AUTHOR=Spaeder Michael C. , Moorman J. Randall , Moorman Liza P. , Adu-Darko Michelle A. , Keim-Malpass Jessica , Lake Douglas E. , Clark Matthew T. 

TITLE=Signatures of illness in children requiring unplanned intubation in the pediatric intensive care unit: A retrospective cohort machine-learning study

JOURNAL=Frontiers in Pediatrics

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2022.1016269

DOI=10.3389/fped.2022.1016269

ISSN=2296-2360

ABSTRACT=Acute respiratory failure requiring the initiation of invasive mechanical ventilation remains commonplace in the pediatric intensive care unit. Early recognition of patients at risk for respiratory failure has the potential to prevent intubations, or, at the least, convert an urgent intubation to a more controlled elective intubation, thereby reducing some of the associated morbidity. We hypothesized that subtle signatures of illness are present in physiological and biochemical time series of PICU patients in the early stages of respiratory decompensation. Here, we tested this hypothesis by developing a random forest model to identify patients at increased risk for requiring urgent unplanned intubation. We observed that children have a physiologic signature of respiratory distress leading to urgent unplanned intubation in the PICU. Generally, it comprises younger age, and abnormalities in electrolyte, hematologic and vital sign parameters. Additionally, given the heterogeneity of the PICU patient population, we found differences in the presentation among the major patient groups – medical, non-cardiac surgical, and cardiac surgical. The multivariable statistical models that captured the physiological and biochemical dynamics leading up to the event of urgent unplanned intubation in a PICU can be repurposed for bedside risk prediction.