On November 12, 2021 Biodesix, Inc. (Nasdaq: BDSX), a leading data-driven diagnostic solutions company with a focus in lung disease, reported that the company will co-present with Genentech, a member of the Roche Group (SIX: RO, ROG; OTCQX: RHHBY), three posters at the 36th Annual Society for Immunotherapy of Cancer (SITC) (Free SITC Whitepaper) Nov. 10 – 14, 2021 from research into diagnostic tests of treatment response of NSCLC patients to immune checkpoint inhibitor therapy (Press release, Biodesix, NOV 12, 2021, View Source [SID1234595467]).
Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:
Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing
Schedule Your 30 min Free Demo!
"Biodesix is committed to performing research with biopharma companies, while pursuing, discovering and developing applications that can help physicians and researchers address the needs of patients with lung cancer who will benefit from quick, actionable test results," said Scott Hutton, CEO, Biodesix. "We are pleased to present data on two tests that have the potential to become instrumental in the care of patients with non-small cell lung cancer (NSCLC). Additionally, our data highlights novel methods that we have developed to provide an explanation as to how our proprietary Diagnostic Cortex Artificial Intelligence (AI) platform combines molecular attributes to produce individual patient results. This data is extremely important because we expect that this will provide clarity and transparency to how our AI-based tests work and how a diagnostic test may better predict efficacy of various treatments in the most appropriate patient populations. We are proud of the data being presented at SITC (Free SITC Whitepaper) as it underscores our commitment to the lung cancer community."
The three Genentech/Biodesix-sponsored posters include the following:
Abstract #26: Validation of the Primary Immune Response (PIR) test in advanced non-small cell lung cancer (NSCLC): blinded retrospective analyses from the POPLAR and OAK trials
Findings will be presented from blinded, retrospective analyses of two Genentech multicenter, open-label RCT clinical studies comparing atezolizumab versus docetaxel in patients with previously treated NSCLC (POPLAR Phase 2 and OAK Phase 3). The Biodesix liquid-biopsy mass spectrometry-based Primary Immune Response (PIR) test stratified outcomes for patients treated with the study drug in second and third line, predicting overall survival, even when adjusted for PD-L1 expression and clinical factors. The importance of understanding who will or will not respond to immunotherapy is critical and identifying predictive biomarkers of immunotherapy response has become a growing focus of immune-oncology research. This study highlights the potential of biomarkers of immune checkpoint inhibitors, such as the PIR test, to support patient stratification.
Abstract #28: Predictions of outcomes and benefit of immune checkpoint inhibitor treatment in non-small cell lung cancer require information on both tumor and host biology
Findings from a Genentech blinded, retrospective study of second- and third-line NSCLC patients in the OAK Phase 3 clinical study comparing atezolizumab versus docetaxel in patients with previously treated NSCLC will be presented. The study demonstrated that the Biodesix Anti-PD-L1 Response Test (ART), based on mass spectrometry of pretreatment serum, stratifies outcomes in both treatment arms overall and in all PD-L1 subgroups. The Biodesix ART test was shown in independent validation to predict outcomes for NSCLC patients treated in a large Phase 3 study and was discovered and developed for Genentech as a part of a partnership between the two companies.
Abstract #831: Exact Shapley Values for explaining complex machine learning based molecular tests of checkpoint inhibitors: potential utility for patients, physicians, and translational research
Data will show how Exact Shapley Values (SVs), a technique developed by Biodesix, can explain how complex machine learning (ML)-based tests combine molecular attributes to produce individual patient results. Exact SVs can be obtained for certain ML architectures used in molecular test development, revealing the overall relative importance of attributes used in such molecular tests. Specifically, this study evaluated SVs for the Biodesix Anti-PD-L1 Response Test (ART), that was shown in independent validation to predict outcomes for NSCLC patients treated in a large Phase 3 study. By subgrouping patients according to ART results, different patterns of SVs were determined, potentially revealing different biologies that were predictive of overall survival outcomes. Exact SVs explain how complex ML-based tests combine molecular attributes to produce individual patient results.