Blood pressure estimation using neural networks

S. Colak, C. Isik

Research output: Chapter in Book/Entry/PoemConference contribution

23 Scopus citations

Abstract

Oscillometry is an indirect method to determine blood pressure. An inflatable and deflatable cuff is placed on arm to observe oscillations at different pressure levels. Thus, an envelope obtained from the oscillations is related to the blood pressure. In our work, we extract few features from the oscillometric waveforms, and estimate blood pressure using feedforward neural networks. Feature strength is evaluated by computing the standard deviation of the errors. The results are compared with the traditional maximum amplitude pressure algorithm. A large non-invasively collected database is used for this purpose.

Original languageEnglish (US)
Title of host publication2004 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA
Pages21-25
Number of pages5
StatePublished - 2004
Event2004 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA - Boston, MA, United States
Duration: Jul 14 2004Jul 16 2004

Publication series

Name2004 IEEE International Conference on Computational Intelligence for Measurements Systems and Applications, CIMSA

Other

Other2004 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA
Country/TerritoryUnited States
CityBoston, MA
Period7/14/047/16/04

Keywords

  • Blood pressure estimation
  • Neural networks
  • Oscillometry

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Blood pressure estimation using neural networks'. Together they form a unique fingerprint.

Cite this