RNA-Seq, machine learning test enables diagnosis of lung disease when results from high-resolution CT imaging are not definitive

Veracyte, Inc. announced today the publication of an independent study showing that the Envisia Genomic Classifier enables physicians to more confidently diagnose idiopathic pulmonary fibrosis (IPF), a progressive lung disease, when results from high-resolution CT (HRCT) imaging are not definitive. The real-world clinical findings appear online ahead of print in CHESTthe journal of the American College of Chest Physicians.

The Envisia classifier is the first and only commercially available genomic test that helps distinguish IPF from other interstitial lung diseases (ILDs), without the need for risky surgery. Veracyte developed the classifier by combining RNA whole-transcriptome sequencing and machine learning, which enables a comprehensive genomic approach for distinguishing the usual interstitial pneumonia (UIP) pattern, whose presence is essential to IPF diagnosis. Veracyte is preparing to launch the test in global markets in 2021.

The new study compared the impact of Envisia classifier results on diagnostic decision-making among two physician multidisciplinary discussion (MDD) groups that each evaluated 24 patients with suspected IPF or other ILDs whose HRCT results were inconclusive. The groups sequentially reviewed clinical and HRCT findings, followed by Envisia results, either after (MDD1) or before (MDD2) findings from cryobiopsy (a diagnostic procedure that is sometimes conducted during bronchoscopy). In each case, the MDD group sought additional information, including UIP, to make a more confident ILD diagnosis, including IPF in some cases.

The researchers found that the rate of high-confidence diagnosis was significantly higher for the MDD1 group after adding the Envisia results to those of cryobiopsy (46% to 75%). The increase in a confident diagnosis was higher for those individuals with “probable” UIP (43% to 93%) and patients with a final diagnosis of IPF (31% to 92%). Additionally, they found high overall agreement between the Envisia result and the final diagnosis of UIP or non-UIP for both MDD groups (96% and 92%, for MDD1 and MDD2 respectively) as compared to 83% agreement between cryobiopsy results and both MDD groups.

“Distinguishing IPF from other ILDs can be challenging even in settings where a multidisciplinary approach is used. However, obtaining a timely, accurate diagnosis is critical to rapidly initiate and optimize treatments to slow disease progression,” said Joseph Lasky, M.D., professor of medicine at Tulane University and corresponding author of the study. “Our findings suggest that integrating Envisia classifier genomic data into the full context of recommended practice enables clinicians to increase their confidence in diagnosing IPF, particularly in patients whose imaging results suggest probable UIP, but for whom a secure diagnosis remains in doubt.”

Each year in the United States and Europe, up to 200,000 patients are evaluated for suspected ILDs, including IPF, which is among the most common, deadly and difficult to diagnose of these lung-scarring diseases. A survey conducted by the Pulmonary Fibrosis Foundation showed that 55 percent of IPF/ILD patients are misdiagnosed at least once and, for one in five patients, accurate diagnosis took three or more years. Accurate and timely diagnosis is important because therapies are now available to slow the progression of IPF.

“This new publication adds to the growing body of clinical evidence showing that the Envisia classifier helps physicians make a more confident diagnosis of IPF,” said Bonnie Anderson, Veracyte’s chairman and chief executive officer. “We believe our test can significantly improve care for patients with suspected IPF, helping them avoid unnecessary surgeries and receive appropriate treatment more quickly. These findings are important to helping us expand coverage with commercial payers, pursue clinical guideline inclusion and expand access for the Envisia classifier globally.”

Source – BusinessWire

Kheir F et al. (2020) Employing Bronchoscopic Lung Cryobiopsy and a Genomic Classifier in the Multidisciplinary Diagnosis of Diffuse Interstitial Lung Diseases. Chest S0012-3692(20)31499-9. [article]

Leave a Reply

Your email address will not be published. Required fields are marked *


Time limit is exhausted. Please reload CAPTCHA.