertension, ischemic heart disease, valvular cardiomyopathy and increased risk of stroke. Technological advances in electrical stimulation and sensing modalities have led to the proliferation of medical devices including pacemakers and implantable defibrillators, aiming to restore normal cardiac rhythm. However, given the complex spatiotemporal dynamics and non-linearity of the human heart, predicting the onset of arrhythmias and preventing the transition from steady state to unstable rhythms has been an extremely challenging task. Defibrillatory shocks still remain the primary clinical intervention for lethal ventricular arrhythmias, yet patients with implantable cardioverter defibrillators often suffer from inappropriate shocks due to false positives and reduced quality of life. Here, we aim to present a comprehensive review of the current advances in cardiac arrhythmia prediction, prevention and control strategies. We provide an overview of traditional clinical arrhythmia management methods and describe promising potential pacing techniques for predicting the onset of abnormal rhythms and effectively suppressing cardiac arrhythmias. We also offer a clinical perspective on bridging the gap between basic and clinical science that would aid in the assimilation of promising anti-arrhythmic pacing strategies.

Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis

Atrial fibrillation (AF) is the most clinically diagnosed arrhythmia, as its prevalence increases with age, and its initial stage is paroxysmal atrial fibrillation (PAF). This pathology usually triggers hemodynamic disorders that can generate cerebrovascular accidents (CVA), causing morbidity and even death. The aim of this study is to predict the occurrence of PAF episodes in order to take precautions to prevent PAF episodes. The PhysioNet AFPDB prediction database was used to extract 77 heart rate variability (HRV) features using time domain, geometrical analysis, Poincaré plot, nonlinear analysis, detrended fluctuation analysis, autoregressive modeling, fast Fourier transform (FFT), Lomb-Scargle periodogram, wavelet packet transform (WPT) and bispectrum measurements. The number of features was reduced using the near-zero value, correlation, and recursive feature elimination (RFE) methods for time windows of 1, 2, 5, 10, and 30 min. Feature selection was performed using backwards selection, genetic algorithm, analysis of variance (ANOVA), and non-dominated sorting genetic algorithm (NSGA-III) methods, and then random forest, conditional random forest, k-nearest neighbor (KNN), and support vector machine (SVM) classification algorithms were applied and evaluated using 10-fold cross-validation. The proposed method achieved a precision of 93.24% with a 5-minute window and 89.21% with a 2-minute window, improving performance in predicting PAF when compared with similar studies in the literature.

Convolutional neural networks predict the onset of paroxysmal atrial fibrillation: Theory and applications

In this study, we aimed to detect paroxysmal atrial fibrillation episodes before they occur so that patients can take precautions before putting their and others' lives in potentially life-threatening danger. We used the atrial fibrillation prediction database, open data from PhysioNet, and assembled our process based on convolutional neural networks. Conventional heart rate variability features are calculated from time-domain measures, frequency-domain measures using power spectral density estimations, time-frequency-domain measures using wavelet transform, and nonlinear Poincaré plot measures. In addition, we also applied an alternative heart rate normalization, which gave promising results only in a few studies, before calculating these heart rate variability features. We used these features directly and their normalized versions using min-max normalization and z-score normalization methods. Thus, heart rate variability features extracted from six different combinations of these normalizations, in addition to no normalization cases, were applied to the convolutional neural network classifier. We tuned the classifiers' hyperparameters using 90% of feature sets and tested the classifiers' performances using 10% of feature sets. The proposed approach resulted in 87.76% accuracy, 91.30% precision, 80.04% recall, and 87.50% f1-score in heart rate variability with z-score feature normalization. When the heart rate normalization was also utilized, the suggested method gave 100% accuracy, 100% precision, 100% recall, and 100% f1-score in heart rate variability with z-score feature normalization. The proposed method with heart rate normalization and z-score normalization methods resulted in better classification performance than similar studies in the literature. By comparing the existing studies, we conclude that our approach provides a much better tool to determine a near-future paroxysmal atrial fibrillation episode. However, although the achieved benchmarks are impressive, we note that the approach needs to be supported by other studies and on other datasets before clinical trials.

Paroxysmal atrial fibrillation prediction based on morphological variant P-wave analysis with wideband ECG and deep learning

BACKGROUND AND OBJECTIVE

Atrial fibrillation (AF) is one of the most frequent asymptomatic arrhythmias associated with significant morbidity and mortality. Identifying the susceptibility to AF based on routine or continuous ECG recording is of considerable interest. Despite several P-wave characteristics and skin sympathetic nerve activity (SKNA) linked to AF onset, neither factor has offered accurate predictability. We propose a deep learning enabled method for AF risk prediction.

METHODS

We develop a novel MVPNet to predict the upcoming onset of paroxysmal AF. MVPNet combines wavelet-based feature extraction and a deep learning classifier. MVPNet detect the approaching of AF onset by analyzing the template and frequency in P-wave segments. The morphological variant P-wave (MVP) analysis includes P-wave and SKNA features cross temporal-spectral domain. Subsequently, we designed an optimized lightweight convolutional neural network model to detect the MVP features of pre-AF episodes during sinus rhythm segments. Wideband ECG data obtained through the neuECG protocol from eight PAF patients with 177 times AF occurrence in this study. We compared the accuracy of AF prediction between ordinary ECG and neuECG.

RESULTS

The MVPNet effectively predicted the onset of AF episodes. 89% of ECG recorded at 5 min before the AF onset can be identified using neuECG. The proposed deep learning model, MVPNet, obtained a better precision and inference speed with less computing resources than existing models. The gradient activation map showed that neuECG recording may be a superior AF risk predictor.

CONCLUSIONS

MVP analysis combined SKNA and P-wave parameters to improve predictive accuracy. The proposed MVPNet based on neuECG is superior to existing AF risk assessment with improved reliability and effectiveness. The method can be potentially applied in clinical scenarios for real-time, continuous AF prediction.

Review of Deep Learning-Based Atrial Fibrillation Detection Studies

Atrial fibrillation (AF) is a common arrhythmia that can lead to stroke, heart failure, and premature death. Manual screening of AF on electrocardiography (ECG) is time-consuming and prone to errors. To overcome these limitations, computer-aided diagnosis systems are developed using artificial intelligence techniques for automated detection of AF. Various machine learning and deep learning (DL) techniques have been developed for the automated detection of AF. In this review, we focused on the automated AF detection models developed using DL techniques. Twenty-four relevant articles published in international journals were reviewed. DL models based on deep neural network, convolutional neural network (CNN), recurrent neural network, long short-term memory, and hybrid structures were discussed. Our analysis showed that the majority of the studies used CNN models, which yielded the highest detection performance using ECG and heart rate variability signals. Details of the ECG databases used in the studies, performance metrics of the various models deployed, associated advantages and limitations, as well as proposed future work were summarized and discussed. This review paper serves as a useful resource for the researchers interested in developing innovative computer-assisted ECG-based DL approaches for AF detection.

Effects of transcutaneous auricular vagus nerve stimulation on cardiovascular autonomic control in health and disease

Autonomic nervous system (ANS) dysfunction is a well-known feature of cardiovascular diseases (CVDs). Studies on heart rate variability (HRV), a non-invasive method useful in investigating the status of cardiovascular autonomic control, have shown that a predominance of sympathetic modulation not only contributes to the progression of CVDs but has a pivotal role in their onset. Current therapies focus more on inhibition of sympathetic activity, but the presence of drug-resistant conditions and the invasiveness of some surgical procedures are an obstacle to complete therapeutic success. On the other hand, targeting the parasympathetic branch of the autonomic nervous system through invasive vagus nerve stimulation (VNS) has shown interesting results as alternative therapeutic approach for CVDs. However, the invasiveness and cost of the surgical procedure limit the clinical applicability of VNS and hinder the research on the physiological pathway involved. Transcutaneous stimulation of the auricular branch of the vagus nerve (tVNS) seems to represent an important non-invasive alternative with effects comparable to those of VNS with surgical implant. Thus, in the present narrative review, we illustrate the main studies on tVNS performed in healthy subjects and in three key examples of CVDs, namely heart failure, hypertension and atrial fibrillation, highlighting the neuromodulatory effects of this technique.

Atrial Fibrillation Prediction from Critically Ill Sepsis Patients

Sepsis is defined by life-threatening organ dysfunction during infection and is the leading cause of death in hospitals. During sepsis, there is a high risk that new onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. Consequently, early prediction of AF during sepsis would allow testing of interventions in the intensive care unit (ICU) to prevent AF and its severe complications. In this paper, we present a novel automated AF prediction algorithm for critically ill sepsis patients using electrocardiogram (ECG) signals. From the heart rate signal collected from 5-min ECG, feature extraction is performed using the traditional time, frequency, and nonlinear domain methods. Moreover, variable frequency complex demodulation and tunable Q-factor wavelet-transform-based time-frequency methods are applied to extract novel features from the heart rate signal. Using a selected feature subset, several machine learning classifiers, including support vector machine (SVM) and random forest (RF), were trained using only the 2001 Computers in Cardiology data set. For testing the proposed method, 50 critically ill ICU subjects from the Medical Information Mart for Intensive Care (MIMIC) III database were used in this study. Using distinct and independent testing data from MIMIC III, the SVM achieved 80% sensitivity, 100% specificity, 90% accuracy, 100% positive predictive value, and 83.33% negative predictive value for predicting AF immediately prior to the onset of AF, while the RF achieved 88% AF prediction accuracy. When we analyzed how much in advance we can predict AF events in critically ill sepsis patients, the algorithm achieved 80% accuracy for predicting AF events 10 min early. Our algorithm outperformed a state-of-the-art method for predicting AF in ICU patients, further demonstrating the efficacy of our proposed method. The annotations of patients' AF transition information will be made publicly available for other investigators. Our algorithm to predict AF onset is applicable for any ECG modality including patch electrodes and wearables, including Holter, loop recorder, and implantable devices.

A Classification and Prediction Hybrid Model Construction with the IQPSO-SVM Algorithm for Atrial Fibrillation Arrhythmia

Atrial fibrillation (AF) is the most common cardiovascular disease (CVD), and most existing algorithms are usually designed for the diagnosis (i.e., feature classification) or prediction of AF. Artificial intelligence (AI) algorithms integrate the diagnosis of AF electrocardiogram (ECG) and predict the possibility that AF will occur in the future. In this paper, we utilized the MIT-BIH AF Database (AFDB), which is composed of data from normal people and patients with AF and onset characteristics, and the AFPDB database (i.e., PAF Prediction Challenge Database), which consists of data from patients with Paroxysmal AF (PAF; the records contain the ECG preceding an episode of PAF), and subjects who do not have documented AF. We extracted the respective characteristics of the databases and used them in modeling diagnosis and prediction. In the aspect of model construction, we regarded diagnosis and prediction as two classification problems, adopted the traditional support vector machine (SVM) algorithm, and combined them. The improved quantum particle swarm optimization support vector machine (IQPSO-SVM) algorithm was used to speed the training time. During the verification process, the clinical FZU-FPH database created by Fuzhou University and Fujian Provincial Hospital was used for hybrid model testing. The data were obtained from the Holter monitor of the hospital and encrypted. We proposed an algorithm for transforming the PDF ECG waveform images of hospital examination reports into digital data. For the diagnosis model and prediction model trained using the training set of the AFDB and AFPDB databases, the sensitivity, specificity, and accuracy measures were 99.2% and 99.2%, 99.2% and 93.3%, and 91.7% and 92.5% for the test set of the AFDB and AFPDB databases, respectively. Moreover, the sensitivity, specificity, and accuracy were 94.2%, 79.7%, and 87.0%, respectively, when tested using the FZU-FPH database with 138 samples of the ECG composed of two labels. The composite classification and prediction model using a new water-fall ensemble method had a total accuracy of approximately 91% for the test set of the FZU-FPH database with 80 samples with 120 segments of ECG with three labels.

AF episodes recognition using optimized time-frequency features and cost-sensitive SVM

Although atrial fibrillation (AF) Arrhythmia is highly prevalent within a wide range of populations with major associated risks and due to its episodic occurrence, its recognition remains a challenge for doctors. This paper aims to present and experimentally validate a new efficient approach for the detection and classification of this cardiac anomaly using multiple Electrocardiogram (ECG) signals. This work consists of applying Stockwell transform (ST) with compact support kernel (ST-CSK) for ECG time-frequency analysis. The estimation of the atrial activity (AA) is then achieved after analyzing P-waves of the ECG signals for each heartbeat. ECG signals segmentation allows characterizing the AA by making use of its (t, f) flatness, (t, f) flux, energy concentration and heart rate variability. The features matrix is employed as an input of the support vector machines (SVM) working in binary and asymmetrical mode with an embedded reject option. The proposed algorithm is trained and then tested using different ECG sources namely two databases provided by PhysionNet (MIT-BIH Arrhythmia, MIT-BIH Atrial Fibrillation) and recorded ECG signals using MySignals HW development platform with raspberry Pi 3 model B[Formula: see text]. The used method has achieved [Formula: see text] and [Formula: see text] as sensitivity and specificity, respectively. The obtained results confirm that the proposed approach represents a promising tool for Atrial Fibrillation Episodes (AFE) recognition with significant separability between Normal atrial activity and atrial activity with AF even under real and clinical conditions.

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centred on applying ML for dvsetecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modelling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centred in aims, such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g. blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.

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.

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.

Asymmetry of lagged Poincare plot in heart rate signals during meditation

Background and aim

Heart rate variability (HRV) quantifies the variability in the heart’s beat-to-beat intervals. This signal is a potential marker of cardiac function in normal, pathological, and psychological states. Signal asymmetry refers to an unequal distribution in the signal, which can be found by a two-dimensional Poincare plot. Earlier, heart rate asymmetry (HRA) was assessed using a conventional Poincare plot (lag of 1). In this study, we have investigated the effect of delay on the phase space asymmetry using lagged Poincare’s plot.

Experimental procedure

This study compared the presence/lack of asymmetries in the HRV data of 12 meditators (four Kundalini yoga (Yoga) at an advanced level of meditation, eight Chinese Chi meditators (Chi) ∼1–3 months) to 25 non-meditators (11 spontaneous nocturnal breathing (Normal) and 14 metronomic breathing (Metron)). Poincare’s plots were constructed with six different lags, and HRA was calculated. The analysis was conducted using HRV data provided in the Physionet database.

Results

The results showed that using conventional Poincare’s plot (lag of 1), the lowest HRA was observed in the Metron group. In addition, the HRA index was different between meditators and non-meditator groups. Moreover, as the most significant difference between groups was observed in a delay of 6, the role of the delay selection on the signal asymmetry was revealed.

Conclusion

The difference between lagged HRA responses on Yoga in comparison with other groups can be an emphasis on the importance of choosing the type of meditation technique and its effects on the cardiovascular system.

•

Asymmetries in HRV was assessed in different meditator and non-meditator groups.

•

The role of delay selection was explored on the phase space asymmetry using lagged Poincare plot.

•

A weaker asymmetry was observed in the metronomic breathing group.

•

The most significant difference between groups was perceived in a delay of six.

Diagnosis of atrial fibrillation based on arterial pulse wave foot point detection using artificial neural networks

BACKGROUND

Atrial fibrillation (AF) is a common arrhythmia that is strongly related to the risk of stroke. Some methods in the literature approach AF diagnosis based on cardiovascular signals of several minutes in length. However, many traditional methods utilized to monitor health status in terms of AF rely on electrocardiograms, which are time consuming and require specialized equipment to collect. By contrast, more practical systems focus on noninvasively collected short-term cardiovascular signals, such as arterial pulse waveforms (APWs).

METHODS

In this paper, an AF diagnosis algorithm based on the processing of parameters extracted from short-length heart period (HP) measures is proposed. The HP is obtained by locating foot points (FPOs) in 10-second epochs of APW signals. The algorithm consists of two main stages. First, five parameters representative of the APW morphology are extracted to train an artificial neural network (ANN) model for FPO detection. The moving interpolation difference method and an improved second derivative maximum method are employed for APW parameter extraction. Second, 13 temporal-domain, frequency-domain and nonlinear HP parameters are extracted from the previously identified FPOs. These are subsequently orthogonalized using principal component analysis to train a second ANN for effective AF diagnosis.

RESULTS

Both ANNs were trained and validated on a labeled data set with 20-fold cross-validation, achieving a mean sensitivity and specificity of 97.53% and 90.13%, respectively, for AF diagnosis and an F1 score of 99.18% for FPO identification.

CONCLUSIONS

This paper presents a validated solution for the diagnosis of AF from APW records using parameters derived from HP measures. In addition, compared to that of a commercial BP+ device, improved FPO detection performance is achieved, making the proposed algorithm a strong candidate for the automatic detection of FPOs in oscillometric devices.

Analysis of autonomic nervous pattern in hypertension based on short-term heart rate variability

Physiological studies have found that the autonomic nervous system plays an important role in controlling blood pressure values. This paper, based on machine learning approaches, analysed short-term heart rate variability to determine differences in autonomic nervous function between hypertensive patients and normal population. The electrocardiogram (ECG) of hypertensive patients are 137 ECG recordings provided by Smart Health for Assessing the Risk of Events via ECG (SHAREE database). The RR intervals of healthy subjects include the data of 18 subjects from the MIT-BIH Normal Sinus Rhythm Database (nsrdb) and 54 subjects from the Normal Sinus Rhythm RR Interval Database (nsr2db). In this paper, each RR segment includes continuous 500 beats. Seventeen features were extracted to distinguish the hypertensive heart beat rhythms from the normal ones, and Kolmogorov-Smirnov test and sequential backward selection (SBS) were applied to get the best feature combinations. In addition, support vector machine (SVM), k-nearest neighbor (KNN) and random forest (RF) were applied as classifiers in the study. The performance of each classifier was evaluated independently using the leave-one-subject-out validation method. The best predictive model was based on RF and enabled to identify hypertensive patients by five features with an accuracy of 86.44%. The best five HRV features are sample entropy (SampEn), very low frequency spectral powers (VLF), root mean square of successful differences (RMSSD), ratio of low frequency spectral powers and high frequency spectral powers (LF/HF) and vector angle index (VAI). The results of the study show sympathetic overactivity and decreased parasympathetic tone in hypertensive patients.

Recurrent probabilistic neural network-based short-term prediction for acute hypotension and ventricular fibrillation

In this paper, we propose a novel method for predicting acute clinical deterioration triggered by hypotension, ventricular fibrillation, and an undiagnosed multiple disease condition using biological signals, such as heart rate, RR interval, and blood pressure. Efforts trying to predict such acute clinical deterioration events have received much attention from researchers lately, but most of them are targeted to a single symptom. The distinctive feature of the proposed method is that the occurrence of the event is manifested as a probability by applying a recurrent probabilistic neural network, which is embedded with a hidden Markov model and a Gaussian mixture model. Additionally, its machine learning scheme allows it to learn from the sample data and apply it to a wide range of symptoms. The performance of the proposed method was tested using a dataset provided by Physionet and the University of Tokyo Hospital. The results show that the proposed method has a prediction accuracy of 92.5% for patients with acute hypotension and can predict the occurrence of ventricular fibrillation 5 min before it occurs with an accuracy of 82.5%. In addition, a multiple disease condition can be predicted 7 min before they occur, with an accuracy of over 90%.

Heart Rate Variability Analysis to Predict Onset of Ventricular Tachyarrhythmias in Implantable Cardioverter Defibrillators

Implantable cardioverter defibrillators (ICDs) are commonly used in patients at high risk of sudden cardiac death (SCD) to help prevent and treat life-threatening arrhythmia. Up to 80% of cases of sudden cardiac death are caused by ventricular tachyarrhythmias (VTA) and the accurate prediction of VTA in patients with ICDs can help prevent SCD. Early prediction allows tiered and less invasive therapies to be used to help prevent VTA which are more easily tolerated by the patient and are less battery intensive. In this work, a comparative study of three types of frequency domain features (spectral, bispectrum, and Fourier-Bessel) for VTA prediction is presented based on heart rate variability (HRV) signals between one and five minutes prior to known SCD. Using Fourier-Bessel features and a standard classification approach resulted in the best performance of 87.5% accuracy, 89.3% sensitivity and 85.7% specificity. These results suggest that Fourier-Bessel features are a promising approach for SCD prediction, and that new feature development can help improve both the sensitivity and specificity of SCD prediction in ICDs.

Current Directions in the Auricular Vagus Nerve Stimulation II - An Engineering Perspective

Electrical stimulation of the auricular vagus nerve (aVNS) is an emerging electroceutical technology in the field of bioelectronic medicine with applications in therapy. Artificial modulation of the afferent vagus nerve - a powerful entrance to the brain - affects a large number of physiological processes implicating interactions between the brain and body. Engineering aspects of aVNS determine its efficiency in application. The relevant safety and regulatory issues need to be appropriately addressed. In particular, in silico modeling acts as a tool for aVNS optimization. The evolution of personalized electroceuticals using novel architectures of the closed-loop aVNS paradigms with biofeedback can be expected to optimally meet therapy needs. For the first time, two international workshops on aVNS have been held in Warsaw and Vienna in 2017 within the scope of EU COST Action "European network for innovative uses of EMFs in biomedical applications (BM1309)." Both workshops focused critically on the driving physiological mechanisms of aVNS, its experimental and clinical studies in animals and humans, in silico aVNS studies, technological advancements, and regulatory barriers. The results of the workshops are covered in two reviews, covering physiological and engineering aspects. The present review summarizes on engineering aspects - a discussion of physiological aspects is provided by our accompanying article (Kaniusas et al., 2019). Both reviews build a reasonable bridge from the rationale of aVNS as a therapeutic tool to current research lines, all of them being highly relevant for the promising aVNS technology to reach the patient.

Prediction of Sudden Cardiac Death in Implantable Cardioverter Defibrillators: A Review and Comparative Study of Heart Rate Variability Features

Over the last four decades, implantable cardioverter defibrillators (ICDs) have been widely deployed to reduce sudden cardiac death (SCD) risk in patients with a history of life-threatening arrhythmia. By continuous monitoring of the heart rate, ICDs can use decision algorithms to distinguish normal cardiac sinus rhythm or supra-ventricular tachycardia from abnormal cardiac rhythms like ventricular tachycardia and ventricular fibrillation and deliver appropriate therapy such as an electrical stimulus. Despite the success of ICDs, more research is still needed, particularly in decision-making algorithms. Because of low specificity in practical devices, patients with ICDs still receive inappropriate shocks, which may lead to inadvertent mortality and reduction of quality of life. At the same time, higher sensitivity can lead to the use of newer tiered therapies. The purpose of this study is to review the literature on common signal features used in detection algorithms for abnormal cardiac sinus rhythm, as well as reviewing datasets used for algorithm development in previous studies. More than 50 different features to address heart rate changes before SCD have been reviewed and general methodology on this area proposed based on variety of studies on ICDs functionality. A comparative study on the prediction performance of these features, using a common database, is also presented. By combining these features with a support vector machine classifier, achieved results have compared well with other studies.

Automatic Prediction of Atrial Fibrillation Based on Convolutional Neural Network Using a Short-term Normal Electrocardiogram Signal

BACKGROUND

In this study, we propose a method for automatically predicting atrial fibrillation (AF) based on convolutional neural network (CNN) using a short-term normal electrocardiogram (ECG) signal.

METHODS

We designed a CNN model and optimized it by dropout and normalization. One-dimensional convolution, max-pooling, and fully-connected multiple perceptron were used to analyze the short-term normal ECG. The ECG signal was preprocessed and segmented to train and evaluate the proposed CNN model. The training and test sets consisted of the two AF and one normal dataset from the MIT-BIH database.

RESULTS

The proposed CNN model for the automatic prediction of AF achieved a high performance with a sensitivity of 98.6%, a specificity of 98.7%, and an accuracy of 98.7%.

CONCLUSION

The results show the possibility of automatically predicting AF based on the CNN model using a short-term normal ECG signal. The proposed CNN model for the automatic prediction of AF can be a helpful tool for the early diagnosis of AF in healthcare fields.

Can heart rate variability parameters derived by a heart rate monitor differentiate between atrial fibrillation and sinus rhythm?

BACKGROUND

Heart rate variability (HRV) parameters, and especially RMSSD (root mean squared successive differences in RR interval), could distinguish atrial fibrillation (AF) from sinus rhythm(SR) in horses, as was demonstrated in a previous study. If heart rate monitors (HRM) automatically calculating RMSSD could also distinguish AF from SR, they would be useful for the monitoring of AF recurrence. The objective of the study was to assess whether RMSSD values obtained from a HRM can differentiate AF from SR in horses. Furthermore, the impact of artifact correction algorithms, integrated in the analyses software for HRV analyses was evaluated. Fourteen horses presented for AF treatment were simultaneously equipped with a HRM and an electrocardiogram (ECG). A two-minute recording at rest, walk and trot, before and after cardioversion, was obtained. RR intervals used were those determined automatically by the HRM and by the equine ECG analysis software, and those obtained after manual correction of QRS detection within the ECG software. RMSSD was calculated by the HRM software and by dedicated HRV software, using six different artifact filters. Statistical analysis was performed using the Wilcoxon signed-rank test and receiver operating curves.

RESULTS

The HRM, which applies a low level filter, produced high area under the curve (AUC) (> 0.9) and cut off values with high sensitivity and specificity. Similar results were obtained for the ECG, when low level artifact filtering was applied. When no artifact correction was used during trotting, an important decrease in AUC (0.75) occurred.

CONCLUSION

In horses treated for AF, HRMs with automatic RMSSD calculations distinguish between AF and SR. Such devices might be a useful aid to monitor for AF recurrence in horses.

Prediction of paroxysmal Atrial Fibrillation: A machine learning based approach using combined feature vector and mixture of expert classification on HRV signal

BACKGROUND AND OBJECTIVE

Paroxysmal Atrial Fibrillation (PAF) is one of the most common major cardiac arrhythmia. Unless treated timely, PAF might transform into permanent Atrial Fibrillation leading to a high rate of morbidity and mortality. Therefore, increasing attention has been directed towards prediction of PAF, to enable early detection and prevent further progression of the disease. Notwithstanding the pharmacological and electrical treatments, a validated method to predict the onset of PAF is yet to be developed. We aim to address this issue through integrating classical and modern methods.

METHODS

To increase the predictivity, we have made use of a combination of features extracted through linear, time-frequency, and nonlinear analyses performed on heart rate variability. We then apply a novel approach to local feature selection using meticulous methodologies, developed in our previous works, to reduce the dimensionality of the feature space. Subsequently, the Mixture of Experts classification is employed to ensure a precise decision-making on the output of different processes. In the current study, we analyzed 106 signals from 53 pairs of ECG recordings obtained from the standard database called Atrial Fibrillation Prediction Database (AFPDB). Each pair of data contains one 30-min ECG segment that ends just before the onset of PAF event and another 30-min ECG segment at least 45 min distant from the onset.

RESULTS

Combining the features that are extracted using both classical and modern analyses was found to be significantly more effective in predicting the onset of PAF, compared to using either analyses independently. Also, the Mixture of Experts classification yielded more precise class discrimination than other well-known classifiers. The performance of the proposed method was evaluated using the Atrial Fibrillation Prediction Database (AFPDB) which led to sensitivity, specificity, and accuracy of 100%, 95.55%, and 98.21% respectively.

CONCLUSION

Prediction of PAF has been a matter of clinical and theoretical importance. We demonstrated that utilising an optimized combination of - as opposed to being restricted to - linear, time-frequency, and nonlinear features, along with applying the Mixture of Experts, contribute greatly to an early detection of PAF, thus, the proposed method is shown to be superior to those mentioned in similar studies in the literature.

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.

Left atrial phasic function and heart rate variability in patients with systemic sclerosis: A new part of the old puzzle

OBJECTIVE

We aimed to research left atrial (LA) phasic function and heart rate variability (HRV), as well as their relationship, in subjects with uncomplicated systemic sclerosis (SSc).

METHODS

The investigation involved 44 SSc patients and 33 age-matched healthy controls. All participants underwent clinical examination, serological tests, 24-hours Holter monitoring, and echocardiographic examination including strain analysis.

RESULTS

Maximum, minimum, and pre-A LA volumes and volume indices were higher in the SSc patients than in the controls. The total emptying fraction, the parameter of the LA reservoir function, as well as passive LA emptying fraction, which represents the LA conduit function, were significantly lower in the SSc patients compared to the controls. Active LA emptying fraction, the parameter of the LA booster pump function, was significantly higher in the SSc participants. There was no difference in LA reservoir function between the diffuse and the limited SSc form. LA conduit function was significantly decreased, whereas LA booster pump function was compensatory increased in the diffuse SSc form compared to the limited SSc form. Similar results were obtained by LA strain analysis. HRV indices were significantly decreased in the SSc patients. Modified Rodnan skin score, the parameter of skin involvement in SSc, and HRV indices correlated well with LA phasic function in SSc.

CONCLUSION

Left atrial (LA) phasic function, assessed by both volumetric and strain method, as well as cardiac autonomic nervous function is significantly deteriorated in SSc patients. Skin score and HRV indices correlate with LA phasic function parameters.

Usefulness of P-Wave Duration and Morphologic Variability to Identify Patients Prone to Paroxysmal Atrial Fibrillation

Few data are available on the assessment of P-wave beat-to-beat morphology variability and its ability to identify patients prone to paroxysmal atrial fibrillation (AF) occurrence. Aim of this study was to determine whether electrocardiographic (ECG) parameters resulting from the beat-to-beat analysis of P wave in ECG recorded during sinus rhythm could be indicators of paroxysmal AF susceptibility. ECGs of 76 consecutive patients including 36 patients with history of AF and no overt structural cardiac abnormalities and a control group of 40 healthy patients without history of AF were analyzed. After preprocessing, features based on P waves and RR intervals were extracted from lead II of a 5-minute ECG recorded during sinus rhythm. The discriminative power of the extracted features was assessed. Among extracted features, the most discriminative ones to identify patients with paroxysmal episodes of AF were the mean P-wave duration and the SD of beat-to-beat Euclidean distance between P waves (an indicator of beat-to-beat P-wave morphologic variability). Patients with history of AF presented a significantly longer P-wave duration (125 ± 18 vs 110 ± 8 ms, p <0.001) and higher variability of P-wave morphology over time (beat-to-beat Euclidean distance: 0.11 ± 0.07 vs 0.076 ± 0.02, p <0.01) compared to patients without history of AF. Combination of P-wave duration and standard deviation of beat-to-beat Euclidean distance led to an accuracy of 88% in the discrimination between the 2 groups of patients. In conclusion, combination of P-wave duration and beat-to-beat Euclidean distance between P waves efficiently discriminates patients with history of AF and no overt structural cardiac abnormalities from healthy age-matched subjects, and it might be used as an effective tool to identify patients prone to paroxysmal AF occurrence.