Strategies for Biomarker-Driven Sub-population Optimization in Clinical Trials

It is no secret that the cost to bring a drug to market has increased and failed trials can cost sponsors upwards of a billion dollars. Statistics have shown that up to 65 percent of Phase II and over 35 percent of Phase III clinical trials do not progress to the next stage. This results in approximately 12 percent of clinical trials resulting in therapies approved by the US Food and Drug Administration (FDA).

Failed trials often have sub-populations of patients who respond well to the treatment being evaluated; however, the trial is abandoned because of the overall data. This results in a financial loss for sponsors and missed opportunity for patients to benefit from a therapeutic innovation. Moreover, the process of executing this analysis requires a resource-intensive, manual process.

Artificial intelligence (AI), enabled via technology platforms, is a key driver of change in the clinical trial industry. This webinar will delve into how AI, through a SaaS platform like IQVIA’s Sub-Population Optimization and Modeling Solution (SOMS), can rapidly analyze clinical data sets to identify promising patient sub-groups that could benefit from a therapy, thereby increasing safety and treatment outcomes.

SOMS uses an industry method called subgroup identification based on differential effect search (SIDES), which is validated, published and defendable to health authorities. By leveraging SIDES, sub-populations can be identified as fast as 30 seconds (up to 99 percent-time savings over current, manual biostatistics-based processes).

Harnessing the power of SIDES in a technology platform enables sponsors to:

Identify predictive biomarkers and sub-populations

Track sub-populations

Design and adjust strategies to maximize trial success

Develop rescue strategies for poorly performing trials

Execute trial simulation and benchmarking

Join this webinar to learn how IQVIA’s SOMS is leveraging AI for biomarker-driven sub-population optimization to help conduct clinical trials.

Keywords: Clinical Trials, Drug Development, Clinical Research, Biomarkers, Clinical Operations, Clinical Data, Clinical Development, AI, Biostatistics, Commercialization/HEOR/Market Access, Other Software