A newly discovered set of clinical variables may be able to determine whether individuals with asthma would benefit from systemic corticosteroid treatment, according to a new study.1
The researchers identified the 12 variables via machine learning techniques, and when processed by computer software, the variables can precisely predict an individual’s response to systemic corticosteroids.
To evaluate the response to corticosteroids across different asthma subphenotypes, the researchers applied a machine learning algorithm to 100 clinical, physiologic, inflammatory, and demographic variables from 346 adult participants with asthma in the Severe Asthma Research Program.
The algorithm identified 4 subgroups with different responses to corticosteroids.
Subgroups 1 and 2 were comprised of younger participants with allergic asthma and relatively normal lung function who were moderately responsive to the treatment. The 2 groups differed in their sputum neutrophil and macrophage percentages post-steroids.
The third group identified consisted of those with late-onset asthma, low lung function, and high baseline eosinophilia. This group was found to be most responsive to corticosteroids.
The final group consisted of primarily young women with obesity, severe airflow limitation, and little eosinophilic inflammation. This group was the least responsive to treatment.
Of the 100 variables the algorithm analyzed, the researchers determined that 12—including age of onset, weight, race, and scores on a quality-of-life questionnaire—could correctly categorize patients with high confidence if processed by a computer app. This was validated using an independent SARP test set on 182 additional participants.
“We believe we’ve made progress toward making precision medicine a reality,” said study coauthor Dr Wei Wu. “Five years ago, we were only able to categorize patients clinically. Now, using incredibly complex data, we’re able to predict how these subgroups will respond to a critical drug treatment.”2
Wu W, Bang S, Bleecker ER, et al. Multiview cluster analysis identifies variable corticosteroid response phenotypes in severe asthma [published online January 25, 2019]. Am J Respir Crit Care Med. https://doi.org/10.1164/rccm.201808-1543OC.
New method identifies which asthma patients respond to systemic corticosteroids [press release]. Pittsburgh, PA: Carnegie Mellon University; February 20, 2019.https://www.cmu.edu/news/stories/archives/2019/febr uary/asthma-predictions.html. Accessed February 20, 2019.