Potential of feature selection methods in heart rate variability analysis for the classification of different cardiovascular diseases

Abstract

In this study heart rate variability (HRV) analysis was applied to characterize patients suffering from coronary heart disease (CHD), dilated cardiomyopathy (DCM) and patients who had survived an acute myocardial infarction (MI). On the basis of several HRV parameters, an optimal discrimination between the different kinds of cardiovascular diseases and between the diseases and healthy controls (HC) was derived by feature selection and linear classification. For each task a small favourable subset of a set of 33 potentially interesting HRV measures was selected with the intention of improving the diagnostic value and facilitating the physiological interpretation of HRV analysis. Time- and frequency-domain parameters as well as parameters from non-linear dynamics were included in the analysis. With the expectation that different diseases are characterized by different phenomena, feature selection was applied for each task separately. Using the features optimal for one task to another task can reveal a loss in performance, but it turned out that one specific parameter set (set1: normalized low frequency LF/P and a non-linear variability measure WPSUM13) was applicable for all tasks, where diseased and healthy subjects have to be distinguished, without significant reduction in performance. This set seems to be a general marker for pathologic changes in HRV and might be used for early detection of heart diseases. The classification between different heart diseases requires another parameter set (set2: meanNN and sdaNN, reflecting the steady state behaviour of the heart rate and long and short term SEAR describing the spectral composition). However, the use of set1 for the separation of different kinds of diseases, where set2 is appropriate, led to significant reduction in performance and vice versa. This observation may be important for future developments of HRV measures especially suitable for the assessment of disease severity.

Automated diagnosis of coronary artery disease using tunable-Q wavelet transform applied on heart rate signals

“…Other than heart disorders, the heart rate signals can be used for diagnosis of diseases like diabetic neuropathies, and depression [10,[12][13][14][15]. They are cheap and can be acquired from ECG signals.…”

Cardiac autonomic modulation induced by doxorubicin in a rodent model of colorectal cancer and the influence of fullerenol pretreatment

“…A powerful noninvasive tool that allows studying the autonomic cardiovascular modulation is the analysis of heart rate variability (HRV) [21–23]. The reduction in HRV is strongly related to the severity of heart disease [24,25] and could have a reliable prognostic value for its clinical outcome [24–29]. Furthermore, the study of DeAngelis et al [30] reported that alterations in autonomic modulation may be an initiating mechanism underlying the onset of cardiovascular diseases.…”

Dynamical non-linear analysis of heart rate variability in patients with aortic stenosis

“…During recent years, non-linear analysis of Heart Rate Variability (HRV) has been used to characterize healthy people and a variety of heart diseases and different levels of risk [1][2][3][4][5].…”

“…">IntroductionDuring recent years, non-linear analysis of Heart Rate Variability (HRV) has been used to characterize healthy people and a variety of heart diseases and different levels of risk [1][2][3][4][5].Different non-linear measures are used for this purpose, like Hurst and Lyapunov exponents, entropies, complexity and information indexes, symbolic logic and dimensional analysis. This latter one, estimates the dimension of the attractor formed by the set of points in the phase space, which is a statistical measure of the self similarity of the geometry of points and is related to the number of independent variables (degrees of freedom) needed to generate a corresponding process.…”