Algorithm Predicts Risk of Paediatric Septic Shock in Emergency Department
Researchers have developed a unique model allowing them to predict which children arriving to the emergency department (ED) are most likely to go into septic shock.
In a study published in The Journal of Pediatrics, the researchers detailed how they ran electronic medical records through a modern predictive algorithm to accurately project the likelihood of septic shock.
“No models exist to predict the risk of septic shock upon arrival to the ED, a critical time point for intervention,” said lead author Halden Scott, MD, University of Colorado School of Medicine, and Children’s Hospital Colorado, Aurora, Colorado. “We set out to develop a model of the risk based on patients whom doctors suspected had sepsis upon arrival.”
The study looked at 6 paediatric ED and Urgent Care sites focusing on patients aged 60 days to 18 years with suspected sepsis and missed cases of septic shock.
Of the 2,464 visits they analysed, septic shock occurred in 282 (11.4%) patients. The new model was able to predict 90% of the cases. In a high-risk patient, treatment could begin earlier to prevent shock.
“This model estimated risk of septic shock in children at hospital arrival, earlier than existing models,” said Dr. Scott. “Using it offers the potential to enhance clinical risk-stratification in the critical moments before a patient begins to deteriorate.”
“The model is an equation designed for computer-based calculation, in order to maximise the predictive value of data already in the Electronic Health Record,” he added.
A recent study showed that only 24.9% of children with sepsis received the first hour bundle of intravenous fluid, antibiotics, and blood cultures. Dr. Scott said that this study’s findings provides further evidence that most children fail to get the necessary treatment when it could possibly save their lives.
“The early treatment for sepsis is relatively simple, but if it’s not given early a downward spiral of organ failure can begin that is difficult to reverse,” said Dr. Scott. “This is why we believe that a predictive model for septic shock is so important to improve early diagnosis, and get early treatment to the high-risk patients for whom it can be life-saving.”
SOURCE: University of Colorado Anschutz Medical Campus