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

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.