This article is more than 5 years old. Information may no longer be current.

Computer program identified novel phenotypes of asthma, other diseases

The utilization of an unsupervised technique capable of clustering more than 100 variables may offer promising approaches to understanding the underlying mechanisms of complex diseases that include asthma, according to data.

“The ultimate goal is to develop treatments that are based on the biological mechanisms underlying each cluster of patients, rather than simply treating the symptoms,” Wei Wu, PhD, an associate research professor in Carnegie Mellon’s Lane Center for Computational Biology, said in a press release

Wu and colleagues sought to identify subphenotypes of asthma by using blood, bronchoscopy, exhaled nitric oxide, and data from the Severe Asthma Research Program with unsupervised clustering, according to data. This approach was used in 112 clinical, physiologic, and inflammatory variables from 378 patients.

Wei Wu

Researchers identified 10 variable clusters and six subject clusters that appeared to vary and overlap with previously identified clusters.

Wu and colleagues then characterized patients with traditionally defined severe asthma through subject clusters 3 to 6. Those with early-onset allergic asthma with low lung function and eosinophilic inflammation (n=79) were included in cluster 4; cluster 5 consisted of those with later-onset (mostly severe asthma) with nasal polyps and eosinophilia (n=30).

Patients included in cluster 6 presented with persistent inflammation in blood and bronchoalveolar lavage fluid and exacerbations despite the use of high systemic corticosteroids.

“This approach has implications not just for asthma, but for all complex diseases, which include most chronic diseases,” Sally E. Wenzel, MD, director of the University of Pittsburgh Asthma Institute and the University of Pittsburgh School of Medicine, said in the release.

These include osteoporosis, Alzheimer’s disease, kidney disease, Parkinson’s disease and autoimmune diseases caused by a combination of genetic, environmental and lifestyle factors.

“Only a few years ago, we were persuaded that medications worked for everyone and that the only reason people had severe symptoms was that they weren’t taking their medications,” Wenzel said.

These results, however, confirm the presence of previously identified clusters.

Disclosure: See the study for a full list of relevant financial disclosures.