Related Experiment Videos
A CT-based deep learning model for the automated risk stratification of refractory Mycoplasma pneumoniae pneumonia in
Zhoumeng Ying1,2, Ge Hu3, Jing Li4,5,6
1Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Insights
Accurate identification of children with refractory Mycoplasma pneumoniae pneumonia (RMPP) is challenging. A new transformer-based deep learning model using chest CT effectively stratifies pediatric RMPP risk, aiding clinical decisions.
Area of Science:
- Artificial Intelligence in Medicine
- Medical Imaging Analysis
- Pediatric Pulmonology
Background:
- Accurate identification of refractory Mycoplasma pneumoniae pneumonia (RMPP) in children is difficult.
- Chest computed tomography (CT) is often used for diagnosis.
- Developing advanced models for risk stratification is crucial.
Purpose of the Study:
- To develop and validate a transformer-based deep learning framework (trans-DLF) for pediatric RMPP risk stratification.
- To utilize clinically indicated chest CT data for model development.
- To assess the model's performance against existing methods.
Main Methods:
- A multicenter retrospective cohort of 1224 pediatric patients with Mycoplasma pneumoniae pneumonia was used.
- A transformer-based deep learning framework (trans-DLF) was developed and trained.
- Model performance was evaluated using Area Under the Receiver Operating Characteristic Curve (AUC) and compared to 3D-CNN, clinical models, and nomograms.
Main Results:
- The trans-DLF achieved high AUCs across training (0.97), validation (0.91), internal testing (0.90), and external testing (0.89) cohorts.
- The model significantly outperformed the clinical model (p < 0.001).
- Interpretability analysis (Grad-CAM) indicated predictions were based on clinically relevant features like consolidations.
Conclusions:
- The transformer-based deep learning framework offers an efficient method for RMPP risk assessment in children.
- This approach can support timely, evidence-based clinical decision-making without requiring additional tests.
- The model demonstrates strong generalizability and potential for clinical application.
Background:
The accurate identification of children with refractory Mycoplasma pneumoniae pneumonia (RMPP) remains challenging. This study aimed to develop a transformer-based model utilizing clinically indicated chest computed tomography (CT) to stratify pediatric RMPP risk at a critical decision point.
Methods:
Non-contrast chest CT data from a multicenter retrospective cohort of 1224 pediatric patients with Mycoplasma pneumoniae pneumonia who underwent clinically indicated CT were used to develop a transformer-based deep learning framework (trans-DLF). The primary cohort comprised training (n = 506), validation (n = 140), and internal testing (n = 139) cohorts, with two independent external cohorts (n = 331 and n = 108) used to evaluate generalizability. Model performance was assessed by the area under the receiver operating characteristic curve (AUC) and compared against a three-dimensional convolutional neural network (3D-CNN), a clinical model, and a multimodal nomogram. Interpretability was examined using gradient-weighted class activation mapping (Grad-CAM).
Results:
The median age was 6.83 years (interquartile range, 5.0-8.6 years), and 609 (49.8%) were male. The trans-DLF demonstrated strong performance across all cohorts: training (AUC 0.97; 95% confidence interval [CI], 0.96-0.98), validation (0.91; 0.86-0.96), internal testing (0.90; 0.85-0.95), and external testing (0.89; 0.84-0.94 and 0.89; 0.82-0.95). It significantly outperformed the clinical model (p < 0.001), while its AUCs were not significantly different from those of the multimodal nomogram. The model maintained good performance in outpatient settings (AUC 0.87) with good calibration and net clinical benefit. Grad-CAM suggested that predictions were influenced by clinically meaningful features, particularly consolidations.
Conclusion:
The trans-DLF provides a streamlined and efficient approach to RMPP risk assessment in children who have already undergone clinically indicated chest CT and may support timely, evidence-based decision-making without additional tests.
