The value of CT-based radiomics for differentiation of pleural effusions in bacterial pneumonia and

Background: Bacterial pathogens and Methods: The clinical and CT imaging data of hospitalized children with PE detected by chest CT scans from December 2020 to December 2023 were retrospectively collected. A total of 167 cases of BPPE and 368 cases of MPPE were included, and all cases were randomly divided into a training set and a test set in the ratio of 7:3. The region of interest (ROI) was manually segmented in images of non-contrast chest CT scans to extract radiomics features. The optimal radiomics features were screened using Select K Best, max-relevance and min-redundancy (mRMR), least absolute shrinkage and selection operator (LASSO). Logistic regression (LR) was selected to construct the radiomics model. The receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC), 95% confidence interval (CI), sensitivity, specificity, and accuracy were calculated to evaluate the model performance. Results: A total of 2,264 radiomics features were extracted from each ROI, seven optimal features were finally selected. The AUC in the training set was 0.942 (95% CI: 0.917-0.967), with sensitivity, specificity, accuracy and precision of 89.9%, 82.1%, 87.4% and 91.7%, respectively. The AUC in the test set was 0.917 (95% CI: 0.868-0.965), with sensitivity, specificity, accuracy and precision of 87.4%, 80.0%, 85.1% and 90.7%, respectively. Conclusions: The model based on CT radiomics demonstrates the potential to identify BPPE and MPPE in children and provides a new direction for future research.