The presentation addressed the discovery of patient subpopulation-specific prognostic factors of overall survival (OS).
FREMONT, CA: The precision medicine company GNS Healthcare collaborated with Alliance for Clinical Trials in Oncology (Alliance) to present the discoveries of predictive biomarkers for metastatic colorectal cancer (mCRC) patient response to treatments such as cetuximab, bevacizumab, and panitumumab at ESMO World Congress on Gastrointestinal Cancer 2019 conference in Barcelona, Spain.
The presentation included the discovery of patient subpopulation-specific prognostic factors of overall survival (OS). The in-silico patient models identified AST level, the primary side of the tumor, intra-abdominal metastasis status as ubiquitous predictors of OS. The presentation also addressed the role of KRAS status and hemoglobin levels in predicting the side tumor location. The identification of prognostic factors of OS for subpopulations of patients with colorectal cancer is the key to better risk stratification at treatment initiation. It helps in identifying predictive factors for treatment response, which plays a crucial role in forming personalized treatment decisions.
The poster discussion session held on July 5 highlighted the study, ‘Bayesian machine learning on CALGB/SWOG 80405 (Alliance) and PEAK data to identify the heterogeneous landscape of clinical predictors of overall survival (OS) in different populations of metastatic colorectal cancer (mCRC).’
Nine independent predictive model ensembles were developed using clinical data from over 2,000 patients with mCRC and GNS’ powerful casual AI platform, Reverse Engineering & Forward Simulation (REFS), to understand predictive biomarkers for a patient response when receiving different treatments, and to identify patient subpopulation-specific prognostic factors of OS.
The study identified gender-specific predictors, specifically creatinine level, intra-abdominal metastasis status, and the interaction of albumin and neutrophil levels. It showed that urine protein levels predicted better efficacy from cetuximab treatment in patients with mCRC and left-sided tumors.
Colin Hill, Chairman, CEO, and Co-Founder, GNS, said, “We have never been in a better position to unravel drivers of disease and patient response to specific drugs. We built an in silico patient model of colorectal cancer and were able to uncover biomarkers that tell us which patients will respond to which treatment, and most importantly, why. This is what will get us to the point of delivering personalized medicine and eradicating diseases.”