Blood transcriptional biomarkers for active tuberculosis among patients in the United States: A case-control study with systematic cross-classifier evaluation

Nicholas D. Walter, Mikaela A. Miller, Joshua Vasquez, Marc H Weiner, Adam Chapman, Melissa Engle, Michael Higgins, Amy M. Quinones, Vanessa Rosselli, Elizabeth Canono, Christina Yoon, Adithya Cattamanchi, J. Lucian Davis, Tzu Phang, Robert S. Stearman, Gargi Datta, Benjamin J. Garcia, Charles L. Daley, Michael Strong, Katerina KechrisTasha E. Fingerlin, Randall Reves, Mark W. Geraci

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Blood transcriptional signatures are promising for tuberculosis (TB) diagnosis but have not been evaluated among U.S. patients. To be used clinically, transcriptional classifiers need reproducible accuracy in diverse populations that vary in genetic composition, disease spectrum and severity, and comorbidities. In a prospective case-control study, we identified novel transcriptional classifiers for active TB among U.S. patients and systematically compared their accuracy to classifiers from published studies. Blood samples from HIV-uninfected U.S. adults with active TB, pneumonia, or latent TB infection underwent whole-Transcriptome microarray. We used support vector machines to classify disease state based on transcriptional patterns. We externally validated our classifiers using data from sub-Saharan African cohorts and evaluated previously published transcriptional classifiers in our population. Our classifier distinguishing active TB from pneumonia had an area under the concentration-Time curve (AUC) of 96.5% (95.4% to 97.6%) among U.S. patients, but the AUC was lower (90.6% [89.6% to 91.7%]) in HIV-uninfected Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 90.0% (87.7% to 92.3%) and 82.9% (80.8% to 85.1%) when tested in U.S. patients. Our classifier distinguishing active TB from latent TB had AUC values of 95.9% (95.2% to 96.6%) among U.S. patients and 95.3% (94.7% to 96.0%) among Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 98.0% (97.4% to 98.7%) and 94.8% (92.9% to 96.8%) when tested in U.S. patients. Blood transcriptional classifiers accurately detected active TB among U.S. adults. The accuracy of classifiers for active TB versus that of other diseases decreased when tested in new populations with different disease controls, suggesting additional studies are required to enhance generalizability. Classifiers that distinguish active TB from latent TB are accurate and generalizable across populations and can be explored as screening assays.

Original languageEnglish (US)
Pages (from-to)274-282
Number of pages9
JournalJournal of Clinical Microbiology
Volume54
Issue number2
DOIs
StatePublished - Feb 1 2016
Externally publishedYes

Fingerprint

Case-Control Studies
Tuberculosis
Biomarkers
Latent Tuberculosis
Population
Pneumonia
HIV
Inborn Genetic Diseases
Transcriptome
Comorbidity

ASJC Scopus subject areas

  • Microbiology (medical)

Cite this

Blood transcriptional biomarkers for active tuberculosis among patients in the United States : A case-control study with systematic cross-classifier evaluation. / Walter, Nicholas D.; Miller, Mikaela A.; Vasquez, Joshua; Weiner, Marc H; Chapman, Adam; Engle, Melissa; Higgins, Michael; Quinones, Amy M.; Rosselli, Vanessa; Canono, Elizabeth; Yoon, Christina; Cattamanchi, Adithya; Lucian Davis, J.; Phang, Tzu; Stearman, Robert S.; Datta, Gargi; Garcia, Benjamin J.; Daley, Charles L.; Strong, Michael; Kechris, Katerina; Fingerlin, Tasha E.; Reves, Randall; Geraci, Mark W.

In: Journal of Clinical Microbiology, Vol. 54, No. 2, 01.02.2016, p. 274-282.

Research output: Contribution to journalArticle

Walter, ND, Miller, MA, Vasquez, J, Weiner, MH, Chapman, A, Engle, M, Higgins, M, Quinones, AM, Rosselli, V, Canono, E, Yoon, C, Cattamanchi, A, Lucian Davis, J, Phang, T, Stearman, RS, Datta, G, Garcia, BJ, Daley, CL, Strong, M, Kechris, K, Fingerlin, TE, Reves, R & Geraci, MW 2016, 'Blood transcriptional biomarkers for active tuberculosis among patients in the United States: A case-control study with systematic cross-classifier evaluation', Journal of Clinical Microbiology, vol. 54, no. 2, pp. 274-282. https://doi.org/10.1128/JCM.01990-15
Walter, Nicholas D. ; Miller, Mikaela A. ; Vasquez, Joshua ; Weiner, Marc H ; Chapman, Adam ; Engle, Melissa ; Higgins, Michael ; Quinones, Amy M. ; Rosselli, Vanessa ; Canono, Elizabeth ; Yoon, Christina ; Cattamanchi, Adithya ; Lucian Davis, J. ; Phang, Tzu ; Stearman, Robert S. ; Datta, Gargi ; Garcia, Benjamin J. ; Daley, Charles L. ; Strong, Michael ; Kechris, Katerina ; Fingerlin, Tasha E. ; Reves, Randall ; Geraci, Mark W. / Blood transcriptional biomarkers for active tuberculosis among patients in the United States : A case-control study with systematic cross-classifier evaluation. In: Journal of Clinical Microbiology. 2016 ; Vol. 54, No. 2. pp. 274-282.
@article{265bbdfc7b73444f9b41f0a99c16a022,
title = "Blood transcriptional biomarkers for active tuberculosis among patients in the United States: A case-control study with systematic cross-classifier evaluation",
abstract = "Blood transcriptional signatures are promising for tuberculosis (TB) diagnosis but have not been evaluated among U.S. patients. To be used clinically, transcriptional classifiers need reproducible accuracy in diverse populations that vary in genetic composition, disease spectrum and severity, and comorbidities. In a prospective case-control study, we identified novel transcriptional classifiers for active TB among U.S. patients and systematically compared their accuracy to classifiers from published studies. Blood samples from HIV-uninfected U.S. adults with active TB, pneumonia, or latent TB infection underwent whole-Transcriptome microarray. We used support vector machines to classify disease state based on transcriptional patterns. We externally validated our classifiers using data from sub-Saharan African cohorts and evaluated previously published transcriptional classifiers in our population. Our classifier distinguishing active TB from pneumonia had an area under the concentration-Time curve (AUC) of 96.5{\%} (95.4{\%} to 97.6{\%}) among U.S. patients, but the AUC was lower (90.6{\%} [89.6{\%} to 91.7{\%}]) in HIV-uninfected Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 90.0{\%} (87.7{\%} to 92.3{\%}) and 82.9{\%} (80.8{\%} to 85.1{\%}) when tested in U.S. patients. Our classifier distinguishing active TB from latent TB had AUC values of 95.9{\%} (95.2{\%} to 96.6{\%}) among U.S. patients and 95.3{\%} (94.7{\%} to 96.0{\%}) among Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 98.0{\%} (97.4{\%} to 98.7{\%}) and 94.8{\%} (92.9{\%} to 96.8{\%}) when tested in U.S. patients. Blood transcriptional classifiers accurately detected active TB among U.S. adults. The accuracy of classifiers for active TB versus that of other diseases decreased when tested in new populations with different disease controls, suggesting additional studies are required to enhance generalizability. Classifiers that distinguish active TB from latent TB are accurate and generalizable across populations and can be explored as screening assays.",
author = "Walter, {Nicholas D.} and Miller, {Mikaela A.} and Joshua Vasquez and Weiner, {Marc H} and Adam Chapman and Melissa Engle and Michael Higgins and Quinones, {Amy M.} and Vanessa Rosselli and Elizabeth Canono and Christina Yoon and Adithya Cattamanchi and {Lucian Davis}, J. and Tzu Phang and Stearman, {Robert S.} and Gargi Datta and Garcia, {Benjamin J.} and Daley, {Charles L.} and Michael Strong and Katerina Kechris and Fingerlin, {Tasha E.} and Randall Reves and Geraci, {Mark W.}",
year = "2016",
month = "2",
day = "1",
doi = "10.1128/JCM.01990-15",
language = "English (US)",
volume = "54",
pages = "274--282",
journal = "Journal of Clinical Microbiology",
issn = "0095-1137",
publisher = "American Society for Microbiology",
number = "2",

}

TY - JOUR

T1 - Blood transcriptional biomarkers for active tuberculosis among patients in the United States

T2 - A case-control study with systematic cross-classifier evaluation

AU - Walter, Nicholas D.

AU - Miller, Mikaela A.

AU - Vasquez, Joshua

AU - Weiner, Marc H

AU - Chapman, Adam

AU - Engle, Melissa

AU - Higgins, Michael

AU - Quinones, Amy M.

AU - Rosselli, Vanessa

AU - Canono, Elizabeth

AU - Yoon, Christina

AU - Cattamanchi, Adithya

AU - Lucian Davis, J.

AU - Phang, Tzu

AU - Stearman, Robert S.

AU - Datta, Gargi

AU - Garcia, Benjamin J.

AU - Daley, Charles L.

AU - Strong, Michael

AU - Kechris, Katerina

AU - Fingerlin, Tasha E.

AU - Reves, Randall

AU - Geraci, Mark W.

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Blood transcriptional signatures are promising for tuberculosis (TB) diagnosis but have not been evaluated among U.S. patients. To be used clinically, transcriptional classifiers need reproducible accuracy in diverse populations that vary in genetic composition, disease spectrum and severity, and comorbidities. In a prospective case-control study, we identified novel transcriptional classifiers for active TB among U.S. patients and systematically compared their accuracy to classifiers from published studies. Blood samples from HIV-uninfected U.S. adults with active TB, pneumonia, or latent TB infection underwent whole-Transcriptome microarray. We used support vector machines to classify disease state based on transcriptional patterns. We externally validated our classifiers using data from sub-Saharan African cohorts and evaluated previously published transcriptional classifiers in our population. Our classifier distinguishing active TB from pneumonia had an area under the concentration-Time curve (AUC) of 96.5% (95.4% to 97.6%) among U.S. patients, but the AUC was lower (90.6% [89.6% to 91.7%]) in HIV-uninfected Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 90.0% (87.7% to 92.3%) and 82.9% (80.8% to 85.1%) when tested in U.S. patients. Our classifier distinguishing active TB from latent TB had AUC values of 95.9% (95.2% to 96.6%) among U.S. patients and 95.3% (94.7% to 96.0%) among Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 98.0% (97.4% to 98.7%) and 94.8% (92.9% to 96.8%) when tested in U.S. patients. Blood transcriptional classifiers accurately detected active TB among U.S. adults. The accuracy of classifiers for active TB versus that of other diseases decreased when tested in new populations with different disease controls, suggesting additional studies are required to enhance generalizability. Classifiers that distinguish active TB from latent TB are accurate and generalizable across populations and can be explored as screening assays.

AB - Blood transcriptional signatures are promising for tuberculosis (TB) diagnosis but have not been evaluated among U.S. patients. To be used clinically, transcriptional classifiers need reproducible accuracy in diverse populations that vary in genetic composition, disease spectrum and severity, and comorbidities. In a prospective case-control study, we identified novel transcriptional classifiers for active TB among U.S. patients and systematically compared their accuracy to classifiers from published studies. Blood samples from HIV-uninfected U.S. adults with active TB, pneumonia, or latent TB infection underwent whole-Transcriptome microarray. We used support vector machines to classify disease state based on transcriptional patterns. We externally validated our classifiers using data from sub-Saharan African cohorts and evaluated previously published transcriptional classifiers in our population. Our classifier distinguishing active TB from pneumonia had an area under the concentration-Time curve (AUC) of 96.5% (95.4% to 97.6%) among U.S. patients, but the AUC was lower (90.6% [89.6% to 91.7%]) in HIV-uninfected Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 90.0% (87.7% to 92.3%) and 82.9% (80.8% to 85.1%) when tested in U.S. patients. Our classifier distinguishing active TB from latent TB had AUC values of 95.9% (95.2% to 96.6%) among U.S. patients and 95.3% (94.7% to 96.0%) among Sub-Saharan Africans. Previously published comparable classifiers had AUC values of 98.0% (97.4% to 98.7%) and 94.8% (92.9% to 96.8%) when tested in U.S. patients. Blood transcriptional classifiers accurately detected active TB among U.S. adults. The accuracy of classifiers for active TB versus that of other diseases decreased when tested in new populations with different disease controls, suggesting additional studies are required to enhance generalizability. Classifiers that distinguish active TB from latent TB are accurate and generalizable across populations and can be explored as screening assays.

UR - http://www.scopus.com/inward/record.url?scp=84956687135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956687135&partnerID=8YFLogxK

U2 - 10.1128/JCM.01990-15

DO - 10.1128/JCM.01990-15

M3 - Article

C2 - 26582831

AN - SCOPUS:84956687135

VL - 54

SP - 274

EP - 282

JO - Journal of Clinical Microbiology

JF - Journal of Clinical Microbiology

SN - 0095-1137

IS - 2

ER -