Turcatel Gianluca, Xiao Yi, Caveney Scott, Gnacadja Gilles, Kim Julie, Molfino Nestor A
Digital Health and Innovation, Amgen Inc., Thousand Oaks, CA, USA.
Global Development, Amgen Inc., One Amgen Center Dr, Thousand Oaks, CA, 91320, USA.
Adv Ther. 2025 Jan;42(1):362-374. doi: 10.1007/s12325-024-03053-y. Epub 2024 Nov 18.
Although clinical, functional, and biomarker data predict asthma exacerbations, newer approaches providing high accuracy of prognosis are needed for real-world decision-making in asthma. Machine learning (ML) leverages mathematical and statistical methods to detect patterns for future disease events across large datasets from electronic health records (EHR). This study conducted training and fine-tuning of ML algorithms for the real-world prediction of asthma exacerbations in patients with physician-diagnosed asthma.
Adults with ≥ 2 ICD9/10 asthma codes within 1 year and at least 30 days apart were identified from the Optum Panther EHR database between 2016 and 2023. An emergency department (ED), urgent care, or inpatient visit for asthma, while on systemic administration of corticosteroids, was considered an exacerbation. To predict factors associated with exacerbations in a 6-month study period, clinical information from patients was retrieved in the preceding 6-month baseline period. Clinical information included demographics, lab results, diagnoses, medications, immunizations, and allergies. Three models built using Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and Transformers algorithms were trained and tested on independent datasets. Predictions were explained using the SHAP (SHapley Additive exPlanations) library.
Of 1,331,934 patients with asthma, 16,279 (1.2%) experienced ≥ 1 exacerbation. XGBoost was the best predictive algorithm (area under the curve [AUC] = 0.964). Factors associated with exacerbations included a prior history of exacerbation, prednisone usage, high-dose albuterol usage, and elevated troponin I. Reduced probability of exacerbations was associated with receiving inhaled albuterol, vitamins, aspirin, statins, furosemide, and influenza vaccination.
This ML-based study on asthma in the real world confirmed previously known features associated with increased exacerbation risk for asthma, while uncovering not entirely understood features associated with reduced risk of asthma exacerbations. These findings are hypothesis-generating and should contribute to ongoing discussion of the strengths and limitations of ML and other supervised learning models in patient risk stratification.
尽管临床、功能和生物标志物数据可预测哮喘急性发作，但在哮喘的实际临床决策中，仍需要能提供高精度预后的新方法。机器学习（ML）利用数学和统计方法，从电子健康记录（EHR）的大型数据集中检测未来疾病事件的模式。本研究对ML算法进行了训练和微调，用于对医生诊断为哮喘的患者的哮喘急性发作进行实际预测。
从2016年至2023年的Optum Panther EHR数据库中，识别出一年内有≥2个ICD9/10哮喘编码且间隔至少30天的成年人。在全身使用皮质类固醇期间，因哮喘进行的急诊科（ED）、紧急护理或住院就诊被视为一次急性发作。为了预测6个月研究期内与急性发作相关的因素，在之前6个月的基线期检索患者的临床信息。临床信息包括人口统计学、实验室检查结果、诊断、用药、免疫接种和过敏情况。使用极端梯度提升（XGBoost）、长短期记忆（LSTM）和Transformer算法构建的三个模型在独立数据集上进行训练和测试。使用SHAP（SHapley Additive exPlanations）库对预测结果进行解释。
在1331934例哮喘患者中，16279例（1.2%）经历了≥1次急性发作。XGBoost是最佳预测算法（曲线下面积[AUC]=0.964）。与急性发作相关的因素包括既往急性发作史、泼尼松使用情况、高剂量沙丁胺醇使用情况和肌钙蛋白I升高。急性发作概率降低与吸入沙丁胺醇、维生素、阿司匹林、他汀类药物、呋塞米使用以及流感疫苗接种有关。
这项基于ML的真实世界哮喘研究证实了先前已知的与哮喘急性发作风险增加相关的特征，同时发现了一些尚未完全理解的与哮喘急性发作风险降低相关的特征。这些发现可生成假设，并应为正在进行的关于ML和其他监督学习模型在患者风险分层中的优势和局限性的讨论做出贡献。
