Discrimination Power of Short-Term Heart Rate Variability Measures for CHF Assessment

Abstract

Abstract-In this study, we investigated the discrimination power of short-term Heart Rate Variability (HRV) for discriminating normal subjects versus Chronic Heart Failure (CHF) patients. We analyzed 1,914.40 hours of ECG of 83 patients of which 54 are normal and 29 are suffering from CHF with New York Heart Classification (NYHA) I, II, III, extracted by public databases. Following guidelines, we performed time and frequency analysis in order to measure HRV features. To assess the discrimination power of HRV features we designed a classifier based on the Classification and Regression Tree (CART) method, which is a non-parametric statistical technique, strongly effective on non-normal medical data mining. The best subset of features for subject classification includes RMSSD, total power, high frequencies power and the ratio between low and high Frequencies power (LF/HF). The classifier we developed achieved specificity and sensitivity values of 79.31% and 100% respectively. Moreover, we demonstrated that it is possible to achieve specificity and sensitivity of 89.7% and 100% respectively, by introducing two non-standard features ∆ ∆ ∆ ∆AVNN and ∆ ∆ ∆ ∆LF/HF, which account respectively for variation over the 24 hours of the average of consecutive normal intervals (AVNN) and LF/HF. Our results are comparable with other similar studies, but the method we used is particularly valuable because it allows a fully human-understandable description of classification procedures, in terms of intelligible "if … then …" rules.

Comparison of the Effects of Cross-validation Methods on Determining Performances of Classifiers Used in Diagnosing Congestive Heart Failure

“…Recently HRV analysis, which is derived from intervals between two adjacent peaks of ECG records, has been used in the patients with CHF [5,6,7,8,9,10,11]. For example, Isler and Kuntalp studied the CHF discrimination task using classical time-and frequency-domain measures by combining Wavelet Entropy measures and the Nearest Neighbor classifier resulting in the sensitivity rate of 79.3% and the specificity rate of 94.4% [5].…”

Discrimination power of long-term heart rate variability measures for chronic heart failure detection

“…CART was applied to HRV measures for other investigations, such as for the diagnosis of Obstructive Sleep Apnea Syndrome [31], and for the analysis of the relationship between HRV and the menstrual cycle in healthy young women [34]. We have adopted CART in previous studies, to investigate discrimination power of short-term HRV features [28][29] in distinguishing CHF patients from normal subjects and in assessing CHF severity. To the best of the authors' knowledge, CART has not yet been applied to long-term HRV analysis for CHF diagnosis.…”

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

“…The positive predictive accuracy of 98.19% is achieved for time domain features with the Back Propagation Neural Network (BPNN) classifier. Time domain-and frequency domain-based features are computed to separate normal and CHF classes in [59]. The Classification And Regression Tree (CART) method provided 96.4% classification accuracy.…”