The EU project Real4Reg: unlocking real-world data with AI

Area of Science:

• Regulatory Science
• Health Technology Assessment
• Data Science

Background:

• Real-world data (RWD) use is established in post-authorization regulatory processes but faces challenges in pre-authorization stages.
• Limited availability, heterogeneity, and analytical complexities of RWD hinder its regulatory application.
• Emerging AI in healthcare research offers opportunities but requires knowledge on applying it to diverse RWD for regulatory decision-making and health technology assessment (HTA).

Purpose of the Study:

• To enable RWD utilization by developing user-friendly analytical solutions for EU regulatory and HTA bodies.
• To implement AI algorithms for effective RWD analysis in regulatory decision-making and HTA.
• To investigate the value of diverse RWD sources for generating high-quality, population-based information across the product lifecycle.

Main Methods:

• The Real4Reg project employs four use cases to demonstrate best practices for RWD analysis.
• These use cases cover evaluation, pre-authorization, external validity of observational data, post-authorization safety studies, and comparative effectiveness.
• The project introduces its objectives, structure, and role within the European RWD landscape.

Main Results:

• Real4Reg identifies and describes benefits and risks of new/optimized RWD analysis methods.
• Key aspects evaluated include safety, effectiveness, interoperability, appropriateness, accessibility, value creation, and sustainability.
• The project aims to provide evidence supporting better decision-making for medicines.

Conclusions:

• The Real4Reg project's findings will support improved decision-making regarding medicines.
• Enhanced RWD analysis methods will ultimately benefit patient health.
• Real4Reg is registered in the HMA-EMA Catalogues of real-world data sources and studies (EU PAS number EUPAS105544).