Open AccessA New Entropy-Based Heart Failure Detector
Author(s) -
Jinle Xiong,
Xueyu Liang,
Chengyu Liu
Publication year - 2020
Publication title -
2019 computing in cardiology (cinc)
Language(s) - English
Resource type - Conference proceedings
SCImago Journal Rank - 0.257
H-Index - 55
ISSN - 2325-887X
ISBN - 978-1-7281-6936-1
DOI - 10.22489/cinc.2019.060
Subject(s) - bioengineering , computing and processing , signal processing and analysis
Heart failure is a common type of clinical cardiovascular disease and has a high prevalence, disability and fatality rate. Entropy measures, typically as sample entropy (SampEn), has been used in clinic for detecting heart failure. However, SampEn values are sensitive to the selection of threshold r, resulting in a difficulty in the clinical interpretation. This study proposed a new entropy measure named sample difference entropy (SampDEn), for distinguishing congestive heart failure (CHF) patients from normal sinus rhythm (NSR) subjects. Unlike SampEn, the new SampDEn calculated the entropy value by comparing the information increase rate at two threshold settings of r max and r min , to reduce the statistical instability of SampEn due to the single threshold decision. The new algorithm was tested on the MIT-BIH RR Interval Databases. For 300 RR interval time series, the new proposed SampDEn reported an accuracy of 70.46% while SampEn reported 69.18%, 60.47%, 51.21% and 43.27% for r=0.1, 0.15, 0.2 and 0.25 respectively. For 1,000 RR interval time series, SampDEn reported an accuracy of 75.33% while SampEn reported 68.34%, 56.09%, 44.85% and 36.76% for r=0.1, 0.15, 0.2 and 0.25 respectively. The results suggested that the new SampDEn method is more effective for identifying CHF and NSR subjects than the traditional SampEn.