Classification of Aortic Stiffness From Eigendecomposition of the Digital Volume Pulse Waveform

AbstractAn ever increasing number of research is examining the question to what extent physiological information beyond the blood oxygen saturation could be drawn from the photoplethysmogram. One important approach to elicit that information from the photoplethysmogram is the analysis of its waveform. One prominent example for the value of photoplethysmographic waveform analysis in cardiovascular monitoring that has emerged is hemodynamic compensation assessment in the peri-operative setting or trauma situations, as digital pulse waveform dynamically changes with alterations in vascular tone or pulse wave velocity. In this work, we present an algorithm based on modern machine learning techniques that automatically finds individual digital volume pulses in photoplethysmographic signals and sorts them into one of the pulse classes defined by Dawber et al. We evaluate our approach based on two major datasets – a measurement study that we conducted ourselves as well as data from the PhysioNet MIMIC II database. As the results are satisfying we could demonstrate the capabilities of classification algorithms in the automated assessment of the digital volume pulse waveform measured by photoplethysmographic devices.

Download Full-text

Clinical utility of digital volume pulse analysis in prediction of cardiovascular risk and the presence of angiographic coronary artery disease

Artery Research ◽

10.1016/j.artres.2014.10.001 ◽

2014 ◽

Vol 9 (C) ◽

pp. 33 ◽

Cited By ~ 1

Author(s):

Konstantinos Vakalis ◽

Aris Bechlioulis ◽

Katerina K. Naka ◽

Konstantinos Pappas ◽

Christos S. Katsouras ◽

...

Keyword(s):

Coronary Artery Disease ◽

Cardiovascular Risk ◽

Coronary Artery ◽

Clinical Utility ◽

Pulse Analysis ◽

Artery Disease ◽

Volume Pulse ◽

Digital Volume Pulse

Download Full-text

Pulse Waveform Classification Using Support Vector Machine with Gaussian Time Warp Edit Distance Kernel

Computational and Mathematical Methods in Medicine ◽

10.1155/2014/947254 ◽

2014 ◽

Vol 2014 ◽

pp. 1-10 ◽

Cited By ~ 4

Author(s):

Danbing Jia ◽

Dongyu Zhang ◽

Naimin Li

Keyword(s):

Quantitative Research ◽

Edit Distance ◽

Difficult Problem ◽

Average Error ◽

Support Vector ◽

Pulse Waveform ◽

Vector Machines ◽

Processing Techniques ◽

Gaussian Time

Advances in signal processing techniques have provided effective tools for quantitative research in traditional Chinese pulse diagnosis. However, because of the inevitable intraclass variations of pulse patterns, the automatic classification of pulse waveforms has remained a difficult problem. Utilizing the new elastic metric, that is, time wrap edit distance (TWED), this paper proposes to address the problem under the support vector machines (SVM) framework by using the Gaussian TWED kernel function. The proposed method, SVM with GTWED kernel (GTWED-SVM), is evaluated on a dataset including 2470 pulse waveforms of five distinct patterns. The experimental results show that the proposed method achieves a lower average error rate than current pulse waveform classification methods.

Download Full-text