GNS Healthcare’s Subpopulation tool allows biopharma to
run a complete trial dataset and quickly identify predictive
biomarkers to select patients with a high probability of
treatment benefit in a follow-up trial. It also prioritizes
prognostic biomarkers that identify disease drivers
that when perturbed show a change in the outcome of
interest.

The GNS Subpopulation tool:
• Identifies a set of predictive response biomarkers
• Determines confounding variables and removes them
from analysis
• Allows the user to optimize the set of biomarkers by
varying cut- points and the ability to visualize the impact
on the corresponding hazard ratios and information on
the biomarker prevalence
• Prioritizes prognostic biomarkers to identify
disease drivers
The Subpopulation tool eliminates the time-consuming
current methods of biomarker selection, allowing scientists
to explore all potential biomarkers and select the most
relevant predictive biomarkers for a trial. The tool
accelerates the process of preparing for later phase trials
by reducing biomarker discovery from months to weeks.

The REFS Advantage
The REFS causal machine learning platform can be
an integral part of your subpopulation identification
process by:
• Using retrospective analysis to generate biomarker
hypotheses
• Identifying predictive biomarkers to enrich patients
in clinical studies
• Using data to understand disease progression and
treatment impact
• Performing interim analysis to refine biomarker
choice and adjust trials
• Employing causal models to improve clinical
trial analysis
• Continuously validating and improving causal
models using