Wu Hailin, Sun Yinghua, Tang Zifei, Qin Xiaojiao, Wang Yuhuan, Huang Ying
Department of Gastroenterology, Children's Hospital of Fudan University, National Children's Medical Center, Shanghai, People's Republic of China.
Department of Ultrasound, Children's Hospital of Fudan University, National Children's Medical Center, Shanghai, People's Republic of China.
J Inflamm Res. 2025 Jul 12;18:9107-9118. doi: 10.2147/JIR.S529537. eCollection 2025.
Early identification of pediatric inflammatory bowel disease (IBD) improves long-term outcomes; yet, significant diagnostic delays persist. This study aimed to establish and validate the optimal model of noninvasive evaluation tests to help clinicians with the early identification of pediatric IBD.
The study adopted a retrospective development and prospective temporal validation design within the same clinical center. A cohort of 314 pediatric patients (IBD, 103; non-IBD, 211) was used to develop a logistic regression model. The model based on noninvasive features, including IBD-related symptoms, routine laboratory tests, and transabdominal ultrasound findings. Ultrasound parameters included Limberg score >1 (bowel wall thickening with blood flow), increased mesenteric fat, disrupted wall layering, and enlarged lymph nodes. The ultrasound operator was blinded to laboratory and endoscopic results. Feature selection was performed using logistic regression and random forest methods. Model performance was assessed via bootstrapped internal validation (1000 resamples), and temporally validated in a prospective cohort of 66 children (IBD, 19; non-IBD, 47).
In the importance assessment, the ultrasound feature of Limberg level >1 was identified as the most valuable feature, followed by the erythrocyte sedimentation rate, fecal calprotectin, C-reactive protein and hypoalbuminemia. The most valuable clinical symptom identified was active perianal abscess or fistula. The model, constructed from these features, demonstrated high accuracy and robustness in both internal validation (area under the curve, 0.97 [95% confidence interval: 0.95-0.98]) and temporal external validation (area under the curve, 0.94 [95% confidence interval: 0.86-1.00]). In the external validation set, the model showed good calibration, with a calibration slope of 0.86, and a Brier score of 0.08.
The nomogram, based on noninvasive factors, can identify children with IBD at early stages using accessible noninvasive testing.
早期识别儿童炎症性肠病（IBD）可改善长期预后；然而，显著的诊断延迟仍然存在。本研究旨在建立并验证非侵入性评估测试的最佳模型，以帮助临床医生早期识别儿童IBD。
本研究在同一临床中心采用回顾性开发和前瞻性时间验证设计。一组314例儿科患者（IBD患者103例，非IBD患者211例）用于构建逻辑回归模型。该模型基于非侵入性特征，包括IBD相关症状、常规实验室检查和经腹超声检查结果。超声参数包括Limberg评分>1（肠壁增厚伴血流）、肠系膜脂肪增加、肠壁分层破坏和淋巴结肿大。超声检查操作人员对实验室和内镜检查结果不知情。使用逻辑回归和随机森林方法进行特征选择。通过自抽样内部验证（1000次重复抽样）评估模型性能，并在一个由66名儿童组成的前瞻性队列（IBD患者19例，非IBD患者47例）中进行时间验证。
在重要性评估中，Limberg水平>1的超声特征被确定为最有价值的特征，其次是红细胞沉降率、粪便钙卫蛋白、C反应蛋白和低白蛋白血症。确定的最有价值的临床症状是活动性肛周脓肿或瘘管。由这些特征构建的模型在内部验证（曲线下面积，0.97[95%置信区间：0.95-0.98]）和时间外部验证（曲线下面积，0.94[95%置信区间：0.86-1.00]）中均显示出高准确性和稳健性。在外部验证集中，该模型显示出良好的校准，校准斜率为0.86，Brier评分为0.08。
基于非侵入性因素的列线图可以通过可及的非侵入性检测在早期识别IBD患儿。
