Risk prediction for gastrointestinal bleeding in pediatric Henoch-Schönlein purpura using an interpretable
1The Department of Pediatrics at the Affiliated Hospital of North Sichuan Medical College, NanChong, Sichuan, China.
Insights
A new Transformer-based model accurately predicts gastrointestinal bleeding risk in children with IgA vasculitis (IgAV). This AI tool uses key biomarkers to improve early detection and clinical management of this common pediatric condition.
Area of Science:
- Pediatric Medicine
- Artificial Intelligence in Healthcare
- Vascular Inflammation
Background:
- Henoch-Schönlein purpura (HSP), also known as IgA vasculitis (IgAV), is a common systemic vasculitis in children.
- Gastrointestinal (GI) complications, including hemorrhage and necrosis, are significant concerns in pediatric IgAV.
- Early identification of GI bleeding risk is crucial for timely intervention and improved patient outcomes.
Purpose of the Study:
- To develop and clinically validate an interpretable Transformer-based predictive model for assessing GI bleeding risk in pediatric IgAV patients.
- To identify key clinical and laboratory parameters predictive of GI bleeding in this population.
- To enhance clinical decision-making and patient management through AI integration.
Main Methods:
- A retrospective cohort study of 758 pediatric IgAV cases (ages 0-14) was conducted.
- Five machine learning algorithms were optimized, with performance evaluated using accuracy, precision, recall, F1-score, Kappa coefficient, and ROC-AUC.
- The optimal model was interpreted using Shapley Additive Explanations (SHAP) to determine feature importance.
Main Results:
- The Transformer-based TabPFN-V2 model achieved superior predictive performance (validation accuracy: 0.88, AUC-ROC: 0.98).
- Key predictive biomarkers identified include D-dimer, total cholesterol, platelet count, apolipoprotein, and C-reactive protein.
- The model provides interpretable insights into GI bleeding risk factors.
Conclusions:
- An interpretable Transformer-based model (TabPFN-V2) effectively predicts GI bleeding risk in pediatric IgAV.
- The model's reliance on accessible laboratory parameters facilitates clinical application.
- This study supports the integration of medical AI in pediatric care for improved diagnostics and management.
Objective:
Henoch-Schönlein purpura (HSP), clinically recognized as IgA vasculitis (IgAV), a prevalent systemic vasculitis in pediatric populations, frequently involves gastrointestinal (GI) tract manifestations that may lead to serious complications including hemorrhage and tissue necrosis. Timely identification of GI bleeding risk enables prompt clinical intervention and improves therapeutic outcomes. This study aims to develop and clinically validate an interpretable Transformer-based predictive model for assessing GI bleeding risk in pediatric patients with IgAV.
Methods:
This retrospective cohort study analyzed 758 pediatric IgAV cases (ages 0-14 years) admitted to the Department of Pediatrics at the Affiliated Hospital of North Sichuan Medical College between 1 May 2020, and 31 January 2024. Comprehensive clinical data including symptoms and laboratory parameters were systematically collected. GI complications were stratified into three severity tiers: 1) no complications, 2) abdominal pain without bleeding), and 3) documented rectal bleeding or hemorrhage, based on standardized diagnostic criteria. Five machine learning algorithms (Random Forest, XGBoost, LightGBM, CatBoost, and TabPFN-V2) were optimized through nested cross-validation. Model performance was evaluated using multiple metrics: accuracy, precision, recall, F1-score, the Kappa coefficient, and ROC-AUC. The optimal model was subsequently interpreted using Shapley Additive Explanations (SHAP) values to elucidate feature importance.
Results:
Among the evaluated models, the Transformer-based TabPFN-V2 demonstrated superior predictive performance, achieving a validation accuracy of 0.88, precision of 0.88, recall of 0.87, F1-score of 0.88, Kappa coefficient of 0.82, and AUC-ROC of 0.98. SHAP analysis revealed the five most influential biomarkers for global interpretability: D-dimer, total cholesterol, platelet count, apolipoprotein, and C-reactive protein.
Conclusion:
The interpretable Transformer-based TabPFN-V2 model demonstrated robust predictive performance for GI bleeding risk in pediatric IgAV patients. Clinically accessible laboratory parameters identified by this model not only offer practical guidance for clinical decision-making but also establish a foundation for advancing medical artificial intelligence integration in pediatric care.
