SVM classification for discriminating cardiovascular disease patients from non-cardiovascular disease controls using pulse waveform variability analysis

Authors:
Kuanquan Wang;Lu Wang;Dianhui Wang;Lisheng Xu
Affiliations:
Department of Computer Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China;Department of Computer Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China;Department of Computer Science and Computer Engineering, La Trobe University, Melbourne, VIC, Australia;Department of Computer Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 5
Cited 1

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Nonlinear Biomedical Signal Processing: Fuzzy Logic, Neural Networks, and New Algorithms

Nonlinear Biomedical Signal Processing: Fuzzy Logic, Neural Networks, and New Algorithms
Adaptive Baseline Wander Removal in the Pulse Waveform

CBMS '02 Proceedings of the 15th IEEE Symposium on Computer-Based Medical Systems (CBMS'02)
Approximate entropy based pulse variability analysis

CBMS'03 Proceedings of the 16th IEEE conference on Computer-based medical systems

Accurate cirrhosis identification with wrist-pulse data for mobile healthcare

Proceedings of the Second ACM Workshop on Mobile Systems, Applications, and Services for HealthCare

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper analyzes the variability of pulse waveforms by means of approximate entropy (ApEn) and classifies three group objects using support vector machines (SVM) The subjects were divided into three groups according to their cardiovascular conditions Firstly, we employed ApEn to analyze three groups' pulse morphology variability (PMV) The pulse waveform's ApEn of a patient with cardiovascular disease tends to have a smaller value and its variation's spectral contents differ greatly during different cardiovascular conditions Then, we applied a SVM to discriminate cardiovascular disease patients from non-cardiovascular disease controls The specificity and sensitivity for clinical diagnosis of cardiovascular system is 85% and 93% respectively The proposed techniques in this paper, from a long-term PMV analysis viewpoint, can be applied to a further research on cardiovascular system.