The purpose of a new study published in The Journal of Allergy and Clinical Immunology was to demonstrate clinical outcomes of asthma by multidimensional analyses of a long-term real-world database and a prediction model of severe asthma, using machine learning.

The database included 567 severe and 1,337 non-severe adult asthmatics, who had been monitored during a follow-up of up to 10 years. Here, longitudinal changes in eosinophilic inflammation, lung function and the annual number of asthma exacerbation (AE) were evaluated using linear mixed effects model. Least absolute shrinkage and selection operator logistic regression was used to develop a prediction model for severe asthma. Model performance was evaluated and validated.

The findings revealed that severe asthmatics had higher blood eosinophil and neutrophil counts at baseline than non-severe asthmatics; blood eosinophil counts showed significantly slower declines in severe asthmatics than non-severe asthmatics throughout the follow-up. While severe asthmatics had a lower level of forced expiratory volume in 1 second, which declined faster than non-severe asthmatics. Additionally, they showed a higher annual number of severe AEs than non-severe asthmatics. The prediction model for severe asthma consisted of 17 variables, including novel biomarkers.

From the results, it was concluded that severe asthma is a distinct phenotype of asthma with persistent eosinophilia, progressive lung function decline and frequent severe AEs even on regular asthma medication.

Source: The Journal of Allergy and Clinical Immunology. 2020 Oct 10;S2213-2198(20)31105-3. doi: 10.1016/j.jaip.2020.09.055. Online ahead of print.