Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort

Ayodeji Adegunsoye, Justin Oldham, Jonathan H. Chung, Steven M. Montner, Cathryn Lee, Leah J. Witt, Danielle Stahlbaum, Rene S. Bermea, Lena W. Chen, Scully Hsu, Aliya N. Husain, Imre Noth, Rekha Vij, Mary E. Strek, Matthew Churpek

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Background: The current interstitial lung disease (ILD) classification has overlapping clinical presentations and outcomes. Cluster analysis modeling is a valuable tool in identifying distinct clinical phenotypes in heterogeneous diseases. However, this approach has yet to be implemented in ILD. Methods: Using cluster analysis, novel ILD phenotypes were identified among subjects from a longitudinal ILD cohort, and outcomes were stratified according to phenotypic clusters compared with subgroups according to current American Thoracic Society/European Respiratory Society ILD classification criteria. Results: Among subjects with complete data for baseline variables (N = 770), four clusters were identified. Cluster 1 (ie, younger white obese female subjects) had the highest baseline FVC and diffusion capacity of the lung for carbon monoxide (DLCO). Cluster 2 (ie, younger African-American female subjects with elevated antinuclear antibody titers) had the lowest baseline FVC. Cluster 3 (ie, elderly white male smokers with coexistent emphysema) had intermediate FVC and DLCO. Cluster 4 (ie, elderly white male smokers with severe honeycombing) had the lowest baseline DLCO. Compared with classification according to ILD subgroup, stratification according to phenotypic clusters was associated with significant differences in monthly FVC decline (Cluster 4, –0.30% vs Cluster 2, 0.01%; P <.0001). Stratification by using clusters also independently predicted progression-free survival (P <.001) and transplant-free survival (P <.001). Conclusions: Among adults with diverse chronic ILDs, cluster analysis using baseline characteristics identified four distinct clinical phenotypes that might better predict meaningful clinical outcomes than current ILD diagnostic criteria.

Original languageEnglish (US)
Pages (from-to)339-348
Number of pages10
JournalChest
Volume153
Issue number2
DOIs
StatePublished - Feb 1 2018

Fingerprint

Interstitial Lung Diseases
Cluster Analysis
Phenotype
Lung Volume Measurements
Antinuclear Antibodies
Emphysema
Carbon Monoxide
African Americans
Disease-Free Survival
Transplants

Keywords

  • cluster
  • interstitial lung disease
  • mortality
  • phenotype
  • pulmonary fibrosis

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine
  • Critical Care and Intensive Care Medicine
  • Cardiology and Cardiovascular Medicine

Cite this

Adegunsoye, A., Oldham, J., Chung, J. H., Montner, S. M., Lee, C., Witt, L. J., ... Churpek, M. (2018). Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort. Chest, 153(2), 339-348. https://doi.org/10.1016/j.chest.2017.09.026

Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort. / Adegunsoye, Ayodeji; Oldham, Justin; Chung, Jonathan H.; Montner, Steven M.; Lee, Cathryn; Witt, Leah J.; Stahlbaum, Danielle; Bermea, Rene S.; Chen, Lena W.; Hsu, Scully; Husain, Aliya N.; Noth, Imre; Vij, Rekha; Strek, Mary E.; Churpek, Matthew.

In: Chest, Vol. 153, No. 2, 01.02.2018, p. 339-348.

Research output: Contribution to journalArticle

Adegunsoye, A, Oldham, J, Chung, JH, Montner, SM, Lee, C, Witt, LJ, Stahlbaum, D, Bermea, RS, Chen, LW, Hsu, S, Husain, AN, Noth, I, Vij, R, Strek, ME & Churpek, M 2018, 'Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort', Chest, vol. 153, no. 2, pp. 339-348. https://doi.org/10.1016/j.chest.2017.09.026
Adegunsoye, Ayodeji ; Oldham, Justin ; Chung, Jonathan H. ; Montner, Steven M. ; Lee, Cathryn ; Witt, Leah J. ; Stahlbaum, Danielle ; Bermea, Rene S. ; Chen, Lena W. ; Hsu, Scully ; Husain, Aliya N. ; Noth, Imre ; Vij, Rekha ; Strek, Mary E. ; Churpek, Matthew. / Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort. In: Chest. 2018 ; Vol. 153, No. 2. pp. 339-348.
@article{664e5a8f8b8246b39e470460242985e0,
title = "Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort",
abstract = "Background: The current interstitial lung disease (ILD) classification has overlapping clinical presentations and outcomes. Cluster analysis modeling is a valuable tool in identifying distinct clinical phenotypes in heterogeneous diseases. However, this approach has yet to be implemented in ILD. Methods: Using cluster analysis, novel ILD phenotypes were identified among subjects from a longitudinal ILD cohort, and outcomes were stratified according to phenotypic clusters compared with subgroups according to current American Thoracic Society/European Respiratory Society ILD classification criteria. Results: Among subjects with complete data for baseline variables (N = 770), four clusters were identified. Cluster 1 (ie, younger white obese female subjects) had the highest baseline FVC and diffusion capacity of the lung for carbon monoxide (DLCO). Cluster 2 (ie, younger African-American female subjects with elevated antinuclear antibody titers) had the lowest baseline FVC. Cluster 3 (ie, elderly white male smokers with coexistent emphysema) had intermediate FVC and DLCO. Cluster 4 (ie, elderly white male smokers with severe honeycombing) had the lowest baseline DLCO. Compared with classification according to ILD subgroup, stratification according to phenotypic clusters was associated with significant differences in monthly FVC decline (Cluster 4, –0.30{\%} vs Cluster 2, 0.01{\%}; P <.0001). Stratification by using clusters also independently predicted progression-free survival (P <.001) and transplant-free survival (P <.001). Conclusions: Among adults with diverse chronic ILDs, cluster analysis using baseline characteristics identified four distinct clinical phenotypes that might better predict meaningful clinical outcomes than current ILD diagnostic criteria.",
keywords = "cluster, interstitial lung disease, mortality, phenotype, pulmonary fibrosis",
author = "Ayodeji Adegunsoye and Justin Oldham and Chung, {Jonathan H.} and Montner, {Steven M.} and Cathryn Lee and Witt, {Leah J.} and Danielle Stahlbaum and Bermea, {Rene S.} and Chen, {Lena W.} and Scully Hsu and Husain, {Aliya N.} and Imre Noth and Rekha Vij and Strek, {Mary E.} and Matthew Churpek",
year = "2018",
month = "2",
day = "1",
doi = "10.1016/j.chest.2017.09.026",
language = "English (US)",
volume = "153",
pages = "339--348",
journal = "Chest",
issn = "0012-3692",
publisher = "American College of Chest Physicians",
number = "2",

}

TY - JOUR

T1 - Phenotypic Clusters Predict Outcomes in a Longitudinal Interstitial Lung Disease Cohort

AU - Adegunsoye, Ayodeji

AU - Oldham, Justin

AU - Chung, Jonathan H.

AU - Montner, Steven M.

AU - Lee, Cathryn

AU - Witt, Leah J.

AU - Stahlbaum, Danielle

AU - Bermea, Rene S.

AU - Chen, Lena W.

AU - Hsu, Scully

AU - Husain, Aliya N.

AU - Noth, Imre

AU - Vij, Rekha

AU - Strek, Mary E.

AU - Churpek, Matthew

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Background: The current interstitial lung disease (ILD) classification has overlapping clinical presentations and outcomes. Cluster analysis modeling is a valuable tool in identifying distinct clinical phenotypes in heterogeneous diseases. However, this approach has yet to be implemented in ILD. Methods: Using cluster analysis, novel ILD phenotypes were identified among subjects from a longitudinal ILD cohort, and outcomes were stratified according to phenotypic clusters compared with subgroups according to current American Thoracic Society/European Respiratory Society ILD classification criteria. Results: Among subjects with complete data for baseline variables (N = 770), four clusters were identified. Cluster 1 (ie, younger white obese female subjects) had the highest baseline FVC and diffusion capacity of the lung for carbon monoxide (DLCO). Cluster 2 (ie, younger African-American female subjects with elevated antinuclear antibody titers) had the lowest baseline FVC. Cluster 3 (ie, elderly white male smokers with coexistent emphysema) had intermediate FVC and DLCO. Cluster 4 (ie, elderly white male smokers with severe honeycombing) had the lowest baseline DLCO. Compared with classification according to ILD subgroup, stratification according to phenotypic clusters was associated with significant differences in monthly FVC decline (Cluster 4, –0.30% vs Cluster 2, 0.01%; P <.0001). Stratification by using clusters also independently predicted progression-free survival (P <.001) and transplant-free survival (P <.001). Conclusions: Among adults with diverse chronic ILDs, cluster analysis using baseline characteristics identified four distinct clinical phenotypes that might better predict meaningful clinical outcomes than current ILD diagnostic criteria.

AB - Background: The current interstitial lung disease (ILD) classification has overlapping clinical presentations and outcomes. Cluster analysis modeling is a valuable tool in identifying distinct clinical phenotypes in heterogeneous diseases. However, this approach has yet to be implemented in ILD. Methods: Using cluster analysis, novel ILD phenotypes were identified among subjects from a longitudinal ILD cohort, and outcomes were stratified according to phenotypic clusters compared with subgroups according to current American Thoracic Society/European Respiratory Society ILD classification criteria. Results: Among subjects with complete data for baseline variables (N = 770), four clusters were identified. Cluster 1 (ie, younger white obese female subjects) had the highest baseline FVC and diffusion capacity of the lung for carbon monoxide (DLCO). Cluster 2 (ie, younger African-American female subjects with elevated antinuclear antibody titers) had the lowest baseline FVC. Cluster 3 (ie, elderly white male smokers with coexistent emphysema) had intermediate FVC and DLCO. Cluster 4 (ie, elderly white male smokers with severe honeycombing) had the lowest baseline DLCO. Compared with classification according to ILD subgroup, stratification according to phenotypic clusters was associated with significant differences in monthly FVC decline (Cluster 4, –0.30% vs Cluster 2, 0.01%; P <.0001). Stratification by using clusters also independently predicted progression-free survival (P <.001) and transplant-free survival (P <.001). Conclusions: Among adults with diverse chronic ILDs, cluster analysis using baseline characteristics identified four distinct clinical phenotypes that might better predict meaningful clinical outcomes than current ILD diagnostic criteria.

KW - cluster

KW - interstitial lung disease

KW - mortality

KW - phenotype

KW - pulmonary fibrosis

UR - http://www.scopus.com/inward/record.url?scp=85041910988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041910988&partnerID=8YFLogxK

U2 - 10.1016/j.chest.2017.09.026

DO - 10.1016/j.chest.2017.09.026

M3 - Article

C2 - 28964798

AN - SCOPUS:85041910988

VL - 153

SP - 339

EP - 348

JO - Chest

JF - Chest

SN - 0012-3692

IS - 2

ER -