Table 1_Risk prediction for gastrointestinal bleeding in pediatric Henoch-Schönlein purpura using an interpretable transformer model.doc

ObjectiveHenoch-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.
MethodsThis 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.
ResultsAmong 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.
ConclusionThe 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.

研究目的：过敏性紫癜（Henoch-Schönlein purpura, HSP）在临床上又称IgA血管炎（IgAV），是儿童群体中常见的系统性血管炎，常累及胃肠道，可引发出血、组织坏死等严重并发症。及时识别胃肠道出血风险，可实现及时的临床干预，改善治疗结局。本研究旨在开发并经临床验证一款可解释的基于Transformer的预测模型，用于评估儿童IgAV患者的胃肠道出血风险。
研究方法：本回顾性队列研究分析了2020年5月1日至2024年1月31日期间，川北医学院附属医院儿科收治的758例儿童IgAV患者（年龄0~14岁）。研究系统收集了包括症状、实验室参数在内的全面临床数据。基于标准化诊断标准，将胃肠道并发症分为3个严重程度层级：1）无并发症；2）腹痛但无出血；3）经证实的直肠出血或消化道大出血。研究通过嵌套交叉验证对5种机器学习算法（随机森林、XGBoost、LightGBM、CatBoost、TabPFN-V2）进行优化。采用准确率、精确率、召回率、F1分数、Kappa系数以及ROC-AUC多项指标评估模型性能。随后利用Shapley加性解释（Shapley Additive Explanations, SHAP）值对最优模型进行可解释性分析，以阐明特征重要性。
研究结果：在所评估的模型中，基于Transformer的TabPFN-V2展现出最优的预测性能，其验证集准确率达0.88，精确率0.88，召回率0.87，F1分数0.88，Kappa系数0.82，AUC-ROC达0.98。SHAP分析显示，对模型全局可解释性影响最大的5项生物标志物为：D-二聚体、总胆固醇、血小板计数、载脂蛋白以及C反应蛋白。
研究结论：这款可解释的基于Transformer的TabPFN-V2模型，在儿童IgAV患者胃肠道出血风险预测中展现出稳健的预测性能。本模型识别的临床可用实验室参数，不仅可为临床决策提供实用指导，同时也为推动儿科领域医疗人工智能融合应用奠定了基础。