Using Prediction Scores in Antibiotic Stewardship

Julie Ann Justo, PharmD, MS, BCPS-AQ ID, clinical assistant professor, University of South Carolina College of Pharmacy, discusses how prediction scores are used in antibiotic stewardship programs.

Interview Transcript (modified slightly for readability):

"Prediction scores are a useful tool if we have published literature that is looking for a particular outcome. For instance, if we are looking for predicting the chance that someone is going to have Pseudomonas aeruginosa as their gram-negative isolate when you have a concern for gram-negative bacteremia in a patient, you could create a score that would say ‘okay, of all the grand negative bacteremia that we have, let’s look at the patients that had Pseudomonas aeruginosa versus everything else’ and identify risk factors that would predict that would help us predict that a person would have Pseudomonas aeruginosa at baseline. So, most prediction scores, risk scores — whatever you want to call them – they’re predicting for a certain type of outcome using baseline characteristics that a clinician would know at the bedside."