机器学习预测早发性特应性皮炎患儿哮喘与过敏性鼻炎发病风险
2026/04/28
摘要
背景：早发性特应性皮炎是呼吸道特应性疾病的明确前驱病变，但目前仍难以甄别哪些患儿会在学龄期进展为持续性中重度哮喘及过敏性鼻炎。
目的：本研究旨在通过构建并验证机器学习模型预测3岁前确诊特应性皮炎患儿发生持续性中重度哮喘、过敏性鼻炎的个体化发病风险。
方法：本研究基于南加州凯撒永久医疗体系的纵向电子健康档案数据，开展回顾性出生队列研究。针对5～11岁儿童，分别构建哮喘、过敏性鼻炎两类结局的预测模型：整合精细化结构化临床指标的全量电子病历模型，以及依托临床常规易得指标构建的简易临床模型。采用曲线下面积（AUC）、灵敏度、阳性预测值（PPV）及不同风险分层的校准度，综合评估模型效能。
结果：本研究共纳入10688名符合入组标准的儿童。哮喘预测模型区分效能优异：全量模型AUC 为0.893，简易模型AUC为0.892。在特异度95%阈值下，全量模型灵敏度40.4%、阳性预测值39.3%；简易模型灵敏度36.2%、阳性预测值33.8%。过敏性鼻炎模型预测效能中等，全量模型AUC 0.793，简易模型AUC 0.773；特异度90%时，全量模型灵敏度35.5%、阳性预测值72.7%，简易模型灵敏度34.0%、阳性预测值69.2%。所有模型校准度良好，高危人群风险预测一致性佳。
结论：基于婴幼儿早期临床数据构建的机器学习模型，可精准分层学龄期儿童中重度持续性哮喘与过敏性鼻炎的发病风险，为开展主动化、个体化防治管理提供循证依据。
Machine Learning Prediction of Asthma and Allergic Rhinitis in Children with Early-Onset Atopic Dermatitis.
Chen W, Zhou B, Schatz M, Subramaniam A, Stanford RH, Shams M, Zeiger RS.
Abstract
BACKGROUND:Early-onset atopic dermatitis is a known precursor to respiratory atopic diseases, but identifying which children will develop persistent moderate-to-severe asthma and allergic rhinitis in school age remains difficult.
OBJECTIVES:To develop and validate machine learning models that predict individualized risk for moderate-to-severe persistent asthma and allergic rhinitis in children diagnosed with AD before age 3.
METHODS:We conducted a retrospective birth cohort study using longitudinal electronic health record data from Kaiser Permanente Southern California. Two prediction models were developed for each outcome (asthma and rhinitis) among children aged 5-11: a Comprehensive Electronic Health Records Model using detailed, structured clinical variables and a Simplified Clinical Model based on fewer, routinely available clinical features. Model performance was evaluated using area under the curve (AUC), sensitivity, positive predictive value (PPV), and calibration across risk strata.
RESULTS:Among eligible 10,688 children, asthma models demonstrated strong discrimination (AUC: 0.893 Comprehensive; 0.892 Simplified). At 95% specificity, the Comprehensive model achieved 40.4% sensitivity and 39.3% PPV; the Simplified model reached 36.2% sensitivity and 33.8% PPV. Rhinitis models showed moderate performance (AUC: 0.793 and 0.773); at 90% specificity, the Comprehensive model achieved 35.5% sensitivity and 72.7% PPV, while the Simplified model reached 34.0% sensitivity and 69.2% PPV. Calibration was acceptable, with strong agreement in the highest-risk groups.
CONCLUSION: Machine-learning models using early-life clinical data can accurately stratify risk for moderate-to-severe persistent asthma and allergic rhinitis by school age, supporting proactive, individualized care.
背景：早发性特应性皮炎是呼吸道特应性疾病的明确前驱病变，但目前仍难以甄别哪些患儿会在学龄期进展为持续性中重度哮喘及过敏性鼻炎。
目的：本研究旨在通过构建并验证机器学习模型预测3岁前确诊特应性皮炎患儿发生持续性中重度哮喘、过敏性鼻炎的个体化发病风险。
方法：本研究基于南加州凯撒永久医疗体系的纵向电子健康档案数据，开展回顾性出生队列研究。针对5～11岁儿童，分别构建哮喘、过敏性鼻炎两类结局的预测模型：整合精细化结构化临床指标的全量电子病历模型，以及依托临床常规易得指标构建的简易临床模型。采用曲线下面积（AUC）、灵敏度、阳性预测值（PPV）及不同风险分层的校准度，综合评估模型效能。
结果：本研究共纳入10688名符合入组标准的儿童。哮喘预测模型区分效能优异：全量模型AUC 为0.893，简易模型AUC为0.892。在特异度95%阈值下，全量模型灵敏度40.4%、阳性预测值39.3%；简易模型灵敏度36.2%、阳性预测值33.8%。过敏性鼻炎模型预测效能中等，全量模型AUC 0.793，简易模型AUC 0.773；特异度90%时，全量模型灵敏度35.5%、阳性预测值72.7%，简易模型灵敏度34.0%、阳性预测值69.2%。所有模型校准度良好，高危人群风险预测一致性佳。
结论：基于婴幼儿早期临床数据构建的机器学习模型，可精准分层学龄期儿童中重度持续性哮喘与过敏性鼻炎的发病风险，为开展主动化、个体化防治管理提供循证依据。
（中日友好医院呼吸与危重症医学科 张婧媛 摘译 林江涛 审校）
（J Allergy Clin Immunol. 2026 Apr 17:S0091-6749(26)00261-7. doi: 10.1016/j.jaci.2026.03.025.）
（J Allergy Clin Immunol. 2026 Apr 17:S0091-6749(26)00261-7. doi: 10.1016/j.jaci.2026.03.025.）
Machine Learning Prediction of Asthma and Allergic Rhinitis in Children with Early-Onset Atopic Dermatitis.
Chen W, Zhou B, Schatz M, Subramaniam A, Stanford RH, Shams M, Zeiger RS.
Abstract
BACKGROUND:Early-onset atopic dermatitis is a known precursor to respiratory atopic diseases, but identifying which children will develop persistent moderate-to-severe asthma and allergic rhinitis in school age remains difficult.
OBJECTIVES:To develop and validate machine learning models that predict individualized risk for moderate-to-severe persistent asthma and allergic rhinitis in children diagnosed with AD before age 3.
METHODS:We conducted a retrospective birth cohort study using longitudinal electronic health record data from Kaiser Permanente Southern California. Two prediction models were developed for each outcome (asthma and rhinitis) among children aged 5-11: a Comprehensive Electronic Health Records Model using detailed, structured clinical variables and a Simplified Clinical Model based on fewer, routinely available clinical features. Model performance was evaluated using area under the curve (AUC), sensitivity, positive predictive value (PPV), and calibration across risk strata.
RESULTS:Among eligible 10,688 children, asthma models demonstrated strong discrimination (AUC: 0.893 Comprehensive; 0.892 Simplified). At 95% specificity, the Comprehensive model achieved 40.4% sensitivity and 39.3% PPV; the Simplified model reached 36.2% sensitivity and 33.8% PPV. Rhinitis models showed moderate performance (AUC: 0.793 and 0.773); at 90% specificity, the Comprehensive model achieved 35.5% sensitivity and 72.7% PPV, while the Simplified model reached 34.0% sensitivity and 69.2% PPV. Calibration was acceptable, with strong agreement in the highest-risk groups.
CONCLUSION: Machine-learning models using early-life clinical data can accurately stratify risk for moderate-to-severe persistent asthma and allergic rhinitis by school age, supporting proactive, individualized care.
上一篇：
个人网络推演识别复发性喘息与哮喘高危患儿
下一篇：
英格兰多发长期疾病（多重发病）的进展：一项针对4960万成年人的基于人群的描述性研究
