Reduced Data Dualscale Entropy Analysis of HRV Signals for Improved Congestive Heart Failure Detection

Abstract

Heart rate variability (HRV) is an important dynamic variable of the cardiovascular system, which operates on multiple time scales. In this study, Multiscale entropy (MSE) analysis is applied to HRV signals taken from Physiobank to discriminate Congestive Heart Failure (CHF) patients from healthy young and elderly subjects. The discrimination power of the MSE method is decreased as the amount of the data reduces and the lowest amount of the data at which there is a clear discrimination between CHF and normal subjects is found to be 4000 samples. Further, this method failed to discriminate CHF from healthy elderly subjects. In view of this, the Reduced Data Dualscale Entropy Analysis method is proposed to reduce the data size required (as low as 500 samples) for clearly discriminating the CHF patients from young and elderly subjects with only two scales. Further, an easy to interpret index is derived using this new approach for the diagnosis of CHF. This index shows 100 % accuracy and correlates well with the pathophysiology of heart failure.

Multiscale Entropy Analysis with Low-Dimensional Exhaustive Search for Detecting Heart Failure

“…Some reports have indicated that the five and six MSE scales are significantly different between the CHF and NSR groups [47,49]. Others have reported that older CHF and NSR participants cannot be differentiated by MSE alone [43][44][45][46]. Our study shows that the {6} MSE scale is important because it is frequently involved, as shown in Tables 2 and 4; however, a single MSE scale is not sufficient for discrimination.…”

“…However, these HRV metrics are not applied to clinically diagnose heart failure, which means that the improvement of HRV analysis is still required. Besides, the use of MSE for discrimination between congestive heart failure (CHF) and healthy hearts in older people remains controversial [43][44][45][46]. Relatively few studies have evaluated MSE with machine learning in the detection of heart failure.…”

Detection of Congestive Heart Failure using Naive Bayes Classifier

“…This is a degenerative disease observed mostly in the aged people or someone who has suffered earlier from strokes [1][2][3]. From the literature it can be observed that electrocardiography signal (ECG), echocardiography, heart rate variability (HRV) signals are used to detect the CHF [3,[9][10][11][12][13]. Further, machine learning (ML) advancements have been instrumental in the quality and quick diagnosis of various types of diseases.…”

“…Machine learning techniques are getting improved continuously to tackle various types of data, like data of very big size, very scanty in size, again some are of nonlinear high dimensional type and so on [4][5][6]. Machine learning classifiers such as, k-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), classification and regression tree (CART), naive Bayes network (NB), random forest (RF), convolutional neural network (CNN), and various fuzzy classifiers are widely used in many works to detect different types of heart diseases [1][2][3][7][8][9][10][11][12][13]. Wijbenga et al [8] have performed an analysis on CHF patients by using parameters including left ventricular ejection fraction (LVEF), HRV triangular index (HTI), systolic pressure, HR and found significant change in these parameters for CHF patients.…”

The Performance of Short-Term Heart Rate Variability in the Detection of Congestive Heart Failure

“…There is also a wide range of studies that use multiscale entropy (MSE) as fundamental parameter as discriminative power [16]. As an example, a recent work has proposed the use of the reduced data dual-scale metrics in which the accuracy power has reached 100% using 500 RR samples (~10 minutes of ECG recordings) [17]. Yet, measures based on MSE are heavily biased on the number of samples, scales, and block analysis.…”