Limits...
Heart rate variability dynamics for the prognosis of cardiovascular risk.

Ramirez-Villegas JF, Lam-Espinosa E, Ramirez-Moreno DF, Calvo-Echeverry PC, Agredo-Rodriguez W - PLoS ONE (2011)

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: Computational Neuroscience, Department of Physics, Universidad Autonoma de Occidente, Cali, Colombia. juanfelipe.rv@gmail.com

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.

Show MeSH
PCA transform of multi-resolution features of the 5-min HRV records from Normal (black diamond) and cardiovascular risk (red square) subjects.(a) entropy features and, (b) energy features.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3046173&req=5

pone-0017060-g004: PCA transform of multi-resolution features of the 5-min HRV records from Normal (black diamond) and cardiovascular risk (red square) subjects.(a) entropy features and, (b) energy features.

Mentions: Standard PCA was applied to the multi-resolution measures in order to obtain the most relevant features in terms of variance. The total of selected groups of wavelet coefficients was 26 out of 62 (the total of wavelet packet coefficients from a decomposition level of 5). These 26 groups of coefficients, according to the PCA, retain approximately 98% of the variance of the model; however, the features projections given by this transformation were not used to train the classifiers due to the decreasing statistical significance of the projected features. The main results of PCA for the two principal components are illustrated in Figure 4. The second principal component projection showed statistical significance in both energy and entropy wavelet features; these two features retain approximately 50% of the variance of the model. In this analysis, even the third component showed statistical significance; however, the rest of the projected data were not significantly different or discriminative between normal and cardiovascular risk subjects.


Heart rate variability dynamics for the prognosis of cardiovascular risk.

Ramirez-Villegas JF, Lam-Espinosa E, Ramirez-Moreno DF, Calvo-Echeverry PC, Agredo-Rodriguez W - PLoS ONE (2011)

PCA transform of multi-resolution features of the 5-min HRV records from Normal (black diamond) and cardiovascular risk (red square) subjects.(a) entropy features and, (b) energy features.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3046173&req=5

pone-0017060-g004: PCA transform of multi-resolution features of the 5-min HRV records from Normal (black diamond) and cardiovascular risk (red square) subjects.(a) entropy features and, (b) energy features.
Mentions: Standard PCA was applied to the multi-resolution measures in order to obtain the most relevant features in terms of variance. The total of selected groups of wavelet coefficients was 26 out of 62 (the total of wavelet packet coefficients from a decomposition level of 5). These 26 groups of coefficients, according to the PCA, retain approximately 98% of the variance of the model; however, the features projections given by this transformation were not used to train the classifiers due to the decreasing statistical significance of the projected features. The main results of PCA for the two principal components are illustrated in Figure 4. The second principal component projection showed statistical significance in both energy and entropy wavelet features; these two features retain approximately 50% of the variance of the model. In this analysis, even the third component showed statistical significance; however, the rest of the projected data were not significantly different or discriminative between normal and cardiovascular risk subjects.

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: Computational Neuroscience, Department of Physics, Universidad Autonoma de Occidente, Cali, Colombia. juanfelipe.rv@gmail.com

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.

Show MeSH