De-Risking Phase 3 Rheumatoid Arthritis Trials with Model-Based Meta-Analysis (MBMA)

A pharmaceutical company developing a new rheumatoid arthritis treatment faced critical unknowns for Phase 3 planning based on limited Phase 2 data, needing to determine optimal dosing, whether to run a superiority or non-inferiority trial, and how the compound compared competitively. Certara applied model-based meta-analysis, combining the company's Phase 2 results with external rheumatoid arthritis trial data, building dose-response models for efficacy (ACR20/50/70) and safety, adjusting for covariates like baseline CRP and methotrexate use, and simulating Phase 3 outcomes across doses and trial designs. The case study reports that simulated outcomes closely matched actual Phase 3 results, informing dose selection, trial design, and competitive positioning, and enabling "data-driven progression to Phase 3, reducing uncertainty and resource risk" -- no specific enrollment, statistical, or financial figures are disclosed.

The customer is anonymised in Certara’s own case study — not withheld by us.

Certara is a biosimulation software company (Simcyp, Phoenix) whose PK/PD and QSP models predict drug behavior in the body; the FDA itself licenses Certara's software to review sponsor submissions.

This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.