Development and validation of a simple-to-use nomogram for predicting the delayed radiographic recovery in children with mycoplasma pneumoniae pneumonia complicated with atelectasis

Abstract

This study aimed to develop and validate a simple-to-use nomogram for predicting the delayed radiographic recovery in children with mycoplasma pneumoniae pneumonia (MPP) complicated with atelectasis. A retrospective study of 306 children with MPP complicated with atelectasis was performed at the Children’s Hospital of Chongqing Medical University from February 2017 to March 2020.The patients were divided into recovery group and delayed recovery group based on chest CT scan 1 month after discharge. A least absolute shrinkage and selection operator (LASSO) regression model was used to identify the optimal predictors, and the predictive nomogram was plotted by multivariable logistic regression. The nomogram was assessed by calibration, discrimination, and clinical utility. LASSO regression analysis identified that lactate dehydrogenase (LDH), duration of illness prior to bronchoalveolar lavage (BAL), systemic glucocorticoid use and extrapulmonary complications were the optimal predictors for delayed radiographic recovery. The nomogram was plotted by the four predictors. The area under the Receiver Operating Characteristic (ROC) curve of the nomogram was 0.840 (95% CI = 784 ∼ 0.896) in the training set and 0.833 (95% CI = 0.8737 ∼ 0.930) in the testing set. The calibration curve demonstrated that the nomogram was well-fitted, and decision curve analysis (DCA) showed that the nomogram was clinically beneficial. This study developed and validated a simple-to-use nomogram for predicting delayed radiographic recovery in children with MPP complicated with atelectasis. This might be generally applied in clinical practice.