Predictive biomarker graphical approach (PRIME) for Precision medicine

2025-04-10

AI Summary

Traditional biomarker analysis often relies on arbitrary categorical cutoffs, failing to reconcile clinical interpretability with the inherent continuous nature of biomarker–treatment effects—thereby limiting patient enrichment and drug development. To address this, we propose PRIME: a risk-prediction framework modeling treatment–continuous-biomarker interactions, enabling graphical visualization of biomarker–efficacy relationships and facilitating clinically interpretable cutoff selection. PRIME is the first method to embed predictive risk estimation within the TreatmentSelection framework, adjusting for confounding covariates while integrating net benefit analysis and rigorous model calibration. Implemented via G-computation, it accommodates diverse outcome types (e.g., binary, time-to-event) and complex covariate structures. By preserving biomarker continuity, PRIME substantially improves enrichment validity and clinical utility. An open-source R package provides end-to-end tools for modeling, visualization, and decision support.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Precision medicine is an evolving area in the medical field and rely on biomarkers to make patient enrichment decisions, thereby providing drug development direction. A traditional statistical approach is to find the cut-off that leads to the minimum p-value of the interaction between the biomarker dichotomized at that cut-off and treatment. Such an approach does not incorporate clinical significance and the biomarker is not evaluated on a continuous scale. We are proposing to evaluate the biomarker in a continuous manner from a predicted risk standpoint, based on the model that includes the interaction between the biomarker and treatment. The predicted risk can be graphically displayed to explain the relationship between the outcome and biomarker, whereby suggesting a cut-off for biomarker positive/negative groups. We adapt the TreatmentSelection approach and extend it to account for covariates via G-computation. Other features include biomarker comparisons using net gain summary measures and calibration to assess the model fit. The PRIME (Predictive biomarker graphical approach) approach is flexible in the type of outcome and covariates considered. A R package is available and examples will be demonstrated.

Problem

• Develops PRIME to evaluate biomarkers continuously for precision medicine
• Addresses limitations of traditional p-value based cutoff methods
• Provides graphical risk visualization and covariate-adjusted treatment selection

Innovation

• Continuous biomarker evaluation via predicted risk
• Graphical display for outcome-biomarker relationship
• G-computation for covariate-adjusted TreatmentSelection