Heart Rate Variability Dynamics for the Prognosis of Cardiovascular Risk

Abstract

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.

Influence of the Exercise on Autonomic Nervous System in Diabetics: A Literature Review

“…The autonomic changes induced by DM may represent an important negative factor, since autonomic function modulates some of the internal functions of the body and, in this sense, deserves attention. One way to access the autonomic nervous system (ANS) is thought the heart rate variability (HRV), tool that describes the oscillation of intervals between consecutive heart beats (RR intervals) and provides information about the diagnosis and prognosis of several diseases [12,13] . It has a potential to generate knowledge regarding to how neuropathy starts and in which pathway they can change sympathetic and parasympathetic branches.…”

Quantification of Diagnostic Information from Electrocardiogram Signal: A Review

“…The detail description of each of these diagnostic information extraction methods are given below. The heart rate variability features are widely used in applications like cardiovascular disease detection [21], diabetes diagnosis from ECG [22], prognosis of cardiac risk [23], identifying fatigue in elite athletes [24], monitoring sleep apnea from ECG [25] etc. The trace of RR interval with respect to number of beats is termed as heart rate signal.…”

Heart Rate Variability based Classification of Normal and Hypertension Cases by Linear-nonlinear Method

“…Initial normalisation was done between 0 and 1 with min-max normalisation procedure to avoid bias caused by unbalanced feature values. In this present study, to obtain good generalisation performance in correct choice of the regularisation parameter C and kernel parameter γ, an extensive search was carried out in the parameter space for the values of C є {2 −4 ,.., 2 15 } and γ є {2 −12 ,.., 2 5 } using 10-fold cross-validation on training data, as C attempts to maximise the margin while keeping low value for training error [20][21][22][23][24][25][27][28][29][30] . Out of 57 normal cases, two data sets were prepared which consisted of 25 cases for training and testing each.…”