Prediction of Sudden Cardiac Death Risk with a Support Vector Machine Based on Heart Rate Variability and Heartprint Indices.

Most methods for sudden cardiac death (SCD) prediction require long-term (24 h) electrocardiogram recordings to measure heart rate variability (HRV) indices or premature ventricular complex indices (with the heartprint method). This work aimed to identify the best combinations of HRV and heartprint indices for predicting SCD based on short-term recordings (1000 heartbeats) through a support vector machine (SVM). Eleven HRV indices and five heartprint indices were measured in 135 pairs of recordings (one before an SCD episode and another without SCD as control). SVMs (defined with a radial basis function kernel with hyperparameter optimization) were trained with this dataset to identify the 13 best combinations of indices systematically. Through 10-fold cross-validation, the best area under the curve (AUC) value as a function of γ (gamma) and cost was identified. The predictive value of the identified combinations had AUCs between 0.80 and 0.86 and accuracies between 80 and 86%. Further SVM performance tests on a different dataset of 68 recordings (33 before SCD and 35 as control) showed AUC = 0.68 and accuracy = 67% for the best combination. The developed SVM may be useful for preventing imminent SCD through early warning based on electrocardiogram (ECG) or heart rate monitoring.

Comparison of fetal heart rate variability by symbolic dynamics at the third trimester of pregnancy and low-risk parturition.

Fetal heart rate variability (fHRV) is an essential source of information to monitor fetal well-being during pregnancy. This study aimed to apply a nonlinear approach, known as symbolic dynamics (SD), for comparing human fHRV in the third trimester of pregnancy during active fetal state (TT) and active labor at term (P). We performed a longitudinal, prospective, descriptive, and comparative study composed of 42 longitudinal recordings of 5-minutes of fetal heartbeat interval series. Recordings were collected from 21 low-risk, healthy, pregnant women attending the Maternal and Child Research Center (CIMIGen), Mexico City. We calculated relevant linear parameters of fHRV between TT and P stages, such as the percentage of differences between adjacent RR intervals >5 ms (PRR5, related to vagal modulations) and other SD parameters such as the percentage of no variations between three successive symbols (%0V, reflects sympathetic modulations) and the probability of low variability with a threshold of 4 ms (POLVAR4, associated with a low variability). We identified statistical differences for PRR5 between TT and P (37.13% [28.47-47.60%] vs. 28.84% [19.36-36.76%], p = 0.03), respectively. Also, for 0V% (65.66% [59.01-71.80%] vs. 71.14% [65.94-75.87%], p = 0.03) and for POLVAR4 values (0.06 [0.04-0.11] vs. 0.15 [0.09-0.24], p = 0.002), respectively. Our results indicate that during parturition, the short-term fetal fHRV is decreased, showing a decreased vagal modulations and higher adrenergic response of the heart. These autonomic modifications may result from the fetal response to the stressful inflammatory challenge of labor. We thus confirmed that the analysis of the SD applied to fHRV time series could be a potential clinical biomarker to differentiate the fetal autonomic cardiac condition at different stages of pregnancy.

Symbolic analysis of heart rate fluctuations identifies cardiac autonomic modifications during LPS-induced endotoxemia.

The present study aimed to compare linear and symbolic dynamics (SD) indices for detecting the autonomic cardiac changes produced by endotoxemia in freely-moving rats. In this context, we analyzed ECG-derived R-R time series in freely moving Dark Agouti rats, which received lipopolysaccharide (LPS, n = 9), or vehicle (V, n = 7). Five minutes R-R time series were assessed every hour up to +12 h and + 24 h post-LPS injection. We found that SD indices showed significant differences at +7 h between V vs. LPS groups and at +9 h between basal levels of LPS (-3 h) and post-LPS injection (pre-LPS vs. post-LPS). In general, SD seems more appropriate than linear indices to evaluate the autonomic changes of endotoxemic rats. Overall, the symbolic parameters detected decreased R-R variability and complexity, which indicate a modification of the autonomic regulation during LPS-induced endotoxemia. This modification is probably related to a reduced activity of the cholinergic anti-inflammatory pathway at the long term.

Quantifying Effects of Pharmacological Blockers of Cardiac Autonomous Control Using Variability Parameters.

Objective: The aim of this study was to identify the most sensitive heart rate and blood pressure variability (HRV and BPV) parameters from a given set of well-known methods for the quantification of cardiovascular autonomic function after several autonomic blockades. Methods: Cardiovascular sympathetic and parasympathetic functions were studied in freely moving rats following peripheral muscarinic (methylatropine), ß1-adrenergic (metoprolol), muscarinic + ß1-adrenergic, α1-adrenergic (prazosin), and ganglionic (hexamethonium) blockades. Time domain, frequency domain and symbolic dynamics measures for each of HRV and BPV were classified through paired Wilcoxon test for all autonomic drugs separately. In order to select those variables that have a high relevance to, and stable influence on our target measurements (HRV, BPV) we used Fisher's Method to combine the p-value of multiple tests. Results: This analysis led to the following best set of cardiovascular variability parameters: The mean normal beat-to-beat-interval/value (HRV/BPV: meanNN), the coefficient of variation (cvNN = standard deviation over meanNN) and the root mean square differences of successive (RMSSD) of the time domain analysis. In frequency domain analysis the very-low-frequency (VLF) component was selected. From symbolic dynamics Shannon entropy of the word distribution (FWSHANNON) as well as POLVAR3, the non-linear parameter to detect intermittently decreased variability, showed the best ability to discriminate between the different autonomic blockades. Conclusion: Throughout a complex comparative analysis of HRV and BPV measures altered by a set of autonomic drugs, we identified the most sensitive set of informative cardiovascular variability indexes able to pick up the modifications imposed by the autonomic challenges. These indexes may help to increase our understanding of cardiovascular sympathetic and parasympathetic functions in translational studies of experimental diseases.

Sleep apnea-hypopnea quantification by cardiovascular data analysis.

Sleep disorders are a major risk factor for cardiovascular diseases. Sleep apnea is the most common sleep disturbance and its detection relies on a polysomnography, i.e., a combination of several medical examinations performed during a monitored sleep night. In order to detect occurrences of sleep apnea without the need of combined recordings, we focus our efforts on extracting a quantifier related to the events of sleep apnea from a cardiovascular time series, namely systolic blood pressure (SBP). Physiologic time series are generally highly nonstationary and entrap the application of conventional tools that require a stationary condition. In our study, data nonstationarities are uncovered by a segmentation procedure which splits the signal into stationary patches, providing local quantities such as mean and variance of the SBP signal in each stationary patch, as well as its duration L. We analysed the data of 26 apneic diagnosed individuals, divided into hypertensive and normotensive groups, and compared the results with those of a control group. From the segmentation procedure, we identified that the average duration , as well as the average variance <σ2>, are correlated to the apnea-hypoapnea index (AHI), previously obtained by polysomnographic exams. Moreover, our results unveil an oscillatory pattern in apneic subjects, whose amplitude S* is also correlated with AHI. All these quantities allow to separate apneic individuals, with an accuracy of at least 79%. Therefore, they provide alternative criteria to detect sleep apnea based on a single time series, the systolic blood pressure.

Diminished heart beat non-stationarities in congestive heart failure.

Studies on heart rate variability (HRV) have become popular and the possibility of diagnosis based on non-invasive techniques compels us to overcome the difficulties originated on the environmental changes that can affect the signal. We perform a non-parametric segmentation which consists of locating the points where the signal can be split into stationary segments. By finding stationary segments we are able to analyze the size of these segments and evaluate how the signal changes from one segment to another, looking at the statistical moments given in each patch, for example, mean and variance. We analyze HRV data for 15 patients with congestive heart failure (CHF; 11 males, 4 females, age 56±11 years), 18 elderly healthy subjects (EH; 11 males, 7 females, age 50±7 years), and 15 young healthy subjects (YH; 11 females, 4 males, age 31±6 years). Our results confirm higher variance for YH, and EH, while CHF displays diminished variance with p-values <0.01, when compared to the healthy groups, presenting higher HRV in healthy subjects. Moreover, it is possible to distinguish between YH and EH with p < 0.05 through the segmentation outcomes. We found high correlations between the results of segmentation and standard measures of HRV analysis and a connection to results of detrended fluctuation analysis (DFA). The segmentation applied to HRV studies detects aging and pathological conditions effects on the non-stationary behavior of the analyzed groups, promising to contribute in complexity analysis and providing risk stratification measures.

Prognostic value of natriuretic peptides in Chagas' disease: a head-to-head comparison of the 3 natriuretic peptides.

To determine the diagnostic and prognostic value of natriuretic peptides in patients with Chagas' disease (CD), the authors first measured atrial (ANP), B-type (BNP), and C-type natriuretic peptide (CNP) and compared their diagnostic and prognostic capacity with that in other dilated cardiomyopathies (DCM). The CD and DCM patients were subdivided according to their New York Heart Association (NYHA) classification. Circulating ANP and more pronounced BNP, but not CNP, were increased in CD and DCM patients in relation to NYHA class. Importantly, ANP and BNP were already significantly elevated in CD patients without systolic ventricular dysfunction. All 3 natriuretic peptides were correlated with echocardiographic parameters in CD patients. While ANP and BNP have high predictive value for mortality and necessity for heart transplant in CD, CNP can not predict them. Thus, ANP and BNP rather than CNP could be used as valuable molecular markers to identify asymptomatic CD patients for early therapy and predict clinical outcomes.

Ventricular arrhythmias and changes in heart rate preceding ventricular tachycardia in patients with an implantable cardioverter defibrillator.

The objective was to determine the characteristics of heart rate variability and ventricular arrhythmias prior to the onset of ventricular tachycardia (VT) in patients with an implantable cardioverter defibrillator (ICD). Sixty-eight beat-to-beat time series from 13 patients with an ICD were analyzed to quantify heart rate variability and ventricular arrhythmias. The episodes of VT were classified in one of two groups depending on whether the sinus rate in the 1 min preceding the VT was greater or less than 90 beats per minute. In a subset of patients, increased heart rate and reduced heart rate variability was often observed up to 20 min prior to the VT. There was a non-significant trend to higher incidence of premature ventricular complexes (PVCs) before VT compared to control recordings. The patterns of the ventricular arrhythmias were highly heterogeneous among different patients and even within the same patient. Analysis of the changes of heart rate and heart rate variability may have predictive value about the onset of VT in selected patients. The patterns of ventricular arrhythmia could not be used to predict onset of VT in this group of patients.

Prognostic value of natriuretic peptides in Chagas' disease: a 3-year follow-up investigation.

BACKGROUND: Chagas' disease (CD) affects around 18 million people in Latin America. To determine the diagnostic and prognostic value of natriuretic peptides in patients with CD, we measured atrial (ANP) and brain natriuretic peptide (BNP), and compared the findings with other dilated cardiomyopathies (DCM). METHODS: Blood samples were obtained from 111 CD patients, 62 patients with DCM due to other causes, and 43 gender- and age-matched healthy subjects. The CD and DCM patients were subdivided according to their NYHA classification. Natriuretic peptide concentrations were determined by immunoradiometric assays. RESULTS: ANP and more pronounced BNP levels were increased in CD and DCM patients in relation to the NYHA class. Circulating BNP concentrations were higher in CD patients in NYHA classes I-II than in the corresponding DCM patients (p = 0.020). Importantly, ANP and BNP were already significantly elevated in CD patients without systolic ventricular dysfunction (p < or = 0.001). In CD patients, both peptides were highly correlated with echocardiographic parameters (p < 10(-14)). Both ANP and BNP had comparable ability to predict death or the necessity for heart transplant (p < 0.0001). CONCLUSION: Natriuretic peptide levels can be used as a marker of asymptomatic CD without ventricular dysfunction and thus could be an ideal tool to identify these patients for early therapy.

Correlation dimension analysis of heart rate variability in patients with dilated cardiomyopathy.

A correlation dimension analysis of heart rate variability (HRV) was applied to a group of 55 patients with dilated cardiomyopathy (DCM) and 55 healthy subjects as controls. The 24-h RR time series for each subject was divided into segments of 10,000 beats to determine the correlation dimension (CD) per segment. A study of the influence of the time delay (lag) in the calculation of CD was performed. Good discrimination between both groups (p<0.005) was obtained with lag values of 5 or greater. CD values of DCM patients (8.4+/-1.9) were significantly lower than CD values for controls (9.5+/-1.9). An analysis of CD values of HRV showed that for healthy people, CD night values (10.6+/-1.8) were significant greater than CD day values (9.2+/-1.9), revealing a circadian rhythm. In DCM patients, this circadian rhythm was lost and there were no differences between CD values in day (8.8+/-2.4) and night (8.9+/-2.1).