文献速递血管炎

机器学习时代预测儿童IgA血管炎复发:可解释混合集成模型

Predicting relapse in paediatric IgA vasculitis in the era of machine learning: an explainable hybrid ensemble model.
PubMed 文献 · Rheumatology (Oxford) · 2026-01-01

本研究基于653例符合EULAR/PRINTO/PRES标准的儿童IgA血管炎(IgAV)回顾性队列,构建了可解释的混合集成机器学习模型预测复发。随访中117例(17.9%)复发,模型AUC为0.7504±0.0856,SHAP分析识别诊断时年龄较大、PVAS较高、女性及尿检异常为最有影响的预测因素。该模型和列线图可能有助于风险分层和针对性随访。

要点

  • 混合集成模型预测儿童IgAV复发AUC为0.7504±0.0856。
  • 诊断时年龄较大、PVAS较高、女性、尿检异常为最重要预测因素。
  • 模型和列线图可能支持风险分层与针对性随访。

核心结论

  • 儿童IgAV复发可利用临床和实验室数据通过可解释混合集成机器学习方法预测。
  • 预测模型和列线图可能支持IgAV儿童的风险分层和针对性随访。

研究设计与样本

  • 回顾性队列研究纳入653例根据EULAR/PRINTO/PRES标准诊断的IgAV儿童。
  • 评估人口学、临床、实验室数据及诊断时PVAS,采用软投票策略组合树基机器学习算法。
  • 最终模型为随机森林、AdaBoost和Extra Trees的混合集成模型,并进行SHAP可解释性分析和列线图开发。

主要发现

  • 随访期间117例(17.9%)患者出现复发。
  • 混合集成模型获得最高AUC(0.7504±0.0856),精确率-召回率曲线下面积(0.4540±0.1308)和Brier分数(0.1315±0.0130)具有竞争力。
  • SHAP分析识别诊断时年龄较大、PVAS较高、女性性别和尿检异常为复发最有影响的预测因素。
  • 常规回归分析中PVAS与复发强相关,女性性别、诊断时年龄较大、面部皮疹和尿检异常为独立预测因素。

关键数值与推荐

  • IgAV诊断依据EULAR/PRINTO/PRES标准。
  • 复发预测模型AUC为0.7504±0.0856,精确率-召回率曲线下面积为0.4540±0.1308,Brier分数为0.1315±0.0130。
  • 随访中复发率为17.9%(117/653)。

临床怎么用

  • 利用临床和实验室数据及可解释混合集成模型对儿童IgAV进行复发风险预测。
  • 结合列线图进行个体化风险预测,支持风险分层和针对性随访。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: This study aimed to develop an explainable hybrid ensemble machine learning (ML) model to predict relapse in paediatric IgA vasculitis (IgAV) using routine clinical and laboratory data. METHODS: This retrospective cohort study included 653 children diagnosed with IgAV according to EULAR/PRINTO/Pediatric Rheumatology European Society (PRES) criteria. Demographic, clinical, laboratory data and the Paediatric Vasculitis Activity Score (PVAS) at diagnosis were evaluated. Several tree-based ML algorithms were evaluated and combined using a soft voting strategy. The hybrid ensemble model combining Random Forest, AdaBoost and Extra Trees was selected as the final model. SHapley Additive exPlanations (SHAP)-based explainability analysis was performed, and a nomogram was developed for individualized risk prediction. Conventional logistic regression analyses were also performed to identify independent predictors of relapse. RESULTS: Relapses were observed in 117 (17.9%) patients during follow-up. The hybrid ensemble model achieved the highest area under the receiver operating characteristic curve (0.7504 ± 0.0856) with competitive area under the precision-recall curve (0.4540 ± 0.1308) and Brier score (0.1315 ± 0.0130). SHAP analysis identified older age at diagnosis, higher PVAS, female sex and abnormal urinalysis findings as the most influential predictors of relapse. On conventional regression analysis, PVAS was strongly associated with relapse. In addition, female sex, older age at diagnosis, rash involving the face and abnormal urinalysis findings were independent predictors. CONCLUSION: Disease relapse in paediatric IgAV can be predicted using clinical and laboratory data with an explainable hybrid ensemble ML approach. The predictive model and nomogram may support risk stratification and targeted follow-up in children with IgAV.

来源:Rheumatology (Oxford),查看原文。版权归原作者所有。

引用

  1. Dizman EN, Turgut Z, Yildirim S, et al. Predicting relapse in paediatric IgA vasculitis in the era of machine learning: an explainable hybrid ensemble model. Rheumatology (Oxford). 2026. PMID: 42776039. doi:10.1093/rheumatology/keag533

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。