Clinical prediction tool to identify children at risk of pulmonary embolism

Abstract

IntroductionThe diagnosis of pediatric pulmonary embolism (PE) is often delayed due to non-specific symptoms, and clinical prediction tools designed for adults are unsuitable for children. This study aimed to create a PE predictive model and to evaluate the reported tools in the Thai pediatric population. Materials and methodsA multi-center retrospective study from 4 university hospitals included children ≤18 years of age undergoing computed tomography pulmonary angiogram from 2000 to 2020 with the suspicion of PE. Patients' clinical presentations and risk factors of venous thromboembolism (VTE) were compared between the PE-positive and PE-negative groups. Significant risk factors from univariate and multivariate logistic regression were included to create a clinical prediction tool. The performance of the model was demonstrated by sensitivity, specificity, area under the curve (AUC), Hosmer Lemeshow test, ratio of observed and expected outcomes and bootstrapping. ResultsOf the 104 patients included, 43 (41.3 %) were grouped as PE-positive and 61 (58.7 %) as PE-negative. Five parameters, including congenital heart disease/pulmonary surgery, known thrombophilia, previous VTE, nephrotic syndrome and chest pain showed significant differences between the two groups. Score ≥ 2 yielded a 74.4 % sensitivity and a 75.4 % specificity with an AUC of the model of 0.809. The model performance and validation results were within satisfactory ranges. ConclusionThe study created a clinical prediction tool indicating the likelihood of PE among Thai children. A score ≥2 was suggestive of PE.