Chest Computed Tomography Radiomics for Determining Macrolide Resistance-Associated Gene Mutation Status in Children with Mycoplasma pneumoniae Pneumonia: A Two-Center Study.

ABSTRACT

RATIONALE AND OBJECTIVES: The mutations in the 23S ribosomal RNA (rRNA) gene are associated with an increase in resistance to macrolides in children with Mycoplasma pneumoniae pneumonia (MPP). This study aimed to develop and validate a chest computed tomography (CT) radiomics model for determining macrolide resistance-associated gene mutation status in MPP. MATERIALS AND METHODS: A total of 258 MPP patients were retrospectively included from two institutions (training set 194 patients from the first institution; external test set 64 patients from the second). The 23S rRNA gene mutation status was tested by nasopharyngeal swab polymerase chain reaction. Radiomics features were extracted from chest CT images of pulmonary lesions segmented with semi-automatic delineation. Subsequently, radiomics feature reduction was applied to identify the most relevant features. Logistic regression and random forest algorithms were employed to establish the radiomics models, which were five-fold cross-validated in the training set and validated in the external test set. RESULTS: The radiomics feature selection resulted in eight features. After five-fold cross-validation in the training set, the mean areas under the receiver operating characteristic curve (AUCs) of the logistic regression and random forest models were 0.868 (95% confidence interval (CI) 0.813-0.923) and 0.941 (95% CI 0.907-0.975), respectively. In the external test set, the corresponding AUCs were 0.855 (95% CI 0.758-0.952) and 0.815 (95% CI 0.705-0.925). CONCLUSION: Chest CT radiomics is a promising diagnostic tool for determining macrolide resistance gene mutation status in MPP. AVAILABILITY OF DATA AND MATERIAL: The datasets generated or analyzed during the study are available from the corresponding author on reasonable request.