Validation of a multiprotein plasma classifier to identify benign lung nodules

Anil Vachani, Harvey I. Pass, William N. Rom, David Eric Midthun, Eric Edell, Michel Laviolette, Xiao Jun Li, Pui Yee Fong, Stephen W. Hunsucker, Clive Hayward, Peter J. Mazzone, David K. Madtes, York E. Miller, Michael G. Walker, Jing Shi, Paul Kearney, Kenneth C. Fang, Pierre P. Massion

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Introduction: Indeterminate pulmonary nodules (IPNs) lack clinical or radiographic features of benign etiologies and often undergo invasive procedures unnecessarily, suggesting potential roles for diagnostic adjuncts using molecular biomarkers. The primary objective was to validate a multivariate classifier that identifies likely benign lung nodules by assaying plasma protein expression levels, yielding a range of probability estimates based on high negative predictive values (NPVs) for patients with 8 to 30 mm IPNs. Methods: A retrospective, multicenter, case-control study was performed using multiple reaction monitoring mass spectrometry, a classifier comprising five diagnostic and six normalization proteins, and blinded analysis of an independent validation set of plasma samples. Results: The classifier achieved validation on 141 lung nodule-associated plasma samples based on predefined statistical goals to optimize sensitivity. Using a population based nonsmall-cell lung cancer prevalence estimate of 23% for 8 to 30 mm IPNs, the classifier identified likely benign lung nodules with 90% negative predictive value and 26% positive predictive value, as shown in our prior work, at 92% sensitivity and 20% specificity, with the lower bound of the classifier's performance at 70% sensitivity and 48% specificity. Classifier scores for the overall cohort were statistically independent of patient age, tobacco use, nodule size, and chronic obstructive pulmonary disease diagnosis. The classifier also demonstrated incremental diagnostic performance in combination with a four-parameter clinical model. Conclusions: This proteomic classifier provides a range of probability estimates for the likelihood of a benign etiology that may serve as a noninvasive, diagnostic adjunct for clinical assessments of patients with IPNs.

Original languageEnglish (US)
Pages (from-to)629-637
Number of pages9
JournalJournal of Thoracic Oncology
Volume10
Issue number4
DOIs
StatePublished - Apr 30 2015

Fingerprint

Lung
Sensitivity and Specificity
Tobacco Use
Non-Small Cell Lung Carcinoma
Proteomics
Chronic Obstructive Pulmonary Disease
Case-Control Studies
Blood Proteins
Mass Spectrometry
Biomarkers
Population
Proteins

Keywords

  • Biomarker
  • Lung nodule
  • Molecular diagnostic
  • Proteomics

ASJC Scopus subject areas

  • Oncology
  • Pulmonary and Respiratory Medicine

Cite this

Validation of a multiprotein plasma classifier to identify benign lung nodules. / Vachani, Anil; Pass, Harvey I.; Rom, William N.; Midthun, David Eric; Edell, Eric; Laviolette, Michel; Li, Xiao Jun; Fong, Pui Yee; Hunsucker, Stephen W.; Hayward, Clive; Mazzone, Peter J.; Madtes, David K.; Miller, York E.; Walker, Michael G.; Shi, Jing; Kearney, Paul; Fang, Kenneth C.; Massion, Pierre P.

In: Journal of Thoracic Oncology, Vol. 10, No. 4, 30.04.2015, p. 629-637.

Research output: Contribution to journalArticle

Vachani, A, Pass, HI, Rom, WN, Midthun, DE, Edell, E, Laviolette, M, Li, XJ, Fong, PY, Hunsucker, SW, Hayward, C, Mazzone, PJ, Madtes, DK, Miller, YE, Walker, MG, Shi, J, Kearney, P, Fang, KC & Massion, PP 2015, 'Validation of a multiprotein plasma classifier to identify benign lung nodules', Journal of Thoracic Oncology, vol. 10, no. 4, pp. 629-637. https://doi.org/10.1097/JTO.0000000000000447
Vachani, Anil ; Pass, Harvey I. ; Rom, William N. ; Midthun, David Eric ; Edell, Eric ; Laviolette, Michel ; Li, Xiao Jun ; Fong, Pui Yee ; Hunsucker, Stephen W. ; Hayward, Clive ; Mazzone, Peter J. ; Madtes, David K. ; Miller, York E. ; Walker, Michael G. ; Shi, Jing ; Kearney, Paul ; Fang, Kenneth C. ; Massion, Pierre P. / Validation of a multiprotein plasma classifier to identify benign lung nodules. In: Journal of Thoracic Oncology. 2015 ; Vol. 10, No. 4. pp. 629-637.
@article{a1c05854062340f29ceb55c9097f5ce7,
title = "Validation of a multiprotein plasma classifier to identify benign lung nodules",
abstract = "Introduction: Indeterminate pulmonary nodules (IPNs) lack clinical or radiographic features of benign etiologies and often undergo invasive procedures unnecessarily, suggesting potential roles for diagnostic adjuncts using molecular biomarkers. The primary objective was to validate a multivariate classifier that identifies likely benign lung nodules by assaying plasma protein expression levels, yielding a range of probability estimates based on high negative predictive values (NPVs) for patients with 8 to 30 mm IPNs. Methods: A retrospective, multicenter, case-control study was performed using multiple reaction monitoring mass spectrometry, a classifier comprising five diagnostic and six normalization proteins, and blinded analysis of an independent validation set of plasma samples. Results: The classifier achieved validation on 141 lung nodule-associated plasma samples based on predefined statistical goals to optimize sensitivity. Using a population based nonsmall-cell lung cancer prevalence estimate of 23{\%} for 8 to 30 mm IPNs, the classifier identified likely benign lung nodules with 90{\%} negative predictive value and 26{\%} positive predictive value, as shown in our prior work, at 92{\%} sensitivity and 20{\%} specificity, with the lower bound of the classifier's performance at 70{\%} sensitivity and 48{\%} specificity. Classifier scores for the overall cohort were statistically independent of patient age, tobacco use, nodule size, and chronic obstructive pulmonary disease diagnosis. The classifier also demonstrated incremental diagnostic performance in combination with a four-parameter clinical model. Conclusions: This proteomic classifier provides a range of probability estimates for the likelihood of a benign etiology that may serve as a noninvasive, diagnostic adjunct for clinical assessments of patients with IPNs.",
keywords = "Biomarker, Lung nodule, Molecular diagnostic, Proteomics",
author = "Anil Vachani and Pass, {Harvey I.} and Rom, {William N.} and Midthun, {David Eric} and Eric Edell and Michel Laviolette and Li, {Xiao Jun} and Fong, {Pui Yee} and Hunsucker, {Stephen W.} and Clive Hayward and Mazzone, {Peter J.} and Madtes, {David K.} and Miller, {York E.} and Walker, {Michael G.} and Jing Shi and Paul Kearney and Fang, {Kenneth C.} and Massion, {Pierre P.}",
year = "2015",
month = "4",
day = "30",
doi = "10.1097/JTO.0000000000000447",
language = "English (US)",
volume = "10",
pages = "629--637",
journal = "Journal of Thoracic Oncology",
issn = "1556-0864",
publisher = "International Association for the Study of Lung Cancer",
number = "4",

}

TY - JOUR

T1 - Validation of a multiprotein plasma classifier to identify benign lung nodules

AU - Vachani, Anil

AU - Pass, Harvey I.

AU - Rom, William N.

AU - Midthun, David Eric

AU - Edell, Eric

AU - Laviolette, Michel

AU - Li, Xiao Jun

AU - Fong, Pui Yee

AU - Hunsucker, Stephen W.

AU - Hayward, Clive

AU - Mazzone, Peter J.

AU - Madtes, David K.

AU - Miller, York E.

AU - Walker, Michael G.

AU - Shi, Jing

AU - Kearney, Paul

AU - Fang, Kenneth C.

AU - Massion, Pierre P.

PY - 2015/4/30

Y1 - 2015/4/30

N2 - Introduction: Indeterminate pulmonary nodules (IPNs) lack clinical or radiographic features of benign etiologies and often undergo invasive procedures unnecessarily, suggesting potential roles for diagnostic adjuncts using molecular biomarkers. The primary objective was to validate a multivariate classifier that identifies likely benign lung nodules by assaying plasma protein expression levels, yielding a range of probability estimates based on high negative predictive values (NPVs) for patients with 8 to 30 mm IPNs. Methods: A retrospective, multicenter, case-control study was performed using multiple reaction monitoring mass spectrometry, a classifier comprising five diagnostic and six normalization proteins, and blinded analysis of an independent validation set of plasma samples. Results: The classifier achieved validation on 141 lung nodule-associated plasma samples based on predefined statistical goals to optimize sensitivity. Using a population based nonsmall-cell lung cancer prevalence estimate of 23% for 8 to 30 mm IPNs, the classifier identified likely benign lung nodules with 90% negative predictive value and 26% positive predictive value, as shown in our prior work, at 92% sensitivity and 20% specificity, with the lower bound of the classifier's performance at 70% sensitivity and 48% specificity. Classifier scores for the overall cohort were statistically independent of patient age, tobacco use, nodule size, and chronic obstructive pulmonary disease diagnosis. The classifier also demonstrated incremental diagnostic performance in combination with a four-parameter clinical model. Conclusions: This proteomic classifier provides a range of probability estimates for the likelihood of a benign etiology that may serve as a noninvasive, diagnostic adjunct for clinical assessments of patients with IPNs.

AB - Introduction: Indeterminate pulmonary nodules (IPNs) lack clinical or radiographic features of benign etiologies and often undergo invasive procedures unnecessarily, suggesting potential roles for diagnostic adjuncts using molecular biomarkers. The primary objective was to validate a multivariate classifier that identifies likely benign lung nodules by assaying plasma protein expression levels, yielding a range of probability estimates based on high negative predictive values (NPVs) for patients with 8 to 30 mm IPNs. Methods: A retrospective, multicenter, case-control study was performed using multiple reaction monitoring mass spectrometry, a classifier comprising five diagnostic and six normalization proteins, and blinded analysis of an independent validation set of plasma samples. Results: The classifier achieved validation on 141 lung nodule-associated plasma samples based on predefined statistical goals to optimize sensitivity. Using a population based nonsmall-cell lung cancer prevalence estimate of 23% for 8 to 30 mm IPNs, the classifier identified likely benign lung nodules with 90% negative predictive value and 26% positive predictive value, as shown in our prior work, at 92% sensitivity and 20% specificity, with the lower bound of the classifier's performance at 70% sensitivity and 48% specificity. Classifier scores for the overall cohort were statistically independent of patient age, tobacco use, nodule size, and chronic obstructive pulmonary disease diagnosis. The classifier also demonstrated incremental diagnostic performance in combination with a four-parameter clinical model. Conclusions: This proteomic classifier provides a range of probability estimates for the likelihood of a benign etiology that may serve as a noninvasive, diagnostic adjunct for clinical assessments of patients with IPNs.

KW - Biomarker

KW - Lung nodule

KW - Molecular diagnostic

KW - Proteomics

UR - http://www.scopus.com/inward/record.url?scp=84938288264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938288264&partnerID=8YFLogxK

U2 - 10.1097/JTO.0000000000000447

DO - 10.1097/JTO.0000000000000447

M3 - Article

VL - 10

SP - 629

EP - 637

JO - Journal of Thoracic Oncology

JF - Journal of Thoracic Oncology

SN - 1556-0864

IS - 4

ER -