Business
SOPHiA GENETICS Announces Launch of DEEP-Lung-IV Multimodal Clinical Study
Study to leverage deep learning-enabled analysis of the aggregation of real-world multimodal data to validate predictive signatures associated with response
About this update from Sophia Genetics Sa
[{"type":"text","content":"Study to leverage deep learning-enabled analysis of the aggregation of real-world multimodal data to validate predictive signatures associated with response to immunotherapy and prognosis of patients with stage IV non-small cell lung cancer\nLarge-scale, multicentric real-world study aims to enroll 4,000 patients from approximately 30 sites across North America, Europe, and Latin America\n BOSTON and LAUSANNE, Switzerland, Dec. 1, 2021 /PRNewswire/ -- SOPHiA GENETICS SA (Nasdaq: SOPH), the creator of a global data pooling and knowledge sharing platform that advances data-driven medicine, announced today the launch of their DEEP-Lung-IV clinical study (NCT04994795). The study leverages deep learning-enabled analysis of the aggregation of multimodal clinical, biological, genomic and radiomics data to identify and validate predictive signatures associated with response to immunotherapy and prognosis of patients with metastatic non-small cell lung cancer (NSCLC).\n\n \n \n \n \n \n \n\n \nOver the last decade, immunotherapy has revolutionized the treatment landscape for patients diagnosed with stage IV NSCLC and has become the standard of care in the frontline setting for patients without oncogene-activating mutations. Despite the clinical promise of immunotherapy, significant challenges remain as the majority of NSCLC patients fail to respond to immune checkpoint inhibitors. Today, PD-L1 is the only standard predictive biomarker for immune checkpoint inhibitor efficacy. However, it remains a very suboptimal biomarker with several well-characterized issues limiting its clinical utility. Thus, an urgent need exists to discover new predictive biomarkers of response to immunotherapy.\nSOPHiA GENETICS' DEEP-Lung-IV clinical study aims to predict immunotherapy treatment response at first evaluation at the individual patient level using data across multiple modalities including genomics, radiomics, clinical and biological data. The study also aims to validate an algorithm that will allow the prediction of outcomes at the individual patient such as progression-free survival (PFS) and overall survival (OS). This predictive model will help identify patients that are likely to benefit from immunotherapy versus those that are not, as well as stratify patients according to risk, helping clinicians make more informed therapeutic decisions for th...