Detection and quantification of acute myocardial ischemia by morphologic evaluation of QRS changes by an angle-based method

Heart Rate Variability to Automatically Identify Hyperbaric States Considering Respiratory Component

This study's primary objective was to identify individuals whose physiological responses deviated from the rest of the study population by automatically monitoring atmospheric pressure levels to which they are exposed and using parameters derived from their heart rate variability (HRV). To achieve this, 28 volunteers were placed in a dry hyperbaric chamber, where they experienced varying pressures from 1 to 5 atmospheres, with five sequential stops lasting five minutes each at different atmospheric pressures. The HRV was dissected into two components: the respiratory component, which is linked to respiration; and the residual component, which is influenced by factors beyond respiration. Nine parameters were assessed, including the respiratory rate, four classic HRV temporal parameters, and four frequency parameters. A k-nearest neighbors classifier based on cosine distance successfully identified the atmospheric pressures to which the subjects were exposed to. The classifier achieved an 88.5% accuracy rate in distinguishing between the 5 atm and 3 atm stages using only four features: respiratory rate, heart rate, and two frequency parameters associated with the subjects' sympathetic responses. Furthermore, the study identified 6 out of 28 subjects as having atypical responses across all pressure levels when compared to the majority. Interestingly, two of these subjects stood out in terms of gender and having less prior diving experience, but they still exhibited normal responses to immersion. This suggests the potential for establishing distinct safety protocols for divers based on their previous experience and gender.

Dynamic Bayesian Model for Detecting Obstructive Respiratory Events by Using an Experimental Model

In this study, we propose a model-based tool for the detection of obstructive apnea episodes by using ECG features from a single lead channel. Several sequences of recurrent apnea were provoked in separate 15-min periods in anesthetized rats during an experimental model of obstructive sleep apnea (OSA). Morphology-based ECG markers and the beat-to-beat interval (RR) were assessed in each sequence. These markers were used to train dynamic Bayesian networks (DBN) with different orders and feature combinations to find a good tradeoff between network complexity and apnea-detection performance. By using a filtering approach, the resulting DBNs were used to infer the apnea probability signal for subsequent episodes in the same rat. These signals were then processed using by 15-s epochs to determine whether epochs were classified as apneic or nonapneic. Our results showed that fifth-order models provided suitable RMSE values, since higher order models become significantly more complex and present worse generalization. A global threshold of 0.2 gave the best overall performance for all combinations tested, with Acc = 81.3%, Se = 69.8% and Sp = 81.5%, using only two parameters including the RR and Ds (R-wave downslope) markers. We concluded that multivariate models using DBNs represent a powerful tool for detecting obstructive apnea episodes in short segments, which may also serve to estimate the number of total events in a given time period.

Multivariate ensemble classification for the prediction of symptoms in patients with Brugada syndrome

Identification of asymptomatic patients at higher risk for suffering cardiac events remains controversial and challenging in Brugada syndrome (BS). In this work, we proposed an ECG-based classifier to predict BS-related symptoms, by merging the most predictive electrophysiological features derived from the ventricular depolarization and repolarization periods, along with autonomic-related markers. The initial feature space included local and dynamic ECG markers, assessed during a physical exercise test performed in 110 BS patients (25 symptomatic). Morphological, temporal and spatial properties quantifying the ECG dynamic response to exercise and recovery were considered. Our model was obtained by proposing a two-stage feature selection process that combined a resampled-based regularization approach with a wrapper model assessment for balancing, simplicity and performance. For the classification step, an ensemble was constructed by several logistic regression base classifiers, whose outputs were fused using a performance-based weighted average. The most relevant predictors corresponded to the repolarization interval, followed by two autonomic markers and two other makers of depolarization dynamics. Our classifier allowed for the identification of novel symptom-related markers from autonomic and dynamic ECG responses during exercise testing, suggesting the need for multifactorial risk stratification approaches in order to predict future cardiac events in asymptomatic BS patients. Graphical abstract Pipeline for feature selection and predictive modeling of symptoms in Brugada syndrome.

An integrated framework for evaluation on typical ECG-derived respiration waveform extraction and respiration

OBJECTIVE

ECG-derived respiration (EDR) methods have been developed during the past decades to obtain respiration-relevant information. However, it is still necessary to compare the performance of these methods under uniform conditions for reasonable application.

APPROACH

In this paper, the performance of 10 feature-based EDR methods was evaluated comprehensively on three aspects: sampling rate, noise, and window length. The Fantasia database was used in this study, as it contained ECG signals and simultaneously measured respiration signals. The performance was quantified by two parameters: waveform correlation and breathing rate (BR) errors.

MAIN RESULTS

The BR errors of AM_area, AM_QR, AM_R were all below 2 beats per minute (bpm) when the sampling rate was above 150 Hz, while they decreased sharply by about 60% when the sampling rate was below 150 Hz. FM_RR presented stable performance with an error below 2 bpm at different sampling rates. The effect of noise was obviously found in amplitude-based EDR methods, with the maximum decreased by about 40% in waveform correlation. For all EDR methods, significant increase of BR errors occurred with the window shorting from 32 s to 16 s in the frequency-based technique. In addition, about 30%-40% of the window cannot obtain the BR error, calculated based on the time-based technique, within an 8 s window.

SIGNIFICANCE

We proposed a comprehensive and integrated evaluation on typical ECG-derived respiration waveform extraction and respiration rate calculation, providing references for algorithm selection based on different requirements.

Diagnostic Interpretation of Non-Uniformly Sampled Electrocardiogram

We present a set of three fundamental methods for electrocardiogram (ECG) diagnostic interpretation adapted to process non-uniformly sampled signal. The growing volume of ECGs recorded daily all over the world (roughly estimated to be 600 TB) and the expectance of long persistence of these data (on the order of 40 years) motivated us to challenge the feasibility of medical-grade diagnostics directly based on arbitrary non-uniform (i.e., storage-efficient) ECG representation. We used a refined time-independent QRS detection method based on a moving shape matching technique. We applied a graph data representation to quantify the similarity of asynchronously sampled heartbeats. Finally, we applied a correlation-based non-uniform to time-scale transform to get a multiresolution ECG representation on a regular dyadic grid and to find precise P, QRS and T wave delimitation points. The whole processing chain was implemented and tested with MIT-BIH Database (probably the most referenced cardiac database) and CSE Multilead Database (used for conformance testing of medical instruments) signals arbitrarily sampled accordingly to a perceptual model (set for variable sampling frequency of 100-500 Hz, compression ratio 3.1). The QRS detection shows an accuracy of 99.93% with false detection ratio of only 0.18%. The classification shows an accuracy of 99.27% for 14 most frequent MIT-BIH beat types and 99.37% according to AAMI beat labels. The wave delineation shows cumulative (i.e., sampling model and non-uniform processing) errors of: 9.7 ms for P wave duration, 3.4 ms for QRS, 6.7 ms for P-Q segment and 17.7 ms for Q-T segment, all the values being acceptable for medical-grade interpretive software.

Assessing heart disease using a novel magnetocardiography device

The aim of this paper is to present the use of a portable, unshielded magnetocardiograph (MCG) and identify key characteristics of MCG scans that could be used in future studies to identify parameters that are sensitive to cardiac pathology. We recruited 50 patients with confirmed myocardial infarction (MI) within the past 12 weeks and 46 volunteers with no history of cardiac disease. A set of 38 parameters were extracted from MCG features including both signals from the sensor array and from magnetic images obtained from the device and principal component analysis was used to concentrate the information contained in these parameters into uncorrelated predictors. Linear fits of these parameters were then used to examine the ability of MCG to distinguish between sub-groups of patients. In the fist instance, the primary aim of this study was to ensure that MCG has a basic ability to separate a highly polarised patient group (young controls from post infarction patients) and to identify parameters that could be used in future studies to build a formal diagnostic tool kit. Parameters that parameterised left ventricular ejection fraction (LVEF) were identified and an example is presented to show differential low and high ejection fractions.

Hypoxia-induced Effects on ECG Depolarization by Time Warping Analysis during Recurrent Obstructive Apnea

In this work, we evaluated a non-linear approach to estimate morphological variations in ECG depolarization, in the context of intermittent hypoxia (IH). Obstructive apnea sequences were provoked for 15 minutes in anesthetized Sprague-Dawley rats, alternating with equal periods of normal breathing, in a recurrent obstructive sleep apnea (OSA) model. Each apnea episode lasted 15 s, while the frequency used for each sequence was randomly selected. Average heartbeats obtained before the start and at the end of each episode, were delineated to extract only the QRS wave. Then, the segmented QRS waves were non-linearly aligned using the dynamic time warping (DWT) algorithm. Morphological QRS changes in both the amplitude and temporal domains were estimated from this alignment procedure. The hypoxic and basal segments were analyzed using ECG (lead I) recordings acquired during the experiment. To assess the effects of IH over time, the changes relative to the basal QRS wave were determined, in the intervals prior to each successive events until the end of the experiment. The results showed a progressive increase in the amplitude and time-domain morphological markers of the QRS wave along the experiment, which were strongly correlated with the changes in traditional QRS markers (r ≈ 0.9). Significant changes were found between pre-apnea and hypoxic measures only for the time-domain analysis (p<0.001), probably due to the short duration of the simulated apnea episodes.Clinical relevance Increased variability in ECG depolarization morphology during recurrent hypoxic episodes would be closely related to the expression of cardiovascular dysfunction in OSA patients.

A novel low-complexity post-processing algorithm for precise QRS localization

Precise localization of QRS complexes is an essential step in the analysis of small transient changes in instant heart rate and before signal averaging in QRS morphological analysis. Most localization algorithms reported in literature are either not robust to artifacts, depend on the sampling rate of the ECG recordings or are too computationally expensive for real-time applications, especially in low-power embedded devices. This paper proposes a localization algorithm based on the intersection of tangents fitted to the slopes of R waves detected by any QRS detector. Despite having a lower complexity, this algorithm achieves comparable trigger jitter to more complex localization methods without requiring the data to first be upsampled. It also achieves high localization precision regardless of which QRS detector is used as input. It is robust to clipping artifacts and to noise, achieving an average localization error below 2 ms and a trigger jitter below 1 ms on recordings where no additional artifacts were added, and below 8 ms for recordings where the signal was severely degraded. Finally, it increases the accuracy of template-based false positive rejection, allowing nearly all mock false positives added to a set of QRS detections to be removed at the cost of a very small decrease in sensitivity. The localization algorithm proposed is particularly well-suited for implementation in embedded, low-power devices for real-time applications.

Transient and rapid QRS-widening associated with a J-wave pattern predicts impending ventricular fibrillation in experimental myocardial infarction

BACKGROUND

Certain types of the early repolarization phenomenon, previously considered to be benign, have been reported to be associated with ventricular fibrillation (VF), both in population-based studies and in the myocardial infarction (MI) settings.

OBJECTIVE

To analyze whether QRS widening and appearance of a J-wave pattern in experimental MI settings is predictive of VF.

METHODS

MI was induced in 32 pigs by 40-minute inflation of an angioplasty balloon in the left descending artery, and electrocardiogram was continuously recorded. Multilead QRS boundaries were computed, and QRS duration was calculated on a beat-to-beat basis during the occlusion period for each pig. An association between QRS widening and subsequent VF was studied using receiver operating characteristic curve analysis. Electrocardiograms at maximum QRS duration were reviewed for the presence of a J-wave pattern.

RESULTS

Sixteen animals had VF episodes during the occlusion period. Two peaks of QRS widening were found in all animals: the first peak immediately on left descending artery occlusion and the second peak 19.1 ± 4.0 minutes later. The magnitude of changes in the QRS width over time had significant interindividual differences. A QRS widening of ≥28 ms during a 3-minute time window was observed in 14 animals and predicted impending VF (selectivity 80%, specificity 73%, positive predictive value 57%, and negative predictive value 89%; P = .008). In 10 of 14 (71%) pigs, a J-wave pattern appeared at maximal QRS duration. The appearance of a J-wave pattern predicted VF with selectivity 80%, specificity 68%, positive predictive value 53%, and negative predictive value 88% (P = .02).

CONCLUSION

Transient QRS widening, commonly associated with a J-wave pattern, appears to predict impending VF in acute ischemia settings and motivates further clinical studies for monitoring immediate risk of VF in MI.