Yadav Chandra Prakash, Chakraborty Atlanta, Price David B, Lim Laura Huey Mien, Juang Yah Ru, Beasley Richard, Sadatsafavi Mohsen, Janson Christer, Siyue Mariko Koh, Wang Eileen, Wechsler Michael E, Jackson David J, Busby John, Heaney Liam G, Pfeffer Paul E, Mahboub Bassam, Perng Diahn-Warng, Cosio Borja G, Perez-de-Llano Luis, Al-Lehebi Riyad, Larenas-Linnemann Désirée, Al-Ahmad Mona S, Rhee Chin Kook, Iwanaga Takashi, Heffler Enrico, Canonica Giorgio Walter, Costello Richard W, Papadopoulos Nikolaos G, Papaioannou Andriana I, Porsbjerg Celeste M, Torres-Duque Carlos A, Christoff George C, Popov Todor A, Hew Mark, Peters Matthew J, Gibson Peter G, Máspero Jorge, Bergeron Celine, Cerda Saraid, Contreras Elvia Angelica, Chen Wenjia
Saw Swee Hock School of Public Health, National University of Singapore, Ann Arbor, MI.
University of Michigan, Ann Arbor, MI.
Chest. 2025 Aug;168(2):301-316. doi: 10.1016/j.chest.2025.04.046. Epub 2025 May 19.
Accurate risk prediction of exacerbations is pivotal in severe asthma management. Multiple risk factors are at play, but the pathway of risk prediction remains unclear.
How do the interplays of clinically relevant predictors lead to severe exacerbations in patients with severe asthma?
Patients with severe asthma (n = 6,814, aged ≥ 18 years), biologic naive, were identified from the Severe Asthma Registry (2017-2021). Relevant predictors covered demographics, lung function, inflammation biomarkers, health care use, medications, exacerbation history, and comorbidities. A Bayesian network, representing the prediction process of severe exacerbations, was obtained by combining expert knowledge and machine learning algorithms. Internal validation was performed. The proposed influence diagram integrated decision and utility nodes into the prediction pathway.
The Bayesian network analysis revealed that blood eosinophil count, fractional exhaled nitric oxide level, and FEV directly influenced the transition between prior and future severe exacerbations. The presence of chronic rhinosinusitis indirectly affected such transition by directly influencing blood eosinophil count, fractional exhaled nitric oxide, and % predicted FEV. Macrolide use independently affected history of exacerbations to influence future severe asthma exacerbations. Model discrimination was moderate in 10-fold cross-validation and leave-1-country-out cross-validation, and model calibration was high in train-test data.
This study identified an essential prediction pathway of severe exacerbation, which involves the influence of chronic rhinosinusitis on the immediate predictors of risk transition from current to future severe asthma exacerbations. Macrolide use was another essential prediction pathway identified. The findings support shared clinical decision-making in severe asthma treatment.
准确预测哮喘急性加重对于重度哮喘的管理至关重要。多种风险因素在其中起作用，但风险预测的途径仍不明确。
临床相关预测因素之间的相互作用如何导致重度哮喘患者发生严重急性加重？
从重度哮喘注册研究（2017 - 2021年）中识别出未使用生物制剂、年龄≥18岁的重度哮喘患者（n = 6814）。相关预测因素包括人口统计学特征、肺功能、炎症生物标志物、医疗保健利用情况、药物治疗、急性加重病史和合并症。通过结合专家知识和机器学习算法，获得了一个代表严重急性加重预测过程的贝叶斯网络。进行了内部验证。所提出的影响图将决策和效用节点整合到预测途径中。
贝叶斯网络分析显示，血液嗜酸性粒细胞计数、呼出一氧化氮分数水平和第一秒用力呼气容积直接影响既往和未来严重急性加重之间的转变。慢性鼻 - 鼻窦炎的存在通过直接影响血液嗜酸性粒细胞计数、呼出一氧化氮分数和预计第一秒用力呼气容积百分比间接影响这种转变。使用大环内酯类药物独立影响急性加重病史，进而影响未来重度哮喘急性加重。在10折交叉验证和留一国家交叉验证中，模型辨别能力中等，在训练 - 测试数据中模型校准良好。
本研究确定了严重急性加重的一条重要预测途径，其中涉及慢性鼻 - 鼻窦炎对从当前到未来重度哮喘急性加重风险转变的直接预测因素的影响。使用大环内酯类药物是另一条确定的重要预测途径。这些发现支持重度哮喘治疗中的共同临床决策。
