Key result
A multi-layer perceptron neural network utilizing five selected heart rate variability features achieved a maximum classification accuracy of 96.67% in distinguishing cardiovascular risk patients from healthy subjects.
Why the study?
Does advanced heart rate variability (HRV) analysis combined with machine learning classifiers accurately discriminate between healthy subjects and patients at high cardiovascular risk?
Case-Control (n=90)
No
Does advanced heart rate variability (HRV) analysis combined with machine learning classifiers accurately discriminate between healthy subjects and patients at high cardiovascular risk?
Advanced heart rate variability analysis using non-linear and multi-resolution methods combined with machine learning can accurately identify patients at high cardiovascular risk.
Promising retrospective discrimination supports ML-HRV exploration; hypothesis-generating and should not yet change practice without prospective validation.
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.
No takes yet. Share an insight, caveat, or question.
Ramírez-Villegas et al. (2011) conducted a case-control in Cardiovascular risk (n=90). Heart rate variability (HRV) analysis using machine learning classifiers vs. Healthy controls was evaluated on Classification accuracy. A multi-layer perceptron neural network utilizing five selected heart rate variability features achieved a maximum classification accuracy of 96.67% in distinguishing cardiovascular risk patients from healthy subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: