Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples: a prospective validation study

Ganesh Raghu, Kevin R. Flaherty, David J. Lederer, David A. Lynch, Thomas V. Colby, Jeffrey L. Myers, Steve D. Groshong, Brandon Larsen, Jonathan H. Chung, Mark P. Steele, Sadia Benzaquen, Karel Calero, Amy H. Case, Gerard J. Criner, Steven D. Nathan, Navdeep S. Rai, Murali Ramaswamy, Lars Hagmeyer, J. Russell Davis, Umair A. GauharDaniel G. Pankratz, Yoonha Choi, Jing Huang, P. Sean Walsh, Hannah Neville, Lori R. Lofaro, Neil M. Barth, Giulia C. Kennedy, Kevin K. Brown, Fernando J. Martinez

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Background: In the appropriate clinical setting, the diagnosis of idiopathic pulmonary fibrosis (IPF)requires a pattern of usual interstitial pneumonia to be present on high-resolution chest CT (HRCT)or surgical lung biopsy. A molecular usual interstitial pneumonia signature can be identified by a machine learning algorithm in less-invasive transbronchial lung biopsy samples. We report prospective findings for the clinical validity and utility of this molecular test. Methods: We prospectively recruited 237 patients for this study from those enrolled in the Bronchial Sample Collection for a Novel Genomic Test (BRAVE)study in 29 US and European sites. Patients were undergoing evaluation for interstitial lung disease and had had samples obtained by clinically indicated surgical or transbronchial biopsy or cryobiopsy for pathology. Histopathological diagnoses were made by experienced pathologists. Available HRCT scans were reviewed centrally. Three to five transbronchial lung biopsy samples were collected from all patients specifically for this study, pooled by patient, and extracted for transcriptomic sequencing. After exclusions, diagnostic histopathology and RNA sequence data from 90 patients were used to train a machine learning algorithm (Envisia Genomic Classifier, Veracyte, San Francisco, CA, USA)to identify a usual interstitial pneumonia pattern. The primary study endpoint was validation of the classifier in 49 patients by comparison with diagnostic histopathology. To assess clinical utility, we compared the agreement and confidence level of diagnosis made by central multidisciplinary teams based on anonymised clinical information and radiology results plus either molecular classifier or histopathology results. Findings: The classifier identified usual interstitial pneumonia in transbronchial lung biopsy samples from 49 patients with 88% specificity (95% CI 70–98)and 70% sensitivity (47–87). Among 42 of these patients who had possible or inconsistent usual interstitial pneumonia on HRCT, the classifier showed 81% positive predictive value (95% CI 54–96)for underlying biopsy-proven usual interstitial pneumonia. In the clinical utility analysis, we found 86% agreement (95% CI 78–92)between clinical diagnoses using classifier results and those using histopathology data. Diagnostic confidence was improved by the molecular classifier results compared with histopathology results in 18 with IPF diagnoses (proportion of diagnoses that were confident or provisional with high confidence 89% vs 56%, p=0·0339)and in all 48 patients with non-diagnostic pathology or non-classifiable fibrosis histopathology (63% vs 42%, p=0·0412). Interpretation: The molecular test provided an objective method to aid clinicians and multidisciplinary teams in ascertaining a diagnosis of IPF, particularly for patients without a clear radiological diagnosis, in samples that can be obtained by a less invasive method. Further prospective clinical validation and utility studies are planned. Funding: Veracyte.

Original languageEnglish (US)
Pages (from-to)487-496
Number of pages10
JournalThe Lancet Respiratory Medicine
Volume7
Issue number6
DOIs
StatePublished - Jun 1 2019

Fingerprint

Idiopathic Pulmonary Fibrosis
Validation Studies
Prospective Studies
Biopsy
Lung
Thorax
Pathology
San Francisco
Interstitial Lung Diseases
Radiology
Fibrosis

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine

Cite this

Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples : a prospective validation study. / Raghu, Ganesh; Flaherty, Kevin R.; Lederer, David J.; Lynch, David A.; Colby, Thomas V.; Myers, Jeffrey L.; Groshong, Steve D.; Larsen, Brandon; Chung, Jonathan H.; Steele, Mark P.; Benzaquen, Sadia; Calero, Karel; Case, Amy H.; Criner, Gerard J.; Nathan, Steven D.; Rai, Navdeep S.; Ramaswamy, Murali; Hagmeyer, Lars; Davis, J. Russell; Gauhar, Umair A.; Pankratz, Daniel G.; Choi, Yoonha; Huang, Jing; Walsh, P. Sean; Neville, Hannah; Lofaro, Lori R.; Barth, Neil M.; Kennedy, Giulia C.; Brown, Kevin K.; Martinez, Fernando J.

In: The Lancet Respiratory Medicine, Vol. 7, No. 6, 01.06.2019, p. 487-496.

Research output: Contribution to journalArticle

Raghu, G, Flaherty, KR, Lederer, DJ, Lynch, DA, Colby, TV, Myers, JL, Groshong, SD, Larsen, B, Chung, JH, Steele, MP, Benzaquen, S, Calero, K, Case, AH, Criner, GJ, Nathan, SD, Rai, NS, Ramaswamy, M, Hagmeyer, L, Davis, JR, Gauhar, UA, Pankratz, DG, Choi, Y, Huang, J, Walsh, PS, Neville, H, Lofaro, LR, Barth, NM, Kennedy, GC, Brown, KK & Martinez, FJ 2019, 'Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples: a prospective validation study', The Lancet Respiratory Medicine, vol. 7, no. 6, pp. 487-496. https://doi.org/10.1016/S2213-2600(19)30059-1
Raghu, Ganesh ; Flaherty, Kevin R. ; Lederer, David J. ; Lynch, David A. ; Colby, Thomas V. ; Myers, Jeffrey L. ; Groshong, Steve D. ; Larsen, Brandon ; Chung, Jonathan H. ; Steele, Mark P. ; Benzaquen, Sadia ; Calero, Karel ; Case, Amy H. ; Criner, Gerard J. ; Nathan, Steven D. ; Rai, Navdeep S. ; Ramaswamy, Murali ; Hagmeyer, Lars ; Davis, J. Russell ; Gauhar, Umair A. ; Pankratz, Daniel G. ; Choi, Yoonha ; Huang, Jing ; Walsh, P. Sean ; Neville, Hannah ; Lofaro, Lori R. ; Barth, Neil M. ; Kennedy, Giulia C. ; Brown, Kevin K. ; Martinez, Fernando J. / Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples : a prospective validation study. In: The Lancet Respiratory Medicine. 2019 ; Vol. 7, No. 6. pp. 487-496.
@article{45beb03f934d42b783cbfa42bfe0fb9c,
title = "Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples: a prospective validation study",
abstract = "Background: In the appropriate clinical setting, the diagnosis of idiopathic pulmonary fibrosis (IPF)requires a pattern of usual interstitial pneumonia to be present on high-resolution chest CT (HRCT)or surgical lung biopsy. A molecular usual interstitial pneumonia signature can be identified by a machine learning algorithm in less-invasive transbronchial lung biopsy samples. We report prospective findings for the clinical validity and utility of this molecular test. Methods: We prospectively recruited 237 patients for this study from those enrolled in the Bronchial Sample Collection for a Novel Genomic Test (BRAVE)study in 29 US and European sites. Patients were undergoing evaluation for interstitial lung disease and had had samples obtained by clinically indicated surgical or transbronchial biopsy or cryobiopsy for pathology. Histopathological diagnoses were made by experienced pathologists. Available HRCT scans were reviewed centrally. Three to five transbronchial lung biopsy samples were collected from all patients specifically for this study, pooled by patient, and extracted for transcriptomic sequencing. After exclusions, diagnostic histopathology and RNA sequence data from 90 patients were used to train a machine learning algorithm (Envisia Genomic Classifier, Veracyte, San Francisco, CA, USA)to identify a usual interstitial pneumonia pattern. The primary study endpoint was validation of the classifier in 49 patients by comparison with diagnostic histopathology. To assess clinical utility, we compared the agreement and confidence level of diagnosis made by central multidisciplinary teams based on anonymised clinical information and radiology results plus either molecular classifier or histopathology results. Findings: The classifier identified usual interstitial pneumonia in transbronchial lung biopsy samples from 49 patients with 88{\%} specificity (95{\%} CI 70–98)and 70{\%} sensitivity (47–87). Among 42 of these patients who had possible or inconsistent usual interstitial pneumonia on HRCT, the classifier showed 81{\%} positive predictive value (95{\%} CI 54–96)for underlying biopsy-proven usual interstitial pneumonia. In the clinical utility analysis, we found 86{\%} agreement (95{\%} CI 78–92)between clinical diagnoses using classifier results and those using histopathology data. Diagnostic confidence was improved by the molecular classifier results compared with histopathology results in 18 with IPF diagnoses (proportion of diagnoses that were confident or provisional with high confidence 89{\%} vs 56{\%}, p=0·0339)and in all 48 patients with non-diagnostic pathology or non-classifiable fibrosis histopathology (63{\%} vs 42{\%}, p=0·0412). Interpretation: The molecular test provided an objective method to aid clinicians and multidisciplinary teams in ascertaining a diagnosis of IPF, particularly for patients without a clear radiological diagnosis, in samples that can be obtained by a less invasive method. Further prospective clinical validation and utility studies are planned. Funding: Veracyte.",
author = "Ganesh Raghu and Flaherty, {Kevin R.} and Lederer, {David J.} and Lynch, {David A.} and Colby, {Thomas V.} and Myers, {Jeffrey L.} and Groshong, {Steve D.} and Brandon Larsen and Chung, {Jonathan H.} and Steele, {Mark P.} and Sadia Benzaquen and Karel Calero and Case, {Amy H.} and Criner, {Gerard J.} and Nathan, {Steven D.} and Rai, {Navdeep S.} and Murali Ramaswamy and Lars Hagmeyer and Davis, {J. Russell} and Gauhar, {Umair A.} and Pankratz, {Daniel G.} and Yoonha Choi and Jing Huang and Walsh, {P. Sean} and Hannah Neville and Lofaro, {Lori R.} and Barth, {Neil M.} and Kennedy, {Giulia C.} and Brown, {Kevin K.} and Martinez, {Fernando J.}",
year = "2019",
month = "6",
day = "1",
doi = "10.1016/S2213-2600(19)30059-1",
language = "English (US)",
volume = "7",
pages = "487--496",
journal = "The Lancet Respiratory Medicine",
issn = "2213-2600",
publisher = "Elsevier Limited",
number = "6",

}

TY - JOUR

T1 - Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples

T2 - a prospective validation study

AU - Raghu, Ganesh

AU - Flaherty, Kevin R.

AU - Lederer, David J.

AU - Lynch, David A.

AU - Colby, Thomas V.

AU - Myers, Jeffrey L.

AU - Groshong, Steve D.

AU - Larsen, Brandon

AU - Chung, Jonathan H.

AU - Steele, Mark P.

AU - Benzaquen, Sadia

AU - Calero, Karel

AU - Case, Amy H.

AU - Criner, Gerard J.

AU - Nathan, Steven D.

AU - Rai, Navdeep S.

AU - Ramaswamy, Murali

AU - Hagmeyer, Lars

AU - Davis, J. Russell

AU - Gauhar, Umair A.

AU - Pankratz, Daniel G.

AU - Choi, Yoonha

AU - Huang, Jing

AU - Walsh, P. Sean

AU - Neville, Hannah

AU - Lofaro, Lori R.

AU - Barth, Neil M.

AU - Kennedy, Giulia C.

AU - Brown, Kevin K.

AU - Martinez, Fernando J.

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Background: In the appropriate clinical setting, the diagnosis of idiopathic pulmonary fibrosis (IPF)requires a pattern of usual interstitial pneumonia to be present on high-resolution chest CT (HRCT)or surgical lung biopsy. A molecular usual interstitial pneumonia signature can be identified by a machine learning algorithm in less-invasive transbronchial lung biopsy samples. We report prospective findings for the clinical validity and utility of this molecular test. Methods: We prospectively recruited 237 patients for this study from those enrolled in the Bronchial Sample Collection for a Novel Genomic Test (BRAVE)study in 29 US and European sites. Patients were undergoing evaluation for interstitial lung disease and had had samples obtained by clinically indicated surgical or transbronchial biopsy or cryobiopsy for pathology. Histopathological diagnoses were made by experienced pathologists. Available HRCT scans were reviewed centrally. Three to five transbronchial lung biopsy samples were collected from all patients specifically for this study, pooled by patient, and extracted for transcriptomic sequencing. After exclusions, diagnostic histopathology and RNA sequence data from 90 patients were used to train a machine learning algorithm (Envisia Genomic Classifier, Veracyte, San Francisco, CA, USA)to identify a usual interstitial pneumonia pattern. The primary study endpoint was validation of the classifier in 49 patients by comparison with diagnostic histopathology. To assess clinical utility, we compared the agreement and confidence level of diagnosis made by central multidisciplinary teams based on anonymised clinical information and radiology results plus either molecular classifier or histopathology results. Findings: The classifier identified usual interstitial pneumonia in transbronchial lung biopsy samples from 49 patients with 88% specificity (95% CI 70–98)and 70% sensitivity (47–87). Among 42 of these patients who had possible or inconsistent usual interstitial pneumonia on HRCT, the classifier showed 81% positive predictive value (95% CI 54–96)for underlying biopsy-proven usual interstitial pneumonia. In the clinical utility analysis, we found 86% agreement (95% CI 78–92)between clinical diagnoses using classifier results and those using histopathology data. Diagnostic confidence was improved by the molecular classifier results compared with histopathology results in 18 with IPF diagnoses (proportion of diagnoses that were confident or provisional with high confidence 89% vs 56%, p=0·0339)and in all 48 patients with non-diagnostic pathology or non-classifiable fibrosis histopathology (63% vs 42%, p=0·0412). Interpretation: The molecular test provided an objective method to aid clinicians and multidisciplinary teams in ascertaining a diagnosis of IPF, particularly for patients without a clear radiological diagnosis, in samples that can be obtained by a less invasive method. Further prospective clinical validation and utility studies are planned. Funding: Veracyte.

AB - Background: In the appropriate clinical setting, the diagnosis of idiopathic pulmonary fibrosis (IPF)requires a pattern of usual interstitial pneumonia to be present on high-resolution chest CT (HRCT)or surgical lung biopsy. A molecular usual interstitial pneumonia signature can be identified by a machine learning algorithm in less-invasive transbronchial lung biopsy samples. We report prospective findings for the clinical validity and utility of this molecular test. Methods: We prospectively recruited 237 patients for this study from those enrolled in the Bronchial Sample Collection for a Novel Genomic Test (BRAVE)study in 29 US and European sites. Patients were undergoing evaluation for interstitial lung disease and had had samples obtained by clinically indicated surgical or transbronchial biopsy or cryobiopsy for pathology. Histopathological diagnoses were made by experienced pathologists. Available HRCT scans were reviewed centrally. Three to five transbronchial lung biopsy samples were collected from all patients specifically for this study, pooled by patient, and extracted for transcriptomic sequencing. After exclusions, diagnostic histopathology and RNA sequence data from 90 patients were used to train a machine learning algorithm (Envisia Genomic Classifier, Veracyte, San Francisco, CA, USA)to identify a usual interstitial pneumonia pattern. The primary study endpoint was validation of the classifier in 49 patients by comparison with diagnostic histopathology. To assess clinical utility, we compared the agreement and confidence level of diagnosis made by central multidisciplinary teams based on anonymised clinical information and radiology results plus either molecular classifier or histopathology results. Findings: The classifier identified usual interstitial pneumonia in transbronchial lung biopsy samples from 49 patients with 88% specificity (95% CI 70–98)and 70% sensitivity (47–87). Among 42 of these patients who had possible or inconsistent usual interstitial pneumonia on HRCT, the classifier showed 81% positive predictive value (95% CI 54–96)for underlying biopsy-proven usual interstitial pneumonia. In the clinical utility analysis, we found 86% agreement (95% CI 78–92)between clinical diagnoses using classifier results and those using histopathology data. Diagnostic confidence was improved by the molecular classifier results compared with histopathology results in 18 with IPF diagnoses (proportion of diagnoses that were confident or provisional with high confidence 89% vs 56%, p=0·0339)and in all 48 patients with non-diagnostic pathology or non-classifiable fibrosis histopathology (63% vs 42%, p=0·0412). Interpretation: The molecular test provided an objective method to aid clinicians and multidisciplinary teams in ascertaining a diagnosis of IPF, particularly for patients without a clear radiological diagnosis, in samples that can be obtained by a less invasive method. Further prospective clinical validation and utility studies are planned. Funding: Veracyte.

UR - http://www.scopus.com/inward/record.url?scp=85065841090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065841090&partnerID=8YFLogxK

U2 - 10.1016/S2213-2600(19)30059-1

DO - 10.1016/S2213-2600(19)30059-1

M3 - Article

C2 - 30948346

AN - SCOPUS:85065841090

VL - 7

SP - 487

EP - 496

JO - The Lancet Respiratory Medicine

JF - The Lancet Respiratory Medicine

SN - 2213-2600

IS - 6

ER -