Integrated monitoring can detect critical events and improve alarm accuracy

M. J. Navabi, R. C. Watt, Stuart R Hameroff, K. C. Mylrea

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A computer-based, integrated monitor system was designed and utilized to collect and interactively manage physiologic data (13 variables and 3 waveforms) from six routinely used operating room monitors. Various approaches were developed to reduce false alarms, classify waveforms, and recognize events. False alarms: false alarms in ECG heart rate detection were reduced from 37.3% to 2.6% (p = 0.005) of total alarms using multi-variable analysis and rate-of-change limits. Waveform classification: using artificial neural networks (ANN), CO2 waveforms were classified into (a) spontaneous, (b) mechanical, and (c) mechanical/with spontaneous breathing attempts. The system properly classified 47 of 71 spontaneous, 65 of 67 mechanical, 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. Event recognition: an algorithm developed to identify endotracheal intubation correctly recognized 13 of 17 intubations. This resulted in a 42% reduction in low end-tidal-CO2 false alarms.

Original languageEnglish (US)
Pages (from-to)295-306
Number of pages12
JournalJournal of Clinical Engineering
Volume16
Issue number4
StatePublished - Jul 1991

Fingerprint

Electrocardiography
Respiration
Neural networks
Operating rooms
Intratracheal Intubation
Monitoring
Operating Rooms
Intubation
Heart Rate

ASJC Scopus subject areas

  • Biophysics
  • Mechanical Engineering

Cite this

Integrated monitoring can detect critical events and improve alarm accuracy. / Navabi, M. J.; Watt, R. C.; Hameroff, Stuart R; Mylrea, K. C.

In: Journal of Clinical Engineering, Vol. 16, No. 4, 07.1991, p. 295-306.

Research output: Contribution to journalArticle

Navabi, M. J. ; Watt, R. C. ; Hameroff, Stuart R ; Mylrea, K. C. / Integrated monitoring can detect critical events and improve alarm accuracy. In: Journal of Clinical Engineering. 1991 ; Vol. 16, No. 4. pp. 295-306.
@article{af935cb367d24c0894e40ac6c1461d7c,
title = "Integrated monitoring can detect critical events and improve alarm accuracy",
abstract = "A computer-based, integrated monitor system was designed and utilized to collect and interactively manage physiologic data (13 variables and 3 waveforms) from six routinely used operating room monitors. Various approaches were developed to reduce false alarms, classify waveforms, and recognize events. False alarms: false alarms in ECG heart rate detection were reduced from 37.3{\%} to 2.6{\%} (p = 0.005) of total alarms using multi-variable analysis and rate-of-change limits. Waveform classification: using artificial neural networks (ANN), CO2 waveforms were classified into (a) spontaneous, (b) mechanical, and (c) mechanical/with spontaneous breathing attempts. The system properly classified 47 of 71 spontaneous, 65 of 67 mechanical, 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. Event recognition: an algorithm developed to identify endotracheal intubation correctly recognized 13 of 17 intubations. This resulted in a 42{\%} reduction in low end-tidal-CO2 false alarms.",
author = "Navabi, {M. J.} and Watt, {R. C.} and Hameroff, {Stuart R} and Mylrea, {K. C.}",
year = "1991",
month = "7",
language = "English (US)",
volume = "16",
pages = "295--306",
journal = "Journal of Clinical Engineering",
issn = "0363-8855",
publisher = "Lippincott Williams and Wilkins",
number = "4",

}

TY - JOUR

T1 - Integrated monitoring can detect critical events and improve alarm accuracy

AU - Navabi, M. J.

AU - Watt, R. C.

AU - Hameroff, Stuart R

AU - Mylrea, K. C.

PY - 1991/7

Y1 - 1991/7

N2 - A computer-based, integrated monitor system was designed and utilized to collect and interactively manage physiologic data (13 variables and 3 waveforms) from six routinely used operating room monitors. Various approaches were developed to reduce false alarms, classify waveforms, and recognize events. False alarms: false alarms in ECG heart rate detection were reduced from 37.3% to 2.6% (p = 0.005) of total alarms using multi-variable analysis and rate-of-change limits. Waveform classification: using artificial neural networks (ANN), CO2 waveforms were classified into (a) spontaneous, (b) mechanical, and (c) mechanical/with spontaneous breathing attempts. The system properly classified 47 of 71 spontaneous, 65 of 67 mechanical, 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. Event recognition: an algorithm developed to identify endotracheal intubation correctly recognized 13 of 17 intubations. This resulted in a 42% reduction in low end-tidal-CO2 false alarms.

AB - A computer-based, integrated monitor system was designed and utilized to collect and interactively manage physiologic data (13 variables and 3 waveforms) from six routinely used operating room monitors. Various approaches were developed to reduce false alarms, classify waveforms, and recognize events. False alarms: false alarms in ECG heart rate detection were reduced from 37.3% to 2.6% (p = 0.005) of total alarms using multi-variable analysis and rate-of-change limits. Waveform classification: using artificial neural networks (ANN), CO2 waveforms were classified into (a) spontaneous, (b) mechanical, and (c) mechanical/with spontaneous breathing attempts. The system properly classified 47 of 71 spontaneous, 65 of 67 mechanical, 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. Event recognition: an algorithm developed to identify endotracheal intubation correctly recognized 13 of 17 intubations. This resulted in a 42% reduction in low end-tidal-CO2 false alarms.

UR - http://www.scopus.com/inward/record.url?scp=0026196252&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026196252&partnerID=8YFLogxK

M3 - Article

C2 - 10114048

AN - SCOPUS:0026196252

VL - 16

SP - 295

EP - 306

JO - Journal of Clinical Engineering

JF - Journal of Clinical Engineering

SN - 0363-8855

IS - 4

ER -