Clustering to identify novel phenotypes in childhood asthma
University Of Wisconsin-Madison, Madison WI
Investigators
Linked publications & trials
Abstract
DESCRIPTION (provided by applicant): Childhood asthma is a heterogeneous disease. This is evident given the broad range of clinical characteristics and treatment responses for children defined as asthmatic. Current classification systems for asthma phenotypes are inadequate to fully understand the pathogenesis, pathophysiology, and treatment outcomes of asthma. Given the heterogeneous nature of asthma, novel ensemble clustering of childhood asthma using data from five clinical trials is proposed. It is hypothesized these discovered phenotypes (or clusters) will have defining characteristics that suggest unique etiologies and appropriate treatment strategies. The aims are to (1) perform ensemble clustering of childhood asthma and describe characteristics for the observed phenotype, (2) develop a model to classify childhood asthma into the phenotypes previously defined in Aim (1), and (3) retrospectively determine whether childhood asthma phenotypes identified by ensemble clustering correlate with treatment responses in clinical trials. We expect (1) fewer than ten phenotypes to be identified with some attributes over- represented in each phenotype, (2) to develop a simple, easily interpretable classification model, and (3) to identify phenotypes for which clinical trial treatments were effective or ineffective. On the path toward personalized medicine, novel research with ensemble clustering and a large dataset with clinical trial outcomes will advance the field by validating and hypothesizing childhood asthma pathogenesis, pathophysiology and treatment responses. PUBLIC HEALTH RELEVANCE: Childhood asthma is likely not a single disease, but rather a heterogeneous disease with many phenotypes (or subtypes). Computational analysis can identify and elucidate the characteristics of these phenotypes. These phenotypes may provide insight into the causes of and appropriate treatments for asthma.
View original record on NIH RePORTER →