Related Experiment Video
Updated: Apr 7, 2026
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
Early identification of refractory Mycoplasma pneumoniae pneumonia in children using CT-based radiomics: a
Qian Li1, Jian Zhang1, Zi-Jun Song1
1Department of Critical Care Medicine, Baoding First Central Hospital, Baoding, China.
Insights
An integrated model combining clinical, imaging, and radiomics data accurately predicts refractory Mycoplasma pneumoniae pneumonia (RMPP) in children. This approach improves early risk stratification for RMPP, aiding timely clinical decisions.
Area of Science:
- Pediatric Pulmonology
- Medical Imaging
- Radiomics
Background:
- Refractory Mycoplasma pneumoniae pneumonia (RMPP) poses a significant challenge in pediatric care.
- Early prediction of RMPP is crucial for timely intervention and improved patient outcomes.
Purpose of the Study:
- To develop and validate a predictive model for early identification of RMPP in children.
- The model integrates clinical, imaging, and radiomics characteristics.
Main Methods:
- A multicenter retrospective study involving 419 children.
- Radiomics features extracted from chest CT scans using PyRadiomics.
- Development of clinical-imaging, radiomics, and integrated predictive models using random forest algorithms.
Main Results:
- The integrated model achieved the highest predictive performance (AUC: 0.811) in the validation cohort.
- Key predictors included D-dimer, fever type, systemic immune-inflammation index, and specific radiomics features.
- Significant improvements in classification accuracy were observed with the integrated model compared to individual models.
Conclusions:
- An integrated model combining clinical, imaging, and radiomics data significantly enhances risk stratification for RMPP in children.
- This multimodal approach offers a promising tool for early RMPP prediction and management.
Objective:
To develop and validate a model that utilizing clinical, imaging, and radiomics characteristics for early predicting refractory Mycoplasma pneumoniae pneumonia (RMPP) in children.
Methods:
This multicenter retrospective study included a total of 419 children, divided into training (n = 248), testing (n = 62), and external validation (n = 109) cohorts. Patients were classified into non-RMPP and RMPP groups based on clinical guidelines. Radiomics features were extracted from chest CT scans using PyRadiomics, followed by SelectKBest and least absolute shrinkage and selection operator regression for feature selection. Three random forest-based predictive models were developed: clinical-imaging, radiomics, and integrated. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC), McNemar tests, and net reclassification improvement (NRI).
Results:
The integrated model demonstrated the highest predictive performance (AUC: 0.811, 95% CI: 0.704-0.917), compared with both the radiomics (AUC: 0.784, 95% CI: 0.683-0.885) and clinical-imaging (AUC: 0.675, 95% CI: 0.603-0.833) models in the validation cohort. McNemar tests revealed significant differences in classification between the radiomics and clinical-imaging models (p = 0.001), radiomics and integrated models (p = 0.013), and clinical-imaging and integrated models (p < 0.001) in the validation cohort. In the validation cohort, the NRI was higher for the integrated model than for the radiomics and clinical-imaging models (both p < 0.001) but did not differ between the radiomics and clinical-imaging models (p = 0.070). Key predictors included D-dimer, type of fever, and the systemic immune-inflammation index, along with radiomics features such as gray-level co-occurrence matrix and wavelet kurtosis.
Conclusion:
The integrated model, combining clinical, imaging, and radiomics features, enhances risk stratification for RMPP.
More Related Videos
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
11:31Using Micro-computed Tomography for the Assessment of Tumor Development and Follow-up of Response to Treatment in a Mouse Model of Lung Cancer
Published on: May 20, 2016