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

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.

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.

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.

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.

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.

Life events are associated with elevated heart rate and reduced heart complexity to acute psychological stress

The current study examined whether the exposure to life events and reported impact of life events are associated with altered cardiac reactivity to an acute psychological stressor. Participants (N = 69) completed the Life Experience Survey (LES) and Positive and Negative Affect Schedule (PANAS) and undertook a standardized social-evaluative stress task. Cardiac activity was measured via heart rate and non-linear heart rate variability (HRV) indices Sample Entropy, SD1, SD2 and SD1/SD2 ratio. Heart rate and non-linear HRV were measured before, during and after stress exposure. Findings suggest higher heart rate reactivity in individuals reporting higher number and impact of negative and total life events. Decreases in Sample Entropy were evident for number as well as impact of life events. No associations were found for SD1, SD2 and SD1/SD2 ratio. Findings suggest that life-events are associated with elevated heart rate and diminished heart rate complexity in response to acute stress.

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.

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.

The complexity of clinically-normal sinus-rhythm ECGs is decreased in equine athletes with a diagnosis of paroxysmal atrial fibrillation

Equine athletes have a pattern of exercise which is analogous to human athletes and the cardiovascular risks in both species are similar. Both species have a propensity for atrial fibrillation (AF), which is challenging to detect by ECG analysis when in paroxysmal form. We hypothesised that the proarrhythmic background present between fibrillation episodes in paroxysmal AF (PAF) might be detectable by complexity analysis of apparently normal sinus-rhythm ECGs. In this retrospective study ECG recordings were obtained during routine clinical work from 82 healthy horses and from 10 horses with a diagnosis of PAF. Artefact-free 60-second strips of normal sinus-rhythm ECGs were converted to binary strings using threshold crossing, beat detection and a novel feature detection parsing algorithm. Complexity of the resulting binary strings was calculated using Lempel-Ziv (‘76 & ‘78) and Titchener complexity estimators. Dependence of Lempel-Ziv ‘76 and Titchener T-complexity on the heart rate in ECG strips obtained at low heart rates (25–60 bpm) and processed by the feature detection method was found to be significantly different in control animals and those diagnosed with PAF. This allows identification of horses with PAF from sinus-rhythm ECGs with high accuracy.

The application of Lempel-Ziv and Titchener complexity analysis for equine telemetric electrocardiographic recordings

The analysis of equine electrocardiographic (ECG) recordings is complicated by the absence of agreed abnormality classification criteria. We explore the applicability of several complexity analysis methods for characterization of non-linear aspects of electrocardiographic recordings. We here show that complexity estimates provided by Lempel-Ziv ’76, Titchener’s T-complexity and Lempel-Ziv ’78 analysis of ECG recordings of healthy Thoroughbred horses are highly dependent on the duration of analysed ECG fragments and the heart rate. The results provide a methodological basis and a feasible reference point for the complexity analysis of equine telemetric ECG recordings that might be applied to automate detection of equine arrhythmias in equine clinical practice.

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.

Spatial and temporal analysis center of pressure displacement during adolescence: Clinical implications of developmental changes

This study aimed to provide insight into the development of postural control abilities in youth. A total of 276 typically developing adolescents (155 males, 121 females) with a mean age of 13.23 years (range of 7.11-18.80) were recruited for participation. Subjects performed two-minute quiet standing trials in bipedal stance on a force plate. Center of pressure (COP) trajectories were quantified using Sample Entropy (SampEn) in the anterior-posterior direction (SampEn-AP), SampEn in the medial-lateral direction (SampEn-ML), and Path Length (PL) measures. Three separate linear regression analyses were conducted to predict the relationship between age and each of the response variables after adjusting for individuals' physical characteristics. Linear regression models showed an inverse relationship between age and entropy measures after adjusting for body mass index. Results indicated that chronological age was predictive of entropy and path length patterns. Specifically, older adolescents exhibited center of pressure displacement (smaller path length) and less complex, more regular center of pressure displacement patterns (lower SampEn-AP and SampEn-ML values) compared to the younger children. These findings support prior studies suggesting that developmental changes in postural control abilities may continue throughout adolescence and into adulthood.

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.

Systematic mapping study of data mining–based empirical studies in cardiology

Data mining provides the methodology and technology to transform huge amount of data into useful information for decision making. It is a powerful process to extract knowledge and discover new patterns embedded in large data sets. Data mining has been increasingly used in medicine, particularly in cardiology. In fact, data mining applications can greatly benefits all parts involved in cardiology such as patients, cardiologists and nurses. This article aims to perform a systematic mapping study so as to analyze and synthesize empirical studies on the application of data mining techniques in cardiology. A total of 142 articles published between 2000 and 2015 were therefore selected, studied and analyzed according to the four following criteria: year and channel of publication, research type, medical task and empirical type. The results of this mapping study are discussed and a list of recommendations for researchers and cardiologists is provided.

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.

Paroxysmal atrial fibrillation prediction method with shorter HRV sequences

This paper proposes a method that predicts the onset of paroxysmal atrial fibrillation (PAF), using heart rate variability (HRV) segments that are shorter than those applied in existing methods, while maintaining 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 stabilize (electrically) and prevent the onset of atrial arrhythmias with different pacing techniques. We investigate the effect of HRV features extracted from different lengths of HRV segments prior to PAF onset with the proposed PAF prediction method. The pre-processing stage of the predictor includes QRS detection, HRV quantification and ectopic beat correction. Time-domain, frequency-domain, non-linear and bispectrum features are then extracted from the quantified HRV. In the feature selection, the HRV feature set and classifier parameters are optimized simultaneously using an optimization procedure based on genetic algorithm (GA). Both full feature set and statistically significant feature subset are optimized by GA respectively. For the statistically significant feature subset, Mann-Whitney U test is used to filter non-statistical significance features that cannot pass the statistical test at 20% significant level. The final stage of our predictor is the classifier that is based on support vector machine (SVM). A 10-fold cross-validation is applied in performance evaluation, and the proposed method achieves 79.3% prediction accuracy using 15-minutes HRV segment. This accuracy is comparable to that achieved by existing methods that use 30-minutes HRV segments, most of which achieves accuracy of around 80%. More importantly, our method significantly outperforms those that applied segments shorter than 30 minutes.

Effects of transcranial direct current stimulation (tDCS) on multiscale complexity of dual-task postural control in older adults

Transcranial direct current stimulation (tDCS) targeting the prefrontal cortex reduces the size and speed of standing postural sway in younger adults, particularly when performing a cognitive dual task. Here, we hypothesized that tDCS would alter the complex dynamics of postural sway as quantified by multiscale entropy (MSE). Twenty healthy older adults completed two study visits. Center-of-pressure (COP) fluctuations were recorded during single-task (i.e., quiet standing) and dual-task (i.e., standing while performing serial subtractions) conditions, both before and after a 20-min session of real or sham tDCS. MSE was used to estimate COP complexity within each condition. The percentage change in complexity from single- to dual-task conditions (i.e., dual-task cost) was also calculated. Before tDCS, COP complexity was lower (p = 0.04) in the dual-task condition as compared to the single-task condition. Neither real nor sham tDCS altered complexity in the single-task condition. As compared to sham tDCS, real tDCS increased complexity in the dual-task condition (p = 0.02) and induced a trend toward improved serial subtraction performance (p = 0.09). Moreover, those subjects with lower dual-task COP complexity at baseline exhibited greater percentage increases in complexity following real tDCS (R = -0.39, p = 0.05). Real tDCS also reduced the dual-task cost to complexity (p = 0.02), while sham stimulation had no effect. A single session of tDCS targeting the prefrontal cortex increased standing postural sway complexity with concurrent non-postural cognitive task. This form of noninvasive brain stimulation may be a safe strategy to acutely improve postural control by enhancing the system's capacity to adapt to stressors.

Alteration of the P-wave non-linear dynamics near the onset of paroxysmal atrial fibrillation

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

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

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

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

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

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.

Heart rate variability dynamics for the prognosis of cardiovascular risk

Statistical, spectral, multi-resolution and non-linear methods were applied to heart rate variability (HRV) series linked with classification schemes for the prognosis of cardiovascular risk. A total of 90 HRV records were analyzed: 45 from healthy subjects and 45 from cardiovascular risk patients. A total of 52 features from all the analysis methods were evaluated using standard two-sample Kolmogorov-Smirnov test (KS-test). The results of the statistical procedure provided input to multi-layer perceptron (MLP) neural networks, radial basis function (RBF) neural networks and support vector machines (SVM) for data classification. These schemes showed high performances with both training and test sets and many combinations of features (with a maximum accuracy of 96.67%). Additionally, there was a strong consideration for breathing frequency as a relevant feature in the HRV analysis.

An introduction to artificial neural networks in bioinformatics--application to complex microarray and mass spectrometry datasets in cancer studies

Applications of genomic and proteomic technologies have seen a major increase, resulting in an explosion in the amount of highly dimensional and complex data being generated. Subsequently this has increased the effort by the bioinformatics community to develop novel computational approaches that allow for meaningful information to be extracted. This information must be of biological relevance and thus correlate to disease phenotypes of interest. Artificial neural networks are a form of machine learning from the field of artificial intelligence with proven pattern recognition capabilities and have been utilized in many areas of bioinformatics. This is due to their ability to cope with highly dimensional complex datasets such as those developed by protein mass spectrometry and DNA microarray experiments. As such, neural networks have been applied to problems such as disease classification and identification of biomarkers. This review introduces and describes the concepts related to neural networks, the advantages and caveats to their use, examples of their applications in mass spectrometry and microarray research (with a particular focus on cancer studies), and illustrations from recent literature showing where neural networks have performed well in comparison to other machine learning methods. This should form the necessary background knowledge and information enabling researchers with an interest in these methodologies, but not necessarily from a machine learning background, to apply the concepts to their own datasets, thus maximizing the information gain from these complex biological systems.