@article {1433706,
	title = {Cluster analysis in the COPDGene study identifies subtypes of smokers with distinct patterns of airway disease and emphysema},
	journal = {Thorax},
	volume = {69},
	number = {5},
	year = {2014},
	month = {2014 May},
	pages = {415-22},
	abstract = {BACKGROUND: There is notable heterogeneity in the clinical presentation of patients with COPD. To characterise this heterogeneity, we sought to identify subgroups of smokers by applying cluster analysis to data from the COPDGene study.

METHODS: We applied a clustering method, k-means, to data from 10 192 smokers in the COPDGene study. After splitting the sample into a training and validation set, we evaluated three sets of input features across a range of k (user-specified number of clusters). Stable solutions were tested for association with four COPD-related measures and five genetic variants previously associated with COPD at genome-wide significance. The results were confirmed in the validation set.

FINDINGS: We identified four clusters that can be characterised as (1) relatively resistant smokers (ie, no/mild obstruction and minimal emphysema despite heavy smoking), (2) mild upper zone emphysema-predominant, (3) airway disease-predominant and (4) severe emphysema. All clusters are strongly associated with COPD-related clinical characteristics, including exacerbations and dyspnoea (p,
	keywords = {Cluster Analysis, Female, Follow-Up Studies, Genetic Predisposition to Disease, Genome-Wide Association Study, Humans, Male, Middle Aged, Phenotype, Pulmonary Disease, Chronic Obstructive, Pulmonary Emphysema, Retrospective Studies, Severity of Illness Index, Smoking, Spirometry, Tomography, X-Ray Computed},
	issn = {1468-3296},
	doi = {10.1136/thoraxjnl-2013-203601},
	author = {Castaldi, Peter J and Dy, Jennifer and Ross, James and Chang, Yale and Washko, George R and Curran-Everett, Douglas and Williams, Andre and Lynch, David A and Make, Barry J and Crapo, James D and Bowler, Russ P and Regan, Elizabeth A and Hokanson, John E and Kinney, Greg L and Han, MeiLan K and Soler, Xavier and Ramsdell, Joseph W and Barr, R Graham and Foreman, Marilyn and van Beek, Edwin and Casaburi, Richard and Criner, Gerald J and Lutz, Sharon M and Rennard, Steven I and Santorico, Stephanie and Sciurba, Frank C and DeMeo, Dawn L and Hersh, Craig P and Silverman, Edwin K and Cho, Michael H}
}