用机器学习预测儿童哮喘急性加重，提升早期干预精准度。
AI for pRedicting Exacerbations in KIDs with aSthma (AIRE-KIDS)
- 基于电子病历与环境数据训练梯度提升树模型，识别高风险患儿。
- 模型AUC达0.712，F1分数0.51，显著优于现有决策规则（F1=0.334）。
- 适用于儿科临床预警系统，帮助医生提前干预哮喘恶化风险。
反复急性加重是许多儿童哮喘患者常见但可预防的结局。利用电子病历（EMR）数据的机器学习（ML）算法可准确识别高风险患儿，推动其接受预防性综合护理以避免疾病恶化。本研究基于多伦多儿童医院（CHEO）2017年2月至2019年2月（N=2716）的回顾性非新冠时期数据，结合环境污染物暴露与社区边缘化信息，训练多种机器学习模型，包括梯度提升树（LGBM、XGB）及三种开源大语言模型（DistilGPT2、Llama 3.2 1B 和 Llama-8b-UltraMedical）。模型经调优与校准后，在2022年7月至2023年4月（N=1237）的新冠后回顾数据集上验证。通过曲线下面积（AUC）和F1分数评估性能，使用SHAP值分析关键预测特征。最终，LGBM模型表现最佳，用于预测急诊就诊（AIRE-KIDS_ED）的关键特征包括：既往哮喘急诊史、加拿大分诊严重程度评分、医疗复杂性、食物过敏、非哮喘呼吸系统相关急诊史及年龄，达到AUC 0.712，F1分数0.51。另一模型（AIRE-KIDS_HOSP）的关键特征包括医疗复杂性、既往哮喘急诊史、急诊平均等待时间、分诊时儿科呼吸评估量表得分及食物过敏。
原文摘要 · Abstract (English)
Recurrent exacerbations remain a common yet preventable outcome for many children with asthma. Machine learning (ML) algorithms using electronic medical records (EMR) could allow accurate identification of children at risk for exacerbations and facilitate referral for preventative comprehensive care to avoid this morbidity. We developed ML algorithms to predict repeat severe exacerbations (i.e. asthma-related emergency department (ED) visits or future hospital admissions) for children with a prior asthma ED visit at a tertiary care children's hospital. Retrospective pre-COVID19 (Feb 2017 - Feb 2019, N=2716) Epic EMR data from the Children's Hospital of Eastern Ontario (CHEO) linked with environmental pollutant exposure and neighbourhood marginalization information was used to train various ML models. We used boosted trees (LGBM, XGB) and 3 open-source large language model (LLM) approaches (DistilGPT2, Llama 3.2 1B and Llama-8b-UltraMedical). Models were tuned and calibrated then validated in a second retrospective post-COVID19 dataset (Jul 2022 - Apr 2023, N=1237) from CHEO. Models were compared using the area under the curve (AUC) and F1 scores, with SHAP values used to determine the most predictive features. The LGBM ML model performed best with the most predictive features in the final AIRE-KIDS_ED model including prior asthma ED visit, the Canadian triage acuity scale, medical complexity, food allergy, prior ED visits for non-asthma respiratory diagnoses, and age for an AUC of 0.712, and F1 score of 0.51. This is a nontrivial improvement over the current decision rule which has F1=0.334. While the most predictive features in the AIRE-KIDS_HOSP model included medical complexity, prior asthma ED visit, average wait time in the ED, the pediatric respiratory assessment measure score at triage and food allergy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。