Integration of operating room monitors for development of a smart alarm system.

Persistent Link:
http://hdl.handle.net/10150/185184
Title:
Integration of operating room monitors for development of a smart alarm system.
Author:
Navabi-Shirazi, Mohammad Jafar.
Issue Date:
1990
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
A computer based system was designed and used to collect physiologic and respiratory data (13 variables and 3 waveforms) from six routinely used operating room monitors. 23 hours of data were collected during 20 general surgery cases (ASA III patients). Part of the data were used to design and implement an integrated monitor with intelligent alarm capability. The system used a rule based approach to reduce false alarms and artificial neural networks (ANN) for classification of physiological waveforms. The integrated monitor was able to correctly identify 13 of 17 intubations which resulted in a 42% reduction in low end-tidal-CO₂ false alarms. False heart rate alarms were reduced to 2.6% of total alarms using multi-variable analysis and rate of change limits. A combination of ANN's and an edge detection filter was used to classify CO₂ waveforms into spontaneous, mechanical, and mechanical with spontaneous breathing attempts. The edge detection algorithm was able to detect 171 of 182 breaths. The ANN's properly classified 65 of 67 mechanical, 47 of 71 spontaneous, and 37 of 44 mechanical breaths with spontaneous breathing attempts. Another ANN was used for detection of elevated and depressed ST segments in the ECG signal. All ST segment elevations and depressions of 0.1 mV were correctly identified. An attempt was made to use ANN's to classify ECG waveforms according to anesthetic levels. However, the back-propagation algorithm used to train the network did not converge perhaps due to the variety of drugs used in the different cases. The system met our goals of providing an integrated operating room monitor with intelligent alarm capability. The system significantly reduced false heart rate alarms, detected intubation and classified ECG and CO₂ waveforms.
Type:
text; Dissertation-Reproduction (electronic)
Keywords:
Engineering.
Degree Name:
Ph.D.
Degree Level:
doctoral
Degree Program:
Electrical and Computer Engineering; Graduate College
Degree Grantor:
University of Arizona
Advisor:
Mylrea, Kenneth C.

Full metadata record

DC FieldValue Language
dc.language.isoenen_US
dc.titleIntegration of operating room monitors for development of a smart alarm system.en_US
dc.creatorNavabi-Shirazi, Mohammad Jafar.en_US
dc.contributor.authorNavabi-Shirazi, Mohammad Jafar.en_US
dc.date.issued1990en_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractA computer based system was designed and used to collect physiologic and respiratory data (13 variables and 3 waveforms) from six routinely used operating room monitors. 23 hours of data were collected during 20 general surgery cases (ASA III patients). Part of the data were used to design and implement an integrated monitor with intelligent alarm capability. The system used a rule based approach to reduce false alarms and artificial neural networks (ANN) for classification of physiological waveforms. The integrated monitor was able to correctly identify 13 of 17 intubations which resulted in a 42% reduction in low end-tidal-CO₂ false alarms. False heart rate alarms were reduced to 2.6% of total alarms using multi-variable analysis and rate of change limits. A combination of ANN's and an edge detection filter was used to classify CO₂ waveforms into spontaneous, mechanical, and mechanical with spontaneous breathing attempts. The edge detection algorithm was able to detect 171 of 182 breaths. The ANN's properly classified 65 of 67 mechanical, 47 of 71 spontaneous, and 37 of 44 mechanical breaths with spontaneous breathing attempts. Another ANN was used for detection of elevated and depressed ST segments in the ECG signal. All ST segment elevations and depressions of 0.1 mV were correctly identified. An attempt was made to use ANN's to classify ECG waveforms according to anesthetic levels. However, the back-propagation algorithm used to train the network did not converge perhaps due to the variety of drugs used in the different cases. The system met our goals of providing an integrated operating room monitor with intelligent alarm capability. The system significantly reduced false heart rate alarms, detected intubation and classified ECG and CO₂ waveforms.en_US
dc.typetexten_US
dc.typeDissertation-Reproduction (electronic)en_US
dc.subjectEngineering.en_US
thesis.degree.namePh.D.en_US
thesis.degree.leveldoctoralen_US
thesis.degree.disciplineElectrical and Computer Engineeringen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.grantorUniversity of Arizonaen_US
dc.contributor.advisorMylrea, Kenneth C.en_US
dc.contributor.committeememberHameroff, Stuart R.en_US
dc.contributor.committeememberStrickland, Robin N.en_US
dc.identifier.proquest9103045en_US
dc.identifier.oclc709777357en_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.