Optimal Timing in Screening Patients with Congestive Heart Failure and Healthy Subjects During Circadian Observation

Abstract

Congestive heart failure (CHF) is a major medical challenge in developed countries. In order to screen patients with CHF and healthy subjects during circadian observation, accurate judgment and fast response are imperative. In this study, optimal timing during circadian observation via the heart rate variability (HRV) was sought. We tested 29 CHF patients and 54 healthy subjects in the control group from the interbeat interval databases of PhysioBank. By invoking the α1 parameter in detrended fluctuation analysis of HRV, we found that it could be used as an indicator to screen the patients with CHF and subjects in normal sinus rhythm (NSR) under Kruskal-Wallis test. By invoking Fano factor, the optimal timing to screen CHF patients and healthy subjects was found to be from 7 PM to 9 PM during the circadian observation. In addition, this result is robust in a sense that the same result can be achieved by using different ECG recording lengths of 2, 5, 10, … , and 120 min, respectively. Furthermore, a support vector machine was employed to classify CHF and NSR with α1 parameter of a moving half-hour ECG recordings via leave-one-out cross validation. The results showed that the superlative screening performance was obtained in the 7 pm-9 pm period during circadian observation. It is believed that this result of optimal timing will be helpful in the non-invasive monitoring and screening of CHF patients and healthy subjects in the clinical practice.

Multiscale Entropy Analysis of the Differential RR Interval Time Series Signal and Its Application in Detecting Congestive Heart Failure

“…HRV analysis has given an insight into understanding the abnormalities of CHF, and can be used to identify the higher-risk CHF patients [9][10][11][12][13]. Depressed HRV has been used as a risk predictor in CHF [14][15][16].…”

Use of Accumulated Entropies for Automated Detection of Congestive Heart Failure in Flexible Analytic Wavelet Transform Framework Based on Short-Term HRV Signals

“…We can observe from Table 7 that p-values are significantly low (p-value <0.05) for all of the features, except AFEnt for SH 1 and APEnt for SL 5 and SL 4 . The classification accuracy of the LS-SVM classifier for the ranked features with the different kernels used in this work is shown in Figure 7.…”

“…The Classification And Regression Tree (CART) method provided 96.4% classification accuracy. The Detrended Fluctuation Analysis (DFA)-based features with SVM yielded 96% classification accuracy to discriminate normal and CHF HRV signals in [4]. In [60], the authors have studied time domain features, frequency domain features and bispectrum features to analyze HRV signals of CHF and normal subjects.…”

“…Dyspnea, edema and fatigue are the common symptoms of CHF [2,3]. It is the last stage of several cardiac diseases namely; heart valve disease, Myocardial Infarction (MI) and dilated cardiomyopathy [4]. In many cases, CHF is not discernible.…”

“…The discrimination ability of non-linear features is found to be better than linear features. Various nonlinear features, such as Detrended Fluctuation Analysis (DFA) [4], approximate entropy [28] and sample entropy [28], are found to be effective in the analysis of CHF HRV signals.…”