Classification of CO2 waveforms using artificial neural networks

Mohammad J. Navabi, Richard C. Watt, Kenneth C. Mylrea, Stuart R. Hameroff

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

A computer-based system for continuous analysis of CO2 waveforms for capnography has been developed which utilizes traditional algorithmic methods to partition the waveform and artificial neural networks for waveform classification. The system uses the CO2 waveform to detect the mode of breathing during anaesthesia. As initial steps, detection of spontaneous breaths, mechanical breaths, and mechanical breaths with attempts to breath against the ventilator was attempted. The system was trained on data from 5 surgical cases and was tested on 12 cases. Of 21 breaths with signs of patient attempts to breathe against the ventilator, 18 were properly identified by the system. There were no false identifications.

Original languageEnglish (US)
Title of host publicationBiomedical Engineering Perspectives
Subtitle of host publicationHealth Care Technologies for the 1990's and Beyond
PublisherPubl by IEEE
Pages1455-1456
Number of pages2
Editionpt 3
ISBN (Print)0879425598
StatePublished - 1990
EventProceedings of the 12th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Philadelphia, PA, USA
Duration: Nov 1 1990Nov 4 1990

Publication series

NameProceedings of the Annual Conference on Engineering in Medicine and Biology
Numberpt 3
ISSN (Print)0589-1019

Other

OtherProceedings of the 12th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CityPhiladelphia, PA, USA
Period11/1/9011/4/90

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'Classification of CO2 waveforms using artificial neural networks'. Together they form a unique fingerprint.

Cite this