Classification of usual interstitial pneumonia in patients with interstitial lung disease: assessment of a machine learning approach using high-dimensional transcriptional data.

BACKGROUND: Idiopathic pulmonary fibrosis is a progressive fibrotic lung disease that distorts pulmonary architecture, leading to hypoxia, respiratory failure, and death. Diagnosis is difficult because other interstitial lung diseases have similar radiological and histopathological characteristics. A usual interstitial pneumonia pattern is a hallmark of idiopathic pulmonary fibrosis and is essential for its diagnosis. We aimed to develop a molecular test that distinguishes usual interstitial pneumonia from other interstitial lung diseases in surgical lung biopsy samples. The eventual goal of this research is to develop a method to diagnose idiopathic pulmonary fibrosis without the patient having to undergo surgery. METHODS: We collected surgical lung biopsy samples from patients with various interstitial lung diseases at 11 hospitals in North America. Pathology diagnoses were confirmed by an expert panel. We measured RNA expression levels for 33 297 transcripts on microarrays in all samples. A classifier algorithm was trained on one set of samples and tested in a second set. We subjected a subset of samples to next-generation RNA sequencing (RNAseq) generating expression levels on 55 097 transcripts, and assessed a classifier trained on RNAseq data by cross-validation. FINDINGS: We took 125 surgical lung biopsies from 86 patients. 58 samples were identified by the expert panel as usual interstitial pneumonia, 23 as non-specific interstitial pneumonia, 16 as hypersensitivity pneumonitis, four as sarcoidosis, four as respiratory bronchiolitis, two as organising pneumonia, and 18 as subtypes other than usual interstitial pneumonia. The microarray classifier was trained on 77 samples and was assessed in a test set of 48 samples, for which it had a specificity of 92% (95% CI 81-100) and a sensitivity of 82% (64-95). Based on a subset of 36 samples, the RNAseq classifier had a specificity of 95% (84-100) and a sensitivity of 59% (35-82). INTERPRETATION: Our results show that the development of a genomic signature that predicts usual interstitial pneumonia is feasible. These findings are an important first step towards the development of a molecular test that could be applied to bronchoscopy samples, thus avoiding surgery in the diagnosis of idiopathic pulmonary fibrosis. FUNDING: Veracyte.

A prospective assessment defining the limitations of thyroid nodule pathologic evaluation.

BACKGROUND: Clinical management of thyroid neoplasms is based on light microscopic diagnosis, but its accuracy and precision are poorly defined. OBJECTIVE: To assess inter- and intraobserver variability of preoperative cytopathologic and postoperative histopathologic thyroid diagnoses. DESIGN: Samples were collected in a prospective, multicenter trial validating a gene expression classifier between June 2009 and December 2010. SETTING: 14 academic and 35 community clinical sites. PATIENTS: 653 patients with 776 surgically resected thyroid nodules of 1 cm or greater. MEASUREMENTS: Intraobserver concordance among 2 or more central histopathologists who independently read histopathology slides was calculated. Interobserver concordance between the diagnoses made by the central histopathologists and those made by local pathologists were calculated. Intra- and interobserver concordance for cytopathology was similarly calculated by comparing diagnoses made by local pathologists with those made by a central panel of 3 cytopathologists. RESULTS: Concordance on the histopathologic distinction between benign and malignant diagnoses was 91% comparing local with central histopathologists and 90% comparing 2 central histopathologists. Using the 6-category Bethesda System, 64.0% of diagnoses made by local and central cytopathologists and 74.7% of intraobserver diagnoses were concordant. Central cytopathologists made fewer indeterminate diagnoses than local pathologists (41.2% vs. 55.0%). LIMITATIONS: Many local pathologists did not use the Bethesda System, so their reports were translated to allow comparison. The study required histopathology, and the study population and specimens did not encompass all newly evaluated patients with a thyroid nodule. CONCLUSION: Substantial inter- and intraobserver variability exists in the cytopathologic and histopathologic evaluation of thyroid nodules, confirming an inherent limitation of visual microscopic diagnosis. PRIMARY FUNDING SOURCE: Veracyte.