Predictive analytics in the pediatric intensive care unit for early identification of sepsis: capturing the context of age.

BACKGROUND: Early recognition of patients at risk for sepsis is paramount to improve clinical outcomes. We hypothesized that subtle signatures of illness are present in physiological and biochemical time series of pediatric-intensive care unit (PICU) patients in the early stages of sepsis. METHODS: We developed multivariate models in a retrospective observational cohort to predict the clinical diagnosis of sepsis in children. We focused on age as a predictor and asked whether random forest models, with their potential for multiple cut points, had better performance than logistic regression. RESULTS: One thousand seven hundred and eleven admissions for 1425 patients admitted to a mixed cardiac and medical/surgical PICU were included. We identified, through individual chart review, 187 sepsis diagnoses that were not within 14 days of a prior sepsis diagnosis. Multivariate models predicted sepsis in the next 24 h: cross-validated C-statistic for logistic regression and random forest were 0.74 (95% confidence interval (CI): 0.71-0.77) and 0.76 (95% CI: 0.73-0.79), respectively. CONCLUSIONS: Statistical models based on physiological and biochemical data already available in the PICU identify high-risk patients up to 24 h prior to the clinical diagnosis of sepsis. The random forest model was superior to logistic regression in capturing the context of age.

Heart rate ranges in premature neonates using high resolution physiologic data.

OBJECTIVE: There are limited evidence-based published heart rate ranges for premature neonates. We determined heart rate ranges in premature neonates based on gestational and post-menstrual age. STUDY DESIGN: Retrospective observational study of premature neonates admitted to the neonatal intensive care unit at the University of Virginia between January 2009 and October 2015. We included gestational ages between 23 0/7 weeks and 34 6/7 weeks. We stratified data by gestational and post-menstrual age groups. RESULTS: Over two billion heart rate values in 1703 neonates were included in our study. We established percentile-based reference ranges based on gestational and post-menstrual age. Our results demonstrate a slight increase in the initial weeks after birth, followed by a gradual decline with age. The baseline heart rate is lower with advancing gestational age. CONCLUSIONS: Knowing heart rate reference ranges in the premature neonatal population can be helpful in the bedside assessment of the neonate.