Background: Clinical prediction models for pediatric community-acquired pneumonia (CAP) may standardize management. Understanding physician risk thresholds is important for model implementation. We aimed to elucidate physician-derived thresholds for chest radiograph performance and empirical antibiotic treatment of CAP among children presenting to the emergency department with respiratory illness before and after knowledge of results of a validated clinical prediction model.
Methods: Pediatric emergency physicians were surveyed through the American Academy of Pediatrics Pediatric Emergency Medicine Collaborative Research Committee and provided 8 clinical vignettes for children with respiratory symptoms. Respondents were asked to indicate their probability of radiographic CAP and choose whether they would obtain a chest radiograph or give empirical antibiotics before and after being provided with the probability of radiographic CAP based on a validated prediction model. We used logistic regression to establish testing and treatment thresholds, defined as the disease probability at which half of physicians acted.
Results: Two-hundred and eight (44.3%) of 469 physicians completed the survey. Most were attending physicians (96.0%) practicing in a freestanding children's hospital (76.8%). Testing and treatment thresholds for CAP were 17.6% (95% confidence interval [CI] 16.4% to 18.8%) and 66.1% (95% CI 60.1% to 72.5%), respectively, before knowledge of the model-estimated probability. With knowledge of the prediction model, testing and treatment thresholds were 13.5% (95% CI 12.3% to 14.7%) and 58.0% (95% CI 53.2-62.8).
Conclusions: We elucidated physician thresholds for testing and treatment of CAP, which may be integrated into future pneumonia risk models to improve acceptability and incorporation into practice.
Copyright © 2024 by the American Academy of Pediatrics.