Zhu Ning, Chen Tingting, Wang Lei, Cai Fangyuan, Zhong Xiaoying, Fang Xiaoxiao, Chen Mingxin, Lin Junyi, Tu Huixi, Zhao Yimin, Hu Yihan, Zhang Weixi, Song Jingjing
Department of Pediatric Allergy and Immunology, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China.
Department of Pediatrics, Yiwu Maternity and Children Hospital, Yiwu, Zhejiang, 322000, China.
World Allergy Organ J. 2025 Jul 12;18(8):101088. doi: 10.1016/j.waojou.2025.101088. eCollection 2025 Aug.
Food allergy (FA) directly affects children's nutritional status, with a significantly higher risk of growth retardation among affected children. Identifying risk factors for FA and strategies to promote growth catch-up can offer valuable guidance for the treatment and nutritional management of children with FA.
We developed machine learning models to predict the occurrence of immunoglobulin E-mediated food allergy (IgE-FA) and the likelihood of post-treatment growth catch-up, using demographic and biological baseline data.
We recruited 130 children aged 0-3 years with IgE-FA as the FA group and 65 healthy children as the control group.
Using machine-learning-based bioinformatics analysis, we developed predictive models and identified key factors influencing growth in IgE-FA children. The IgE-FA prediction model achieved an area under the curve (AUC) of 0.78 (95% CI: 0.708-0.848). Greater birthweight, a family history of allergies, and early-life antibiotic exposure were identified as risk factors for IgE-FA. Notably, early antibiotic exposure increased the risk of IgE-FA by 2.77 times and the risk of milk allergy by 2.56 times. Growth analysis, both overall and by subgroup, revealed that pre-treatment weight strongly correlates with post-treatment height, weight, and body mass index (BMI), offering new perspectives for predicting and monitoring outcomes in IgE-FA. Milk allergy mainly impacts weight catch-up, whereas egg allergy affects BMI. Controlled avoidance of allergenic foods supports growth recovery in affected children.
Growth in children with IgE-FA is often restricted, and achieving expected growth levels remains challenging even after treatment. Weight is a sensitive and accessible indicator for predicting IgE-FA and plays a key role in post-treatment growth catch-up. Early and personalized nutritional guidance, along with regular weight monitoring, is recommended for all children with food allergy.
食物过敏（FA）直接影响儿童的营养状况，患病儿童生长发育迟缓的风险显著更高。识别FA的风险因素以及促进生长追赶的策略可为FA儿童的治疗和营养管理提供有价值的指导。
我们利用人口统计学和生物学基线数据，开发了机器学习模型来预测免疫球蛋白E介导的食物过敏（IgE-FA）的发生以及治疗后生长追赶的可能性。
我们招募了130名0至3岁患有IgE-FA的儿童作为FA组，以及65名健康儿童作为对照组。
通过基于机器学习的生物信息学分析，我们开发了预测模型并确定了影响IgE-FA儿童生长的关键因素。IgE-FA预测模型的曲线下面积（AUC）为0.78（95%CI：0.708-0.848）。出生体重较大、有过敏家族史和早期接触抗生素被确定为IgE-FA的风险因素。值得注意的是，早期接触抗生素使IgE-FA的风险增加了2.77倍，牛奶过敏的风险增加了2.56倍。总体和亚组的生长分析表明，治疗前体重与治疗后的身高、体重和体重指数（BMI）密切相关，为预测和监测IgE-FA的结果提供了新的视角。牛奶过敏主要影响体重追赶，而鸡蛋过敏影响BMI。控制避免食用致敏食物有助于患病儿童的生长恢复。
IgE-FA儿童的生长通常受到限制，即使在治疗后达到预期生长水平仍具有挑战性。体重是预测IgE-FA的敏感且可获取的指标，并且在治疗后生长追赶中起关键作用。建议对所有食物过敏儿童进行早期和个性化的营养指导以及定期体重监测。
