Predicting the need for urgent intubation in a surgical/trauma intensive care unit

Amani Politano, Lin M. Riccio, Douglas E. Lake, Craig G. Rusin, Lauren E. Guin, Christopher S. Josef, Matthew T. Clark, Robert G. Sawyer, J. Randall Moorman, James F. Calland

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Background Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. Methods Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. Results Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95% confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46%). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 % CI, 0.821-0.910). Conclusion Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/trauma patients.

Original languageEnglish (US)
Pages (from-to)1110-1116
Number of pages7
JournalSurgery (United States)
Volume154
Issue number5
DOIs
StatePublished - Nov 1 2013
Externally publishedYes

Fingerprint

Critical Care
Intubation
Intensive Care Units
Respiratory Rate
Wounds and Injuries
Vital Signs
Heart Rate
Confidence Intervals
Entropy
Respiratory Insufficiency
Oxygen
Morbidity
Mortality

ASJC Scopus subject areas

  • Surgery
  • Medicine(all)

Cite this

Politano, A., Riccio, L. M., Lake, D. E., Rusin, C. G., Guin, L. E., Josef, C. S., ... Calland, J. F. (2013). Predicting the need for urgent intubation in a surgical/trauma intensive care unit. Surgery (United States), 154(5), 1110-1116. https://doi.org/10.1016/j.surg.2013.05.025

Predicting the need for urgent intubation in a surgical/trauma intensive care unit. / Politano, Amani; Riccio, Lin M.; Lake, Douglas E.; Rusin, Craig G.; Guin, Lauren E.; Josef, Christopher S.; Clark, Matthew T.; Sawyer, Robert G.; Moorman, J. Randall; Calland, James F.

In: Surgery (United States), Vol. 154, No. 5, 01.11.2013, p. 1110-1116.

Research output: Contribution to journalArticle

Politano, A, Riccio, LM, Lake, DE, Rusin, CG, Guin, LE, Josef, CS, Clark, MT, Sawyer, RG, Moorman, JR & Calland, JF 2013, 'Predicting the need for urgent intubation in a surgical/trauma intensive care unit', Surgery (United States), vol. 154, no. 5, pp. 1110-1116. https://doi.org/10.1016/j.surg.2013.05.025
Politano, Amani ; Riccio, Lin M. ; Lake, Douglas E. ; Rusin, Craig G. ; Guin, Lauren E. ; Josef, Christopher S. ; Clark, Matthew T. ; Sawyer, Robert G. ; Moorman, J. Randall ; Calland, James F. / Predicting the need for urgent intubation in a surgical/trauma intensive care unit. In: Surgery (United States). 2013 ; Vol. 154, No. 5. pp. 1110-1116.
@article{962dae1f45184f2db1d84b1f69c3a160,
title = "Predicting the need for urgent intubation in a surgical/trauma intensive care unit",
abstract = "Background Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. Methods Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. Results Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95{\%} confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46{\%}). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 {\%} CI, 0.821-0.910). Conclusion Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/trauma patients.",
author = "Amani Politano and Riccio, {Lin M.} and Lake, {Douglas E.} and Rusin, {Craig G.} and Guin, {Lauren E.} and Josef, {Christopher S.} and Clark, {Matthew T.} and Sawyer, {Robert G.} and Moorman, {J. Randall} and Calland, {James F.}",
year = "2013",
month = "11",
day = "1",
doi = "10.1016/j.surg.2013.05.025",
language = "English (US)",
volume = "154",
pages = "1110--1116",
journal = "Surgery (United States)",
issn = "0039-6060",
publisher = "Mosby Inc.",
number = "5",

}

TY - JOUR

T1 - Predicting the need for urgent intubation in a surgical/trauma intensive care unit

AU - Politano, Amani

AU - Riccio, Lin M.

AU - Lake, Douglas E.

AU - Rusin, Craig G.

AU - Guin, Lauren E.

AU - Josef, Christopher S.

AU - Clark, Matthew T.

AU - Sawyer, Robert G.

AU - Moorman, J. Randall

AU - Calland, James F.

PY - 2013/11/1

Y1 - 2013/11/1

N2 - Background Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. Methods Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. Results Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95% confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46%). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 % CI, 0.821-0.910). Conclusion Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/trauma patients.

AB - Background Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. Methods Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. Results Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95% confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46%). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 % CI, 0.821-0.910). Conclusion Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/trauma patients.

UR - http://www.scopus.com/inward/record.url?scp=84886096008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886096008&partnerID=8YFLogxK

U2 - 10.1016/j.surg.2013.05.025

DO - 10.1016/j.surg.2013.05.025

M3 - Article

C2 - 24075272

AN - SCOPUS:84886096008

VL - 154

SP - 1110

EP - 1116

JO - Surgery (United States)

JF - Surgery (United States)

SN - 0039-6060

IS - 5

ER -