Aims Very low birth weight (VLBW < 1500 grams) infants in the Neonatal Intensive Care Unit (NICU) are at risk for respiratory deterioration requiring endotracheal intubation and mechanical ventilation, with associated morbidities. Methods for predicting impending respiratory failure are needed, as timely non-invasive treatments might avert severe deterioration and the need to intubate.
Our aim was to develop a predictive statistical model for continuous analysis of cardiorespiratory waveforms and vital signs to predict respiratory failure requiring intubation in VLBW infants.
Methods We collected continuous cardiorespiratory and demographic data, and types and times of respiratory support on all VLBW infants admitted to the University of Virginia NICU from January 2009–June 2011. We identified non-elective intubations that were followed by mechanical ventilation for at least 12h. Over 25 physiological measures were tested, and a multivariate logistic regression model was developed to estimate the relative risk of urgent intubation in the next 24 hours.
Results Of 287 VLBW infants admitted, 96 urgent intubations in which there were at least 12h of waveform data occurred in 51 patients. The final model had ROC area 0.84 and employed oxygen saturation and its cross-correlation with heart rate, cross-correlation of heart and respiratory rates, and apnea burden. Inspection showed rising risk of intubation over the 12 to 24 hours prior to the event.
Conclusion Predictive monitoring of cardiorespiratory waveform patterns and vital signs can detect incipient respiratory failure as much as 24h prior to urgent intubation.