Abstract
An important problem in realizing personalized medicine is the development of methods for identifying disease subtypes using quantitative proteomics. Recently we found that bronchoalveolar lavage (BAL) cytokine patterns contain information about dynamic lung responsiveness. In this study, we examined physiological data from 1,048 subjects enrolled in the US Severe Asthma Research Program (SARP) to identify four largely separable, quantitative intermediate phenotypes. Upper extremes in the study population were identified for eosinophil- or neutrophil-predominant inflammation, bronchodilation in response to albuterol treatment, or methacholine sensitivity. We evaluated four different statistical (" machine" ) learning methods to predict each intermediate phenotype using BAL -cytokine measurements on a 76 subject subset. Comparison of these models using area under the ROC curve and overall classification accuracy indicated that logistic regression and multivariate adaptive regression splines produced the most accurate methods to predict intermediate asthma phenotypes. These robust classification methods will aid future translational studies in asthma targeted at specific intermediate phenotypes.
Original language | English (US) |
---|---|
Pages (from-to) | 147-157 |
Number of pages | 11 |
Journal | Clinical and Translational Science |
Volume | 3 |
Issue number | 4 |
DOIs | |
State | Published - Aug 2010 |
Fingerprint
Keywords
- Asthma
- Logistic regression
- Multivariate regression splines
- Personalized medicine
- Quantitative phenotypes
ASJC Scopus subject areas
- Medicine(all)
- Biochemistry, Genetics and Molecular Biology(all)
- Neuroscience(all)
- Pharmacology, Toxicology and Pharmaceutics(all)
Cite this
Predicting intermediate phenotypes in asthma using bronchoalveolar lavage-derived cytokines. / Brasier, Allan R.; Victor, Sundar; Ju, Hyunsu; Busse, William W.; Curran-Everett, Douglas; Bleecker, Eugene; Castro, Mario; Chung, Kian Fan; Gaston, Benjamin; Israel, Elliot; Wenzel, Sally E.; Erzurum, Serpil C.; Jarjour, Nizar N.; Calhoun, William.
In: Clinical and Translational Science, Vol. 3, No. 4, 08.2010, p. 147-157.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Predicting intermediate phenotypes in asthma using bronchoalveolar lavage-derived cytokines
AU - Brasier, Allan R.
AU - Victor, Sundar
AU - Ju, Hyunsu
AU - Busse, William W.
AU - Curran-Everett, Douglas
AU - Bleecker, Eugene
AU - Castro, Mario
AU - Chung, Kian Fan
AU - Gaston, Benjamin
AU - Israel, Elliot
AU - Wenzel, Sally E.
AU - Erzurum, Serpil C.
AU - Jarjour, Nizar N.
AU - Calhoun, William
PY - 2010/8
Y1 - 2010/8
N2 - An important problem in realizing personalized medicine is the development of methods for identifying disease subtypes using quantitative proteomics. Recently we found that bronchoalveolar lavage (BAL) cytokine patterns contain information about dynamic lung responsiveness. In this study, we examined physiological data from 1,048 subjects enrolled in the US Severe Asthma Research Program (SARP) to identify four largely separable, quantitative intermediate phenotypes. Upper extremes in the study population were identified for eosinophil- or neutrophil-predominant inflammation, bronchodilation in response to albuterol treatment, or methacholine sensitivity. We evaluated four different statistical (" machine" ) learning methods to predict each intermediate phenotype using BAL -cytokine measurements on a 76 subject subset. Comparison of these models using area under the ROC curve and overall classification accuracy indicated that logistic regression and multivariate adaptive regression splines produced the most accurate methods to predict intermediate asthma phenotypes. These robust classification methods will aid future translational studies in asthma targeted at specific intermediate phenotypes.
AB - An important problem in realizing personalized medicine is the development of methods for identifying disease subtypes using quantitative proteomics. Recently we found that bronchoalveolar lavage (BAL) cytokine patterns contain information about dynamic lung responsiveness. In this study, we examined physiological data from 1,048 subjects enrolled in the US Severe Asthma Research Program (SARP) to identify four largely separable, quantitative intermediate phenotypes. Upper extremes in the study population were identified for eosinophil- or neutrophil-predominant inflammation, bronchodilation in response to albuterol treatment, or methacholine sensitivity. We evaluated four different statistical (" machine" ) learning methods to predict each intermediate phenotype using BAL -cytokine measurements on a 76 subject subset. Comparison of these models using area under the ROC curve and overall classification accuracy indicated that logistic regression and multivariate adaptive regression splines produced the most accurate methods to predict intermediate asthma phenotypes. These robust classification methods will aid future translational studies in asthma targeted at specific intermediate phenotypes.
KW - Asthma
KW - Logistic regression
KW - Multivariate regression splines
KW - Personalized medicine
KW - Quantitative phenotypes
UR - http://www.scopus.com/inward/record.url?scp=77955759104&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77955759104&partnerID=8YFLogxK
U2 - 10.1111/j.1752-8062.2010.00204.x
DO - 10.1111/j.1752-8062.2010.00204.x
M3 - Article
C2 - 20718815
AN - SCOPUS:77955759104
VL - 3
SP - 147
EP - 157
JO - Clinical and Translational Science
JF - Clinical and Translational Science
SN - 1752-8054
IS - 4
ER -