Comparison of chest X-ray interpretation by pediatric pulmonologists, pediatric radiologists, and pediatric residents in children with suspected foreign body aspiration—a retrospective cohort study

Chest X-ray (CXR) is an important tool in the assessment of children with suspected foreign body aspiration (FBA), although it can falsely be interpreted as normal in one-third of the cases. The aim of this study is to evaluate the positive predictive value of CXR in children hospitalized with suspected FBA, when interpreted by three disciplines: pediatric pulmonology, pediatric radiology, and pediatric residents. This is a retrospective study that included children aged 0–18 years, admitted with suspected FBA, between 2009 and 2020 in one tertiary center. All patients underwent CXR and a flexible/rigid bronchoscopy for the definitive diagnosis of FBA, up to 1 week apart. Two physicians from each discipline interpreted the CXR, independently. Intra-raters’ and inter-raters’ agreements were assessed. Sensitivity, specificity, and area under the curve (AUC) were calculated for each discipline. Four hundred seventy-three children were included in the study, 175 (37%) with FBA and 298 (63%) without FBA on flexible/rigid bronchoscopy. The most common radiological findings, as interpreted by a pediatric pulmonologist, were unilateral hyperinflation (47%), radiopaque FB (37.6%), lobar atelectasis (10.3%), unilateral hyperinflation with atelectasis (3.4%), and lobar consolidation (1.7%). Intra-raters’ agreement ranged from 0.744 (p < 0.001) among pediatric pulmonologists to 0.326 (p < 0.001) among pediatric radiologists. AUC for predicting FBA based on a CXR was 0.81, 0.77, and 0.7 when interpreted by pediatric pulmonologists, pediatric residents, and radiologists, respectively (p < 0.001).