The need to identify patients who respond to and benefit from specific drugs is becoming increasingly crucial as the pressure to prove better outcomes and lower costs on the biopharma industry builds. Given the high failure rate of novel therapies in clinical development and the need to prove the value of newly approved drugs in the real world, life sciences companies are charged with identifying the patients who benefit most from a new or existing treatment.
The convergence of powerful AI, unparalleled volume and variety of data and faster computing processing now allows life sciences companies to stratify patients who will positively respond to specific drugs.
The GNS causal machine learning and simulation platform, REFS along with our StratifyRx application discovers the most accurate and robust biomarkers of disease risk and treatment response. Our technology has been applied to both clinical trial and real-world settings, across 40-plus diseases from various cancers to arthritis to depression to diabetes.
Users can select which type of visual graphics and information plots they would like to see such as distribution, sparsity, and counts across different data modalities. With a single click, users can switch between the training or test datasets for comparison.
Improving the Probability of Success with Biomarkers
Failure in the clinical trial process can be the result of simply not having the right drug to mitigate a disease. More often, however, an unsuccessful trial results from failing to properly identify the patients who will benefit from the drug. The use of biomarkers to identify subpopulations in trials has been highly effective in accelerating probability of success (POS), especially in the early trial phases. Increased use of biomarkers is key to helping researchers find the target population that responds positively to drugs in development.
Data from Estimation of Clinical Trial Success Rates and Related Parameters study published in Biostatistics January 31, 2018.
StratifyRx discovers biomarkers and subpopulations across the entire drug lifecycle allowing biopharma companies to optimize clinical trials, accelerate drug development timelines, reduce costs, and discover new indications for current therapies.
Learning how the biology of a disease works and nuances of progression in patients creates an opportunity to identify and investigate potential biomarkers. By gaining a deeper understanding of disease and its mechanisms, researchers are better able to target their efforts on developing new drugs.
By discovering relevant biomarkers in patients who respond positively to a drug in early clinical trials, biopharma can optimize and streamline later trials, by precisely recruiting patients, calibrating inclusion criteria and developing companion diagnostic tests. Recruiting the right patients can not only improve the probability of success, but also provide insights into how the drug would perform in the real world.
Drug Label Expansion
Once the drug has been delivered into the hands of physicians and patients, real world data is generated based on its effectiveness for both primary indications and off label use. By analyzing this data, biopharma can generate real-world evidence (RWE) to identify subpopulations for whom the drug is more beneficial, discover new indications, expand a drug’s label and recommend lines of therapy.
By stratifying patient subpopulations based on rate of progression or expected response to therapy, biopharma companies are able to optimize clinical trials through refined criteria and precise recruitment, accelerate drug development timelines, reduce costs, and discover new indications for label expansion of current therapies.
To learn more, download our Subpopulations Tool overview.