Imaging-based clusters in current smokers of the COPD cohort associate with clinical characteristics: the SubPopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS)

Abstract

Background: Classification of COPD is usually based on the severity of airflow, which may not sensitively differentiate subpopulations. Using a multiscale imaging-based cluster analysis (MICA), we aim to identify subpopulations for current smokers with COPD.

Methods: Among the SPIROMICS subjects, we analyzed computed tomography images at total lung capacity (TLC) and residual volume (RV) of 284 current smokers. Functional variables were derived from registration of TLC and RV images, e.g. functional small airways disease (fSAD%). Structural variables were assessed at TLC images, e.g. emphysema and airway wall thickness and diameter. We employed an unsupervised method for clustering.

Results: Four clusters were identified. Cluster 1 had relatively normal airway structures; Cluster 2 had an increase of fSAD% and wall thickness; Cluster 3 exhibited a further increase of fSAD% but a decrease of wall thickness and airway diameter; Cluster 4 had a significant increase of fSAD% and emphysema. Clinically, Cluster 1 showed normal FEV1/FVC and low exacerbations. Cluster 4 showed relatively low FEV1/FVC and high exacerbations. While Cluster 2 and Cluster 3 showed similar exacerbations, Cluster 2 had the highest BMI among all clusters.

Conclusions: Association of imaging-based clusters with existing clinical metrics suggests the sensitivity of MICA in differentiating subpopulations.

Keywords: COPD; Current smokers; Emphysema; Functional small airway disease; Imaging-based cluster analysis.

Conflict of interest statement

Ethics approval and consent to participate

Ethics and consent were approved by SPIROMICS committee.

Consent for publication

The paper was approved by SPIROMICS publications and presentation committee.

Competing interests

There is no conflict of interest for all authors including:

Babak Haghighi, Sanghun Choi, Jiwoong Choi, Eric A. Hoffman, Alejandro P. Comellas, John D. Newell Jr., R. Graham Barr, Eugene Bleecker, Christopher B. Cooper, David Couper, MeiLan Han, Nadia N. Hansel, Richard E. Kanner, Ella A. Kazerooni, Eric C Kleerup, Fernando J. Martinez, Wanda O’Neal, Stephen I Rennard, Prescott G Woodruff, Ching-Long Lin. Although E.A. Hoffman is a shareholder in VIDA diagnostics, which is commercializing lung image analysis software derived from the University of Iowa lung imaging group.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Figures

Fig. 1

A scree plot for determining the optimal number of principal components

Fig. 2

a Clustering membership of K-means clustering on 2-D projected coordinates; (b) Clustering membership of Hierarchical clustering on 2-D projected coordinates

Fig. 3

a Percentage of emphysema (Emph%) for four clusters and the healthy control group (green). † P > 0.05 between clusters 1, 2, 3 and the healthy group. P < 0.05 between Cluster 4 and other groups for all pairwise comparisons (b) Percentage of small airway disease (fSAD%) for four clusters and the healthy control group (green). ‡ P < 0.05 for comparisons between four clusters 2, 3, 4 and the healthy group for all pairwise comparison. P > 0.05 for between Cluster 1 and the healthy group

Fig. 4

A summary of imaging and clinical variables for four clusters

Fig. 5

Predicting imaged-based cluster using only 7 important variables with a classification tree (“simple” imaging-based clustering). Variables are Jacobian (Total), Dh* (sLLL), Dh* (sRLL), WT* (sRUL), WT* (sRML), βtissue (LLL) and fSAD% (Total) with 89% accuracy compared with “original” imaging-based clusters using 69 variables

Fig. 6

PRM based on GOLD stages and imaging-based derived clusters

Fig. 7

FEV1 and FEV1/FVC based of GOLD stages and imaging-based clusters. Dashed lines represent fixed threshold criteria (FEV1 = 0.8, FEV1/FVC = 0.7) used to distinguish possible PRISm subjects