A model-based Bayesian framework for ECG beat segmentation

Electrocardiogram classification using TSST-based spectrogram and ConViT

As an important auxiliary tool of arrhythmia diagnosis, Electrocardiogram (ECG) is frequently utilized to detect a variety of cardiovascular diseases caused by arrhythmia, such as cardiac mechanical infarction. In the past few years, the classification of ECG has always been a challenging problem. This paper presents a novel deep learning model called convolutional vision transformer (ConViT), which combines vision transformer (ViT) with convolutional neural network (CNN), for ECG arrhythmia classification, in which the unique soft convolutional inductive bias of gated positional self-attention (GPSA) layers integrates the superiorities of attention mechanism and convolutional architecture. Moreover, the time-reassigned synchrosqueezing transform (TSST), a newly developed time-frequency analysis (TFA) method where the time-frequency coefficients are reassigned in the time direction, is employed to sharpen pulse traits for feature extraction. Aiming at the class imbalance phenomena in the traditional ECG database, the smote algorithm and focal loss (FL) are used for data augmentation and minority-class weighting, respectively. The experiment using MIT-BIH arrhythmia database indicates that the overall accuracy of the proposed model is as high as 99.5%. Furthermore, the specificity (Spe), F1-Score and positive Matthews Correlation Coefficient (MCC) of supra ventricular ectopic beat (S) and ventricular ectopic beat (V) are all more than 94%. These results demonstrate that the proposed method is superior to most of the existing methods.

Arrhythmia detection and classification using ECG and PPG techniques: a review

Electrocardiogram (ECG) and photoplethysmograph (PPG) are non-invasive techniques that provide electrical and hemodynamic information of the heart, respectively. This information is advantageous in the diagnosis of various cardiac abnormalities. Arrhythmia is the most common cardiovascular disease, manifested as single or multiple irregular heartbeats. However, due to the continuous manual observation, it becomes troublesome for experts sometimes to identify the paroxysmal nature of arrhythmia correctly. Moreover, due to advancements in technology, there is an inclination towards wearable sensors which monitor such patients continuously. Thus, there is a need for automatic detection techniques for the identification of arrhythmia. In the presented work, ECG and PPG-based state-of-the-art methods have been described, including preprocessing, feature extraction, and classification techniques for the detection of various arrhythmias. Additionally, this review exhibits various wearable sensors used in the literature and public databases available for the evaluation of results. The study also highlights the limitations of the current techniques and pragmatic solutions to improvise the ongoing effort.

Electrocardiogram Fiducial Point Detector Using a Bilateral Filter and Symmetrical Point-Filter Structure

The characteristics or aspects of important fiducial points (FPs) in the electrocardiogram (ECG) signal are complicated because of various factors, such as non-stationary effects and low signal-to-noise ratio. Due to the various noises caused by the ECG signal measurement environment and by typical ECG signal deformation due to heart diseases, detecting such FPs becomes a challenging task. In this study, we introduce a novel PQRST complex detector using a one-dimensional bilateral filter (1DBF) and the temporal characteristics of FPs. The 1DBF with noise suppression and edge preservation preserves the P- or T-wave whereas it suppresses the QRS-interval. The 1DBF acts as a background predictor for predicting the background corresponding to the P- and T-waves and the remaining flat interval excluding the QRS-interval. The R-peak and QRS-interval are founded by the difference of the original ECG signal and the predicted background signal. Then, the Q- and S-points and the FPs related to the P- and T-wave are sequentially detected using the determined searching range and detection order based on the detected R-peak. The detection performance of the proposed method is analyzed through the MIT-BIH database (MIT-DB) and the QT database (QT-DB).

An Adaptive Kalman Filter Bank for ECG Denoising

Model-based Bayesian frameworks proved their effectiveness in the field of ECG processing. However, their performances rely heavily on the pre-defined models extracted from ECG signals. Furthermore, their performances decrease substantially when ECG signals do not comply with their models- a situation generally occurs in the case of arrhythmia-. In this paper, we propose a novel Bayesian framework based on Kalman filter, which does not need a predefined model and can adapt itself to different ECG morphologies. Compared with the previous Bayesian techniques, the proposed method requires much less preprocessing and it only needs to know the location of R-peaks to start ECG processing. Our method uses a filter bank comprised of two adaptive Kalman filters, one for denoising QRS complex (high frequency section) and another one for denoising P and T waves (low frequency section). The parameters of these filters are estimated and iteratively updated using expectation maximization (EM) algorithm. In order to deal with nonstationary noises such as muscle artifact (MA) noise, we used Bryson and Henrikson's technique for the prediction and update steps inside the Kalman filter bank. We evaluated the performance of the proposed method on different ECG databases containing signals having morphological changes and abnormalities such as atrial premature complex (APC), premature ventricular contractions (PVC), Ventricular Tachyarrhythmia (VT) and sudden cardiac death (SCD). The proposed algorithm was compared with several popular ECG denoising methods such as wavelet transform (WD) and empirical mode decomposition (EMD). The comparison results showed that the proposed method performs well in the presence of various ECG morphologies in both stationary and non-stationary environments especially at low input SNRs.

Noise robust automatic heartbeat classification system using support vector machine and conditional spectral moment

Heartbeat classification is central to the detection of the arrhythmia. For the effective heartbeat classification, the noise-robust features are very significant. In this work, we have proposed a noise-robust support vector machine (SVM) based heartbeat classifier. The proposed classifier utilizes a novel noise-robust morphological feature which is based on the conditional spectral moment (CSM) of the heartbeat. In addition to the proposed CSM feature, we have also employed the existing RR interval, the wavelets, and the higher-order statistics (HOS) based temporal and morphological feature sets. The noise-robustness test of the proposed CSM and all the studied feature sets is performed for the SVM based heartbeat classifier. Further, we have studied the significance of combining these temporal and morphological features on the final classification performance. For this purpose, the individual SVMs were trained for each of the feature set. The final classification is based on the ensemble of these individual SVMs. Various combining scheme such as sum, majority, and product rules are employed to ensemble the result of the individually trained SVMs. The experimental results show the noise-robustness of the proposed CSM feature. The proposed classifier gives improved overall performance compared to the existing heartbeat classification systems.

Multichannel Esophageal Heart Rate Monitoring of Preterm Infants

OBJECTIVE

Autonomic dysregulation in preterm infants requires continuous monitoring of vital signs such as heart rate over days to months. Unfortunately, common surface electrodes are prone to electrocardiography (ECG) signal artifacts and cause serious skin irritations during long-term use. In contrast, esophageal ECG is known to be very sensitive due to the proximity of electrodes and heart and insensitive to external influences. This study addresses if multichannel esophageal ECG qualifies for heart rate monitoring in preterm infants.

METHODS

We recorded esophageal leads with a multi-electrode gastric feeding tube in a clinical study with 13 neonates and compared the heartbeat detection performance with standard surface leads. A computationally simple and versatile ECG wave detection algorithm was used.

RESULTS

Multichannel esophageal ECG manifested heartbeat sensitivity and positive predictive value greater than 98.5% and significant less false negative (FN) ECG waves as compared to surface ECG due to site-typical electrode motion artifacts. False positive bradycardia as indicated with more than 13 consecutive FN ECG waves was equally expectable in esophageal and surface channels. No adverse events were reported for the multi-electrode gastric feeding tube.

CONCLUSION

Heart rate monitoring of preterm infants with multiple esophageal electrodes is considered as feasible and reliable. Less signal artifacts will improve the detection of bradycardia, which is crucial for immediate interventions, and reduce alarm fatigue.

SIGNIFICANCE

Due to the possibility to integrate the multichannel ECG into a gastric feeding tube and meanwhile omit harmful skin electrodes, the presented system has great potential to facilitate future intensive care of preterm infants.

Delineation of Electrocardiograms Using Multiscale Parameter Estimation

The continuing interest in unobtrusive electrocardiography requires the development of algorithms, compensating for an increased number of artifacts. In previous work, we proposed a framework for robust parameter estimation of signals following a piecewise Gaussian derivative model, well suited for describing all waves of a heartbeat. The framework is based on a numeric and analytic representation of applying the Wavelet Transform at arbitrary scale to the input model. For robustly estimating model parameters, it processes lines of zero-crossings in scale-space, showing high accuracy for various noise models in synthetic signals. An initial evaluation with electrocardiography signals revealed that our basic classifier for identifying the correct lines often fails, leading to false parameter estimates. In this work, we propose a general delineation method based on a solid mathematical framework that treats each heartbeat, wave and fiducial point in the same way, tailored only by intuitive parameters and not relying on any heuristically found decision rules. The steps include a novel line classifier based on pre-filtering using domain knowledge, followed by an exhaustive search among all possible combinations of zero-crossing lines and an error-measure quantifying their agreement with the model. The combination with highest agreement is processed by the parameter estimation framework, customized to the computation of all nine fiducial points. Evaluation using the expert-annotated QT database, shows high sensitivity (P: 99.91%, QRS: 99.92%, T: 99.89%) and mean errors below 1 ms for all onset and offset fiducial points. The proposed combination of line classification and parameter estimation is well suited for delineating electrocardiograms.

An Accurate QRS complex and P wave Detection in ECG Signals using Complete Ensemble Empirical Mode Decomposition Approach

We developed a novel method for QRS complex and P wave detection in the electrocardiogram (ECG) signal. The approach reconstructs two different signals for the purpose of QRS and P wave detection from the modes obtained by the complete ensemble empirical mode decomposition with adaptive noise, taking only those modes that best represent the signal dynamics. This approach eliminates the need for conventional filtering. We first detect QRS complex locations, followed by removal of QRS complexes from the reconstructed signal to enable P wave detection. We introduce a novel method of P wave detection from both the positive and negative amplitudes of the ECG signal and an adaptive P wave search approach to find the true P wave. Our detection method automatically identifies P waves without prior information. The proposed method was validated on two well-known annotated databases-the MIT BIH Arrythmia database (MITDB) and The QT database (QTDB). The QRS detection algorithm resulted in 99.96% sensitivity, 99.9% positive predictive value, and an error of 0.13% on all validation databases. The P wave detection method had better performance when compared to other well-known methods. The performance of our P wave detection on the QTDB showed a sensitivity of 99.96%, a positive predictive value of 99.47%, and the mean error in P peak detection was less than or equal to one sample (4 ms) on average.

Performance Investigation of Marginalized Particle-Extended Kalman Filter under Different Particle Weighting Strategies in the Field of Electrocardiogram Denoising

Background:

Recently, a marginalized particle-extended Kalman filter (MP-EKF) has been proposed for electrocardiogram (ECG) signal denoising. Similar to particle filters, the performance of MP-EKF relies heavily on the definition of proper particle weighting strategy. In this paper, we aim to investigate the performance of MP-EKF under different particle weighting strategies in both stationary and nonstationary noises. Some of these particle weighting strategies are introduced for the first time for ECG denoising.

Methods:

In this paper, the proposed particle weighting strategies use different mathematical functions to regulate the behaviors of particles based on noisy measurements and a synthetic ECG signal built using feature parameters of ECG dynamic model. One of these strategies is a fuzzy-based particle weighting method that is defined to adapt its function based on different input signal-to-noise ratios (SNRs). To evaluate the proposed particle weighting strategies, the denoising performance of MP-EKF was evaluated on MIT-BIH normal sinus rhythm database at 11 different input SNRs and in four different types of artificial and real noises. For quantitative comparison, the SNR improvement measure was used, and for qualitative comparison, the multi-scale entropy-based weighted distortion measure was used.

Results:

The experimental results revealed that the fuzzy-based particle weighting strategy exhibited a very well and reliable performance in both stationary and nonstationary noisy environments.

Conclusion:

We concluded that the fuzzy-based particle weighting strategy is the best-suited strategy for MP-EKF framework because it adaptively and automatically regulates the behaviors of particles in different noisy environments.

ECG fiducial point extraction using switching Kalman filter

In this paper, we propose a novel method for extracting fiducial points (FPs) of the beats in electrocardiogram (ECG) signals using switching Kalman filter (SKF). In this method, according to McSharry's model, ECG waveforms (P-wave, QRS complex and T-wave) are modeled with Gaussian functions and ECG baselines are modeled with first order auto regressive models. In the proposed method, a discrete state variable called "switch" is considered that affects only the observation equations. We denote a mode as a specific observation equation and switch changes between 7 modes and corresponds to different segments of an ECG beat. At each time instant, the probability of each mode is calculated and compared among two consecutive modes and a path is estimated, which shows the relation of each part of the ECG signal to the mode with the maximum probability. ECG FPs are found from the estimated path. For performance evaluation, the Physionet QT database is used and the proposed method is compared with methods based on wavelet transform, partially collapsed Gibbs sampler (PCGS) and extended Kalman filter. For our proposed method, the mean error and the root mean square error across all FPs are 2 ms (i.e. less than one sample) and 14 ms, respectively. These errors are significantly smaller than those obtained using other methods. The proposed method achieves lesser RMSE and smaller variability with respect to others.

Electrocardiogram Delineation in a Wistar Rat Experimental Model

Background and Objectives

The extensive use of electrocardiogram (ECG) recordings during experimental protocols using small rodents requires an automatic delineation technique in the ECG with high performance. It has been shown that the wavelet transform (WT) based ECG delineator is a suitable tool to delineate electrocardiographic waveforms. The aim of this work is to implement and evaluate the ECG waves delineation in Wistar rats applying WT. We also describe the ECG signal of the Wistar rats giving the characteristics of its spectrum among other useful information.

Methods

We evaluated a delineator based on WT in a Wistar rat electrocardiograms database which was annotated manually by experienced observers.

Results

The delineation showed an “overall performance” such as sensitivity and a positive predictive value of 99.2% and 83.9% for P-wave, 100% and 99.9% for QRS complex, and 100% and 99.8% for T-wave, respectively. We also compared temporal analysis based ECG delineator with the WT based ECG delineator in RR interval, QRS duration, QT interval, and T-wave peak-to-end duration. The results showed that WT outperforms the temporal delineation technique in all parameters analyzed.

Conclusions

Finally, we propose a WT based ECG delineator as a methodology to implement in a wide diversity of experimental ECG analyses using Wistar rats.

Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances

Widely developed for clinical screening, electrocardiogram (ECG) recordings capture the cardiac electrical activity from the body surface. ECG analysis can therefore be a crucial first step to help diagnose, understand and predict cardiovascular disorders responsible for 30% of deaths worldwide. Computational techniques, and more specifically machine learning techniques and computational modelling are powerful tools for classification, clustering and simulation, and they have recently been applied to address the analysis of medical data, especially ECG data. This review describes the computational methods in use for ECG analysis, with a focus on machine learning and 3D computer simulations, as well as their accuracy, clinical implications and contributions to medical advances. The first section focuses on heartbeat classification and the techniques developed to extract and classify abnormal from regular beats. The second section focuses on patient diagnosis from whole recordings, applied to different diseases. The third section presents real-time diagnosis and applications to wearable devices. The fourth section highlights the recent field of personalized ECG computer simulations and their interpretation. Finally, the discussion section outlines the challenges of ECG analysis and provides a critical assessment of the methods presented. The computational methods reported in this review are a strong asset for medical discoveries and their translation to the clinical world may lead to promising advances.

Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification

Automatic feature extraction and classification are two main tasks in abnormal ECG beat recognition. Feature extraction is an important prerequisite prior to classification since it provides the classifier with input features, and the performance of classifier depends significantly on the quality of these features. This study develops an effective method to extract low-dimensional ECG beat feature vectors. It employs wavelet multi-resolution analysis to extract time-frequency domain features and then applies principle component analysis to reduce the dimension of the feature vector. In classification, 12-element feature vectors characterizing six types of beats are used as inputs for one-versus-one support vector machine, which is conducted in form of 10-fold cross validation with beat-based and record-based training schemes. Tested upon a total of 107049 beats from MIT-BIH arrhythmia database, our method has achieved average sensitivity, specificity and accuracy of 99.09%, 99.82% and 99.70%, respectively, using the beat-based training scheme, and 44.40%, 88.88% and 81.47%, respectively, using the record-based training scheme.

A New Wavelet-Based ECG Delineator for the Evaluation of the Ventricular Innervation

T-wave amplitude (TWA) has been proposed as a marker of the innervation of the myocardium. Until now, TWA has been calculated manually or with poor algorithms, thus making its use not efficient in a clinical environment. We introduce a new wavelet-based algorithm for the delineation QRS complexes and T-waves, and the automatic calculation of TWA. When validated in the MIT/BIH Arrhythmia database, the QRS detector achieved sensitivity and positive predictive value of 99.84% and 99.87%, respectively. The algorithm was validated also on the QT database and it achieved sensitivity of 99.50% for T-peak detection. In addition, the algorithm achieved delineation accuracy that is similar to the differences in delineation between expert cardiologists. We applied the algorithm for the evaluation of the influence in TWA of anticholinergic and antiadrenergic drugs (i.e., atropine and metoprolol) for healthy subjects. We found that the TWA decreased significantly with atropine and that metoprolol caused a significant increase in TWA, thus confirming the clinical hypothesis that the TWA is a marker of the innervation of the myocardium. The results of this paper show that the proposed algorithm can be used as a useful and efficient tool in clinical practice for the automatic calculation of TWA and its interpretation as a non-invasive marker of the autonomic ventricular innervation.

ECG segmentation and fiducial point extraction using multi hidden Markov model

In this paper, we propose a novel method for extracting fiducial points (FPs) of electrocardiogram (ECG) signals. We propose the use of multi hidden Markov model (MultiHMM) as opposed to the traditional use of Classic HMM. In the MultiHMM method, each segment of an ECG beat is represented by a separate ergodic continuous density HMM. Each HMM has different state number and is trained separately. In the test step, the log-likelihood of two consecutive HMMs is compared and a path is estimated, which shows the correspondence of each part of the ECG signal to the HMM with the maximum log-likelihood. Fiducial points are estimated from the obtained path. For performance evaluation, the Physionet QT database and a Swine ECG database are used and the proposed method is compared with the Classic HMM and a method based on partially collapsed Gibbs sampler (PCGS). In our evaluation using the QT database, we also compare the results with low-pass differentiation, hybrid feature extraction algorithm, a method based on the wavelet transform and three HMM-based approaches. For the Swine database, the root mean square error (RMSE) values, across all FPs for MultiHMM, Classic HMM and PCGS methods are 13, 21 and 40ms, respectively and the MultiHMM exhibits smaller error variability than other methods. For the QT database, RMSE values for MultiHMM, Classic HMM, Wavelet and PCGS methods are 10, 17, 26 and 38ms, respectively. Our results demonstrate that our proposed MultiHMM approach outperforms other benchmark methods that exist in the literature; therefore can be used in practical ECG fiducial point extraction.

ECG Denoising Using Marginalized Particle Extended Kalman Filter With an Automatic Particle Weighting Strategy

In this paper, a model-based Bayesian filtering framework called the "marginalized particle-extended Kalman filter (MP-EKF) algorithm" is proposed for electrocardiogram (ECG) denoising. This algorithm does not have the extended Kalman filter (EKF) shortcoming in handling non-Gaussian nonstationary situations because of its nonlinear framework. In addition, it has less computational complexity compared with particle filter. This filter improves ECG denoising performance by implementing marginalized particle filter framework while reducing its computational complexity using EKF framework. An automatic particle weighting strategy is also proposed here that controls the reliance of our framework to the acquired measurements. We evaluated the proposed filter on several normal ECGs selected from MIT-BIH normal sinus rhythm database. To do so, artificial white Gaussian and colored noises as well as nonstationary real muscle artifact (MA) noise over a range of low SNRs from 10 to -5 dB were added to these normal ECG segments. The benchmark methods were the EKF and extended Kalman smoother (EKS) algorithms which are the first model-based Bayesian algorithms introduced in the field of ECG denoising. From SNR viewpoint, the experiments showed that in the presence of Gaussian white noise, the proposed framework outperforms the EKF and EKS algorithms in lower input SNRs where the measurements and state model are not reliable. Owing to its nonlinear framework and particle weighting strategy, the proposed algorithm attained better results at all input SNRs in non-Gaussian nonstationary situations (such as presence of pink noise, brown noise, and real MA). In addition, the impact of the proposed filtering method on the distortion of diagnostic features of the ECG was investigated and compared with EKF/EKS methods using an ECG diagnostic distortion measure called the "Multi-Scale Entropy Based Weighted Distortion Measure" or MSEWPRD. The results revealed that our proposed algorithm had the lowest MSEPWRD for all noise types at low input SNRs. Therefore, the morphology and diagnostic information of ECG signals were much better conserved compared with EKF/EKS frameworks, especially in non-Gaussian nonstationary situations.

ECG-based heartbeat classification for arrhythmia detection: A survey

An electrocardiogram (ECG) measures the electric activity of the heart and has been widely used for detecting heart diseases due to its simplicity and non-invasive nature. By analyzing the electrical signal of each heartbeat, i.e., the combination of action impulse waveforms produced by different specialized cardiac tissues found in the heart, it is possible to detect some of its abnormalities. In the last decades, several works were developed to produce automatic ECG-based heartbeat classification methods. In this work, we survey the current state-of-the-art methods of ECG-based automated abnormalities heartbeat classification by presenting the ECG signal preprocessing, the heartbeat segmentation techniques, the feature description methods and the learning algorithms used. In addition, we describe some of the databases used for evaluation of methods indicated by a well-known standard developed by the Association for the Advancement of Medical Instrumentation (AAMI) and described in ANSI/AAMI EC57:1998/(R)2008 (ANSI/AAMI, 2008). Finally, we discuss limitations and drawbacks of the methods in the literature presenting concluding remarks and future challenges, and also we propose an evaluation process workflow to guide authors in future works.

Robust off-line heartbeat detection using ECG and pressure-signals

Artefacts in pressure- and ECG-signals generally arise due to different causes. Therefore, the combined analysis of both signals can increase the effectiveness of heartbeat detection compared to analysis using solely ECG-signals. In this paper, we present an algorithm for heartbeat annotation by combining the analysis of both the pressure- and ECG-signals. The novelties of our algorithm are as follows: (1) development of a new approach for annotating heartbeats using pressure-signals, (2) development of a mechanism that identifies and corrects paced rhythms, and (3) development of a noise detection approach. Our algorithm is tested on the datasets from the extended phase of the Physionet CINC-2014 challenge and produces an overall score of 87.31%. Finally, we put forth several recommendations that could further improve our algorithm.

Shape anomaly detection under strong measurement noise: An analytical approach to adaptive thresholding

We suggest an analytical approach to the adaptive thresholding in a shape anomaly detection problem. We find an analytical expression for the distribution of the cosine similarity score between a reference shape and an observational shape hindered by strong measurement noise that depends solely on the noise level and is independent of the particular shape analyzed. The analytical treatment is also confirmed by computer simulations and shows nearly perfect agreement. Using this analytical solution, we suggest an improved shape anomaly detection approach based on adaptive thresholding. We validate the noise robustness of our approach using typical shapes of normal and pathological electrocardiogram cycles hindered by additive white noise. We show explicitly that under high noise levels our approach considerably outperforms the conventional tactic that does not take into account variations in the noise level.

Semisupervised ECG Ventricular Beat Classification With Novelty Detection Based on Switching Kalman Filters

Automatic processing and accurate diagnosis of pathological electrocardiogram (ECG) signals remains a challenge. As long-term ECG recordings continue to increase in prevalence, driven partly by the ease of remote monitoring technology usage, the need to automate ECG analysis continues to grow. In previous studies, a model-based ECG filtering approach to ECG data from healthy subjects has been applied to facilitate accurate online filtering and analysis of physiological signals. We propose an extension of this approach, which models not only normal and ventricular heartbeats, but also morphologies not previously encountered. A switching Kalman filter approach is introduced to enable the automatic selection of the most likely mode (beat type), while simultaneously filtering the signal using appropriate prior knowledge. Novelty detection is also made possible by incorporating a third mode for the detection of unknown (not previously observed) morphologies, and denoted as X-factor. This new approach is compared to state-of-the-art techniques for the ventricular heartbeat classification in the MIT-BIH arrhythmia and Incart databases. F1 scores of 98.3% and 99.5% were found on each database, respectively, which are superior to other published algorithms' results reported on the same databases. Only 3% of all the beats were discarded as X-factor, and the majority of these beats contained high levels of noise. The proposed technique demonstrates accurate beat classification in the presence of previously unseen (and unlearned) morphologies and noise, and provides an automated method for morphological analysis of arbitrary (unknown) ECG leads.

Utility of a nonlinear joint dynamical framework to model a pair of coupled cardiovascular signals

We have recently proposed a correlated model to provide a Gaussian mixture representation of the cardiovascular signals, with promising results in identifying rhythm disturbances. The approach provides a transformation of the data into a set of integrable Gaussians distributed over time. Looking into the model from a new joint modeling perspective, it is capable of assembling a filtered estimation, and can be used to derive temporal information of the waveforms. In this paper, we present a step-by-step derivation of the joint model putting correlation assumptions together to conclude a minimal joint description for a pair of ECG-ABP signals. We then probe novel applications of this model, including Kalman filter based denoising and fiducial point detection. In particular, we use the joint model for denoising and employ the denoised signals for pulse transit time (PTT) estimation. We analyzed more than 70 h of data from 76 patients from the MIMIC database to illustrate the accuracy of the algorithm. We have found that this method can be effectively used for robust joint ECG-ABP noise suppression, with mean signal-to-noise ratio (SNR) improvement up to 23.2 (12.0) dB and weighted diagnostic distortion measures as low as 2.1 (3.3)% for artificial (real) noises, respectively. In addition, we have estimated the error distributions for QT interval, systolic and diastolic blood pressure before and after filtering to demonstrate the maximal preservation of morphological features (ΔQT: mean ± std = 2.2 ± 6.1 ms; ΔSBP: mean ± std = 2.3 ± 1.9 mmHg; ΔDBP: mean ± std = 1.9 ± 1.4 mmHg). Finally, we have been able to present a systematic approach for robust PTT estimation (r = 0.98, p <; 0.001, mean ± std of error = -0.26 ± 2.93 ms). These findings may have important implications for reliable monitoring and estimation of clinically important features in clinical settings. In conclusion, the proposed framework opens the door to the possibility of deploying a hybrid system that integrates these algorithmic approaches for index estimation and filtering scenarios with high output SNRs and low distortion.

A Bayesian-optimized spline representation of the electrocardiogram

We introduce an implementation of a novel spline framework for parametrically representing electrocardiogram (ECG) waveforms. This implementation enables a flexible means to study ECG structure in large databases. Our algorithm allows researchers to identify key points in the waveform and optimally locate them in long-term recordings with minimal manual effort, thereby permitting analysis of trends in the points themselves or in metrics derived from their locations. In the work described here we estimate the location of a number of commonly-used characteristic points of the ECG signal, defined as the onsets, peaks, and offsets of the P, QRS, T, and R' waves. The algorithm applies Bayesian optimization to a linear spline representation of the ECG waveform. The location of the knots-which are the endpoints of the piecewise linear segments used in the spline representation of the signal-serve as the estimate of the waveform's characteristic points. We obtained prior information of knot times, amplitudes, and curvature from a large manually-annotated training dataset and used the priors to optimize a Bayesian figure of merit based on estimated knot locations. In cases where morphologies vary or are subject to noise, the algorithm relies more heavily on the estimated priors for its estimate of knot locations. We compared optimized knot locations from our algorithm to two sets of manual annotations on a prospective test data set comprising 200 beats from 20 subjects not in the training set. Mean errors of characteristic point locations were less than four milliseconds, and standard deviations of errors compared favorably against reference values. This framework can easily be adapted to include additional points of interest in the ECG signal or for other biomedical detection problems on quasi-periodic signals.

Morphological modeling of cardiac signals based on signal decomposition

In this paper a general framework is presented for morphological modeling of cardiac signals from a signal decomposition perspective. General properties of a desired morphological model are presented and special cases of the model are studied in detail. The presented approach is studied for modeling the morphology of electrocardiogram (ECG) signals. Specifically, three types of ECG modeling techniques, including polynomial spline models, sinusoidal model and a model previously presented by McSharry et al., are studied within this framework. The proposed method is applied to datasets from the PhysioNet ECG database for compression and modeling of normal and abnormal ECG signals. Quantitative and qualitative results of these applications are also presented and discussed.

Parametric modelling of cardiac system multiple measurement signals: an open-source computer framework for performance evaluation of ECG, PCG and ABP event detectors

The major focus of this study is to present a performance accuracy assessment framework based on mathematical modelling of cardiac system multiple measurement signals. Three mathematical algebraic subroutines with simple structural functions for synthetic generation of the synchronously triggered electrocardiogram (ECG), phonocardiogram (PCG) and arterial blood pressure (ABP) signals are described. In the case of ECG signals, normal and abnormal PQRST cycles in complicated conditions such as fascicular ventricular tachycardia, rate dependent conduction block and acute Q-wave infarctions of inferior and anterolateral walls can be simulated. Also, continuous ABP waveform with corresponding individual events such as systolic, diastolic and dicrotic pressures with normal or abnormal morphologies can be generated by another part of the model. In addition, the mathematical synthetic PCG framework is able to generate the S4-S1-S2-S3 cycles in normal and in cardiac disorder conditions such as stenosis, insufficiency, regurgitation and gallop. In the PCG model, the amplitude and frequency content (5-700 Hz) of each sound and variation patterns can be specified. The three proposed models were implemented to generate artificial signals with varies abnormality types and signal-to-noise ratios (SNR), for quantitative detection-delineation performance assessment of several ECG, PCG and ABP individual event detectors designed based on the Hilbert transform, discrete wavelet transform, geometric features such as area curve length (ACLM), the multiple higher order moments (MHOM) metric, and the principal components analysed geometric index (PCAGI). For each method the detection-delineation operating characteristics were obtained automatically in terms of sensitivity, positive predictivity and delineation (segmentation) error rms and checked by the cardiologist. The Matlab m-file script of the synthetic ECG, ABP and PCG signal generators are available in the Appendix.

A dynamical model for generating synthetic Phonocardiogram signals

In this paper we introduce a dynamical model for Phonocardiogram (PCG) signal which is capable of generating realistic synthetic PCG signals. This model is based on PCG morphology and consists of three ordinary differential equations and can represent various morphologies of normal PCG signals. Beat-to-beat variation in PCG morphology is significant so model parameters vary from beat to beat. This model is inspired of Electrocardiogram (ECG) dynamical model proposed by McSharry et al. and can be employed to assess biomedical signal processing techniques.

A spline framework for ECG analysis

In this effort we introduce a spline framework for ECG waveform analysis, with initial application to the ECG delineation (segmentation) problem. The framework comprises knot initialization, spline interpolant, error metric, and knot location optimization to parametrically represent the waveform for analysis, classification, or compression. Choice of these constituents is driven by the application of the framework. For our initial application of ECG delineation, we use the framework to identify characteristic points corresponding to waveform onset and offset times, peak values, and junction points. These are represented mathematically as critical points and points of inflection, which serve as knot locations for linear or cubic Hermite interpolants in the framework. Preliminary tests on a limited but diverse set of morphologies from the European ST-T database indicate that the framework obtains knot locations corresponding to characteristic points, and the resultant interpolated waveform represents the original signal well with low mean squared error.

Synthetic ECG generation and Bayesian filtering using a Gaussian wave-based dynamical model

In this paper, we describe a Gaussian wave-based state space to model the temporal dynamics of electrocardiogram (ECG) signals. It is shown that this model may be effectively used for generating synthetic ECGs as well as separate characteristic waves (CWs) such as the atrial and ventricular complexes. The model uses separate state variables for each CW, i.e. P, QRS and T, and hence is capable of generating individual synthetic CWs as well as realistic ECG signals. The model is therefore useful for generating arrhythmias. Simulations of sinus bradycardia, sinus tachycardia, ventricular flutter, atrial fibrillation and ventricular tachycardia are presented. In addition, discrete versions of the equations are presented for a model-based Bayesian framework for denoising. This framework, together with an extended Kalman filter and extended Kalman smoother, was used for denoising the ECG for both normal rhythms and arrhythmias. For evaluating the denoising performance, the signal-to-noise ratio (SNR) improvement of the filter outputs and clinical parameter stability were studied. The results demonstrate superiority over a wide range of input SNRs, achieving a maximum 12.7 dB improvement. Results indicate that preventing clinically relevant distortion of the ECG is sensitive to the number of model parameters. Models are presented which do not exhibit such distortions. The approach presented in this paper may therefore serve as an effective framework for synthetic ECG generation and model-based filtering of noisy ECG recordings.

Robust detection of premature ventricular contractions using a wave-based Bayesian framework

Detection and classification of ventricular complexes from the ECG is of considerable importance in Holter and critical care patient monitoring, being essential for the timely diagnosis of dangerous heart conditions. Accurate detection of premature ventricular contractions (PVCs) is particularly important in relation to life-threatening arrhythmias. In this paper, we introduce a model-based dynamic algorithm for tracking the ECG characteristic waveforms using an extended Kalman filter. The algorithm can work on single or multiple leads. A "polargram"--a polar representation of the signal--is introduced, which is constructed using the Bayesian estimations of the state variables. The polargram allows the specification of a polar envelope for normal rhythms. Moreover, we propose a novel measure of signal fidelity by monitoring the covariance matrix of the innovation signals throughout the filtering procedure. PVCs are detected by simultaneous tracking the signal fidelity and the polar envelope. Five databases, including 40 records from MIT-BIH arrhythmia database, are used for differentiating normal, PVC, and other beats. Performance evaluation results show that the proposed method has an average detection accuracy of 99.10%, aggregate sensitivity of 98.77%, and aggregate positive predictivity of 97.47%. Furthermore, the method is capable of 100% accuracy for records that contain only PVCs and normal sinus beats. The results illustrate that the method can contribute to, and enhance the performance of clinical PVC detection.