Development and validation of a prediction model to predict school-age asthma in preschool children.

Abstract

To develop and validate a clinical prediction model to identify school-age asthma in preschool asthmatic children. In this retrospective prognosis cohort study, asthmatic children aged 3-5 years were enrolled with at least 2 years of follow-up, and their potential variables at baseline and the prognosis of school-age asthma were collected from medical records. A clinical prediction model was developed using Logistic regression. The performance of prediction model was assessed and quantified by discrimination of the area under the receiver operating characteristic curve (AUC) and calibration of Brier score. The model was validated by the temporal-validation method. In the development dataset, 2748 preschool asthmatic children were included for model development, and 883 (32.13%) children were translated to school-age asthma. The independent prognostic variables with an increased risk for school-age asthma were used to develop the prediction model, including: age, parental asthma, early frequent wheezing, allergic rhinitis, eczema, allergic conjunctivitis, obesity, and aeroallergen of dust mite. While assessing model performance, the discrimination power of AUC was moderate [0.788 (0.770-0.805)] with sensitivity (81.5%) and specificity (60.9%), and the calibration of Brier score was 0.169, supporting the calibration ability. In the temporal-validation dataset of 583 preschool asthmatic children, our model showed satisfactory discrimination (AUC 0.818) and calibration (Brier score 0.150). The prediction model was presented by the web-based calculator (https://casthma.shinyapps.io/dynnomapp/) and a nomogram for clinical application. In preschool asthmatic children, our prediction model could be used to predict the risk of school-age asthma.