Veracyte’s Envisia Classifier Improves ILD/IPF Diagnosis, Study Says

Santiago Gisler avatar

by Santiago Gisler |

Share this article:

Share article via email
Envisia

Envisia Genomic Classifier — a non-invasive diagnostic test developed by Veracyte and used as a complement to high-resolution computed tomography (HRCT) imaging — improves diagnosis of interstitial lung disease (ILD) and idiopathic pulmonary fibrosis (IPF) compared with HRCT alone, according to a recent study.

The findings were published in the journal The Lancet Respiratory Medicine in an article titled “Use of a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples: a prospective validation study.

The study analyzed data from 237 patients enrolled in the prospective Bronchial Sample Collection for a Novel Genomic Test (BRAVE) study, including 29 U.S. and European sites. The enrolled patients were being evaluated for ILD using samples from surgical or transbronchial biopsies (removing a small piece of lung tissue).

Researchers used parts of the biopsy samples to isolate RNA (the product molecule derived upon DNA expression) for subsequent quantification of gene expression, which was then used to train the Envisia algorithm to identify patterns associated with usual interstitial pneumonia (UIP), a pattern required for IPF diagnosis.

Validation of the classifier, by testing biopsy samples from 49 patients, showed that Envisia could identify known UIP patterns with an 88%  specificity and 70% sensitivity. In comparison, imaging with HRCT normally has a sensitivity of 43%.

Also, a comparison between results from the Envisia classifier and data from histopathology results (tissue examination) showed 86% agreement between the two. Diagnostic confidence improved using Envisia compared with histopathology data in eighteen of the 46 IPF patients analyzed (89% and 56%, respectively).

“IPF is often challenging to distinguish from other ILDs, but timely and accurate diagnosis is critical so that patients with IPF can access therapies that may slow progression of the disease, while avoiding potentially harmful treatments,” Ganesh Raghu, MD, lead author said in a press release. Raghu is director at the Center for Interstitial Lung Diseases and professor of medicine at the University of Washington.

“Our results with molecular classification through machine learning (the Envisia classifier) are promising and, along with clinical information and radiological features in high-resolution CT imaging, physicians through multidisciplinary discussions, may be able to utilize the molecular classification as a diagnostic tool to make a more informed and confident diagnoses,” Raghu added.

Although available therapies can slow down the progression of IPF, reports show that more than half (55%) of patients with IPF or ILD had been misdiagnosed at least once. According to a study by the Pulmonary Fibrosis Foundation, accurate diagnosis took three years or more for one in five patients.

“We believe our test has the potential to transform the diagnosis of IPF and other ILDs,” said Bonnie Anderson, chairman and CEO of Veracyte.

“More immediately, this new paper, combined with the Medicare coverage policy for the Envisia classifier issued recently, will fuel our efforts to make the classifier more widely available to the patients across the country who can benefit from it,” she said.

The Envisia classifier, which recently earned Medicare coverage, is the first commercially available test that is designed to distinguish between IPF and other ILDs. Envisia combines gene expression data obtained from bronchoscopy samples and machine learning to identify UIP patterns.