TY - JOUR
T1 - Prediction pathway for severe asthma exacerbations
T2 - a Bayesian network analysis
AU - Yadav, Chandra Prakash
AU - Chakraborty, Atlanta
AU - Price, David B.
AU - Lim, Laura Huey Mien
AU - Juang, Yah Ru
AU - Beasley, Richard
AU - Sadatsafavi, Mohsen
AU - Janson, Christer
AU - Siyue, Mariko Koh
AU - Wang, Eileen
AU - Wechsler, Michael E.
AU - Jackson, David J.
AU - Busby, John
AU - Heaney, Liam G.
AU - Pfeffer, Paul E.
AU - Mahboub, Bassam
AU - Perng, Diahn-Warng
AU - Cosio, Borja G.
AU - Perez-de-Llano, Luis
AU - Al-Lehebi, Riyad
AU - Larenas-Linnemann, Désirée
AU - Al-Ahmad, Mona S.
AU - Rhee, Chin Kook
AU - Iwanaga, Takashi
AU - Heffler, Enrico
AU - Canonica, Giorgio Walter
AU - Costello, Richard W.
AU - Papadopoulos, Nikolaos G.
AU - Papaioannou, Andriana I.
AU - Porsbjerg, Celeste M.
AU - Torres-Duque, Carlos A.
AU - Christoff, George C.
AU - Popov, Todor A.
AU - Hew, Mark
AU - Peters, Matthew J.
AU - Gibson, Peter G.
AU - Máspero, Jorge
AU - Bergeron, Celine
AU - Cerda, Saraid
AU - Contreras, Elvia Angelica
AU - Chen, Wenjia
N1 - Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.
PY - 2025/8
Y1 - 2025/8
N2 - Background: 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. Research Question: How do the interplays of clinically relevant predictors lead to severe exacerbations in patients with severe asthma? Study Design and Methods: 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. Results: The Bayesian network analysis revealed that blood eosinophil count, fractional exhaled nitric oxide level, and FEV1 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 FEV1. 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. Interpretation: 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.
AB - Background: 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. Research Question: How do the interplays of clinically relevant predictors lead to severe exacerbations in patients with severe asthma? Study Design and Methods: 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. Results: The Bayesian network analysis revealed that blood eosinophil count, fractional exhaled nitric oxide level, and FEV1 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 FEV1. 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. Interpretation: 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.
KW - asthma
KW - Bayesian network
KW - causal prediction
KW - influence diagram
KW - model validation
KW - risk prediction
KW - severe exacerbation
UR - https://www.scopus.com/pages/publications/105010296198
U2 - 10.1016/j.chest.2025.04.046
DO - 10.1016/j.chest.2025.04.046
M3 - Article
C2 - 40398558
AN - SCOPUS:105010296198
SN - 0012-3692
VL - 168
SP - 301
EP - 316
JO - Chest
JF - Chest
IS - 2
ER -