Paper Info
Title
The Novel Indices of Short-Time Heart Rate Variability for Prediction of Cardiovascular and Cerebrovascular Events
Abstract
In this paper, eight novel instantaneous indices of short-time heart rate variability (HRV) signals are proposed for prediction of cardiovascular and cerebrovascular events. The indices are based on Bubble Entropy (BE) and Singular Value Decompose (SVD). The process of indices calculation is as follows, firstly, the instantaneous amplitude (IA), instantaneous frequency (IF) and instantaneous phase (IP) of HRV signals are estimated by the Hilbert transform. Secondly, according to the HRV, IA, IP and IF, the BE and singular value (SV) is calculated, then eight novel indices are obtained, they are BEHRA, BEIA, BEIF, BEIP, SVHRV, SVIA, SVIF and SVIP. Last but not least, in order to evaluate the performance of the eight novel indices for prediction of cardiovascular and cerebrovascular events, the difference analysis of eight indices is carried out by f-test. According to the p value, seven of the eight indices BEHRV, BEIA, BEIF, BEIP, SVIA, SVIF, SVIP are thought to be the indices to discriminate the E group and N group. The 'K-nearest neighbor (KNN), support vector machine (SVM) and decision tree (DT) are applied on the seven novel indices. The results are that, seven novel indices are significantly different between the events and non-events groups, and the SVM classifier has the highest classification Acc and Spe for prediction of cardiovascular and cerebrovascular events, they are 88.31% and 90.19%, respectively.
Year
DOI
Venue
2020
10.1166/jmihi.2020.2931
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS
Keywords
DocType
Volume
Heart Rate Variability (HRV),Hilbert Transform,Bubble Entropy (BE),Singular Value Decompose (SVD)
Journal
10
Issue
ISSN
Citations 
3
2156-7018
0
PageRank 
References 
Authors
0.34
0
6
Name
Order
Citations
PageRank
Shiliang Shao152.87
Wang Ting25514.14
Chunhe Song3187.66
Yun Su484.23
Xingchi Chen531.46
Hai Zhao6960113.64