Development and validation of a clinical-radiomics nomogram for differentiating Mycoplasma pneumoniae pneumonia from bacterial pneumonia in children - Summary - MDSpire
Advertisement
Development and validation of a clinical-radiomics nomogram for differentiating Mycoplasma pneumoniae pneumonia from bacterial pneumonia in children
To develop a nomogram that integrates CT-based radiomics, clinical indicators, and CT imaging findings for differentiating Mycoplasma pneumoniae pneumonia (MPP) from bacterial pneumonia (BP) in children.
Approach:
Data Analysis: Patients were divided into training (70%) and validation (30%) groups. CT images were segmented using PHIgo-LK segmentation software, and radiomics features were extracted. The minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) were used for feature selection.
Key Findings:
The clinical model achieved AUCs of 0.913 and 0.909 in training and validation sets, respectively.
The radiomics model reached AUCs of 0.918 and 0.895.
The combined nomogram model delivered the highest accuracy with AUCs of 0.971 and 0.958.
Interpretation:
Limitations:
The study is retrospective and conducted at a single center, which may limit generalizability.
Potential biases in patient selection and data collection may affect the results.
