Current Directions in Biomedical Engineering | |
Classification of morphologic changes in photoplethysmographic waveforms | |
Tigges Timo1  Pielmus Alexandru2  Orglmeister Reinhold2  Music Zenit2  Klum Michael2  Feldheiser Aarne3  Hunsicker Oliver3  | |
[1] Chair for Electronics and Medical Signal Processing, TU Berlin, 10587 Berlin, Germany;Chair for Electronics and Medical Signal Processing, TU Berlin, Berlin, Germany;Department of Anaesthesiology and Intensive Care Medicine, Campus Virchow-Klinikum, Charité - University Medicine Berlin, Berlin, Germany; | |
关键词: cardiovascular monitoring; machine learning; photoplethysmography; pulse waveform analysis; | |
DOI : 10.1515/cdbme-2016-0046 | |
来源: DOAJ |
【 摘 要 】
An 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.
【 授权许可】
Unknown