Daniel G Pankratz1, Yoonha Choi1, Urooj Imtiaz1, Grażyna M Fedorowicz1, Jessica D Anderson1, Thomas V Colby2, Jeffrey L Myers3, David A Lynch4, Kevin K Brown5, Kevin R Flaherty6, Mark P Steele7, Steve D Groshong5, Ganesh Raghu8, Neil M Barth1, P Sean Walsh1, Jing Huang1, Giulia C Kennedy1, Fernando J Martinez9. 1. 1 Veracyte, Inc., South San Francisco, California. 2. 2 Department of Laboratory Medicine and Pathology, Mayo Clinic, Scottsdale, Arizona. 3. 3 Department of Pathology, University of Michigan School of Medicine, Ann Arbor, Michigan. 4. 4 Department of Radiology, National Jewish Health, Denver, Colorado. 5. 5 Department of Medicine, National Jewish Health, Denver, Colorado. 6. 6 Department of Internal Medicine, University of Michigan Health System, Ann Arbor, Michigan. 7. 7 W. G. Hefner Veterans Affairs Medical Center, Salisbury, North Carolina. 8. 8 Department of Medicine and Laboratory Medicine, University of Washington Medical Center, Seattle, Washington; and. 9. 9 Division of Pulmonary and Critical Care Medicine, Weill Cornell Medical College, New York, New York.
Abstract
RATIONALE: Usual interstitial pneumonia (UIP) is the histopathologic hallmark of idiopathic pulmonary fibrosis. Although UIP can be detected by high-resolution computed tomography of the chest, the results are frequently inconclusive, and pathology from transbronchial biopsy (TBB) has poor sensitivity. Surgical lung biopsy may be necessary for a definitive diagnosis. OBJECTIVES: To develop a genomic classifier in tissue obtained by TBB that distinguishes UIP from non-UIP, trained against central pathology as the reference standard. METHODS: Exome enriched RNA sequencing was performed on 283 TBBs from 84 subjects. Machine learning was used to train an algorithm with high rule-in (specificity) performance using specimens from 53 subjects. Performance was evaluated by cross-validation and on an independent test set of specimens from 31 subjects. We explored the feasibility of a single molecular test per subject by combining multiple TBBs from upper and lower lobes. To address whether classifier accuracy depends upon adequate alveolar sampling, we tested for correlation between classifier accuracy and expression of alveolar-specific genes. RESULTS: The top-performing algorithm distinguishes UIP from non-UIP conditions in single TBB samples with an area under the receiver operator characteristic curve (AUC) of 0.86, with specificity of 86% (confidence interval = 71-95%) and sensitivity of 63% (confidence interval = 51-74%) (31 test subjects). Performance improves to an AUC of 0.92 when three to five TBB samples per subject are combined at the RNA level for testing. Although we observed a wide range of type I and II alveolar-specific gene expression in TBBs, expression of these transcripts did not correlate with classifier accuracy. CONCLUSIONS: We demonstrate proof of principle that genomic analysis and machine learning improves the utility of TBB for the diagnosis of UIP, with greater sensitivity and specificity than pathology in TBB alone. Combining multiple individual subject samples results in increased test accuracy over single sample testing. This approach requires validation in an independent cohort of subjects before application in the clinic.
RATIONALE: Usual interstitial pneumonia (UIP) is the histopathologic hallmark of idiopathic pulmonary fibrosis. Although UIP can be detected by high-resolution computed tomography of the chest, the results are frequently inconclusive, and pathology from transbronchial biopsy (TBB) has poor sensitivity. Surgical lung biopsy may be necessary for a definitive diagnosis. OBJECTIVES: To develop a genomic classifier in tissue obtained by TBB that distinguishes UIP from non-UIP, trained against central pathology as the reference standard. METHODS: Exome enriched RNA sequencing was performed on 283 TBBs from 84 subjects. Machine learning was used to train an algorithm with high rule-in (specificity) performance using specimens from 53 subjects. Performance was evaluated by cross-validation and on an independent test set of specimens from 31 subjects. We explored the feasibility of a single molecular test per subject by combining multiple TBBs from upper and lower lobes. To address whether classifier accuracy depends upon adequate alveolar sampling, we tested for correlation between classifier accuracy and expression of alveolar-specific genes. RESULTS: The top-performing algorithm distinguishes UIP from non-UIP conditions in single TBB samples with an area under the receiver operator characteristic curve (AUC) of 0.86, with specificity of 86% (confidence interval = 71-95%) and sensitivity of 63% (confidence interval = 51-74%) (31 test subjects). Performance improves to an AUC of 0.92 when three to five TBB samples per subject are combined at the RNA level for testing. Although we observed a wide range of type I and II alveolar-specific gene expression in TBBs, expression of these transcripts did not correlate with classifier accuracy. CONCLUSIONS: We demonstrate proof of principle that genomic analysis and machine learning improves the utility of TBB for the diagnosis of UIP, with greater sensitivity and specificity than pathology in TBB alone. Combining multiple individual subject samples results in increased test accuracy over single sample testing. This approach requires validation in an independent cohort of subjects before application in the clinic.
Authors: Paul A Reyfman; George R Washko; Mark T Dransfield; Avrum Spira; MeiLan K Han; Ravi Kalhan Journal: Am J Respir Crit Care Med Date: 2018-08-15 Impact factor: 21.405
Authors: Tomoyuki Hida; Mizuki Nishino; Takuya Hino; Junwei Lu; Rachel K Putman; Elias F Gudmundsson; Tetsuro Araki; Vladimir I Valtchinov; Osamu Honda; Masahiro Yanagawa; Yoshitake Yamada; Akinori Hata; Masahiro Jinzaki; Noriyuki Tomiyama; Hiroshi Honda; Raul San Jose Estepar; George R Washko; Takeshi Johkoh; David C Christiani; David A Lynch; Vilmundur Gudnason; Gunnar Gudmundsson; Gary M Hunninghake; Hiroto Hatabu Journal: Eur J Radiol Date: 2020-05-18 Impact factor: 3.528
Authors: Fayez Kheir; Ala Alkhatib; Gerald J Berry; Philip Daroca; Lisa Diethelm; Reinaldo Rampolla; Shigeki Saito; David L Smith; David Weill; Marjorie Bateman; Ramsy Abdelghani; Joseph A Lasky Journal: Chest Date: 2020-05-25 Impact factor: 9.410
Authors: Yoonha Choi; Jiayi Lu; Zhanzhi Hu; Daniel G Pankratz; Huimin Jiang; Manqiu Cao; Cristina Marchisano; Jennifer Huiras; Grazyna Fedorowicz; Mei G Wong; Jessica R Anderson; Edward Y Tom; Joshua Babiarz; Urooj Imtiaz; Neil M Barth; P Sean Walsh; Giulia C Kennedy; Jing Huang Journal: BMC Pulm Med Date: 2017-11-17 Impact factor: 3.317