Imagine trying to prove a medicine works by looking at messy, everyday health records instead of a perfectly controlled lab study. This project builds smart AI tools that clean up and analyze this 'real-world' data so regulators can trust it. It's like turning a pile of random receipts into a professional financial audit to prove a product's value.
Regulators struggle to trust real-world data for drug approval because the data is too messy and varies too much between countries. This forces companies to rely on expensive, slow clinical trials even when patient data already exists.
AI-supported methodologies and tools for analyzing real-world data. These include ML approaches for target trial emulation and tools to characterize disease clusters.
If you are a drug developer dealing with the high cost of traditional clinical trials — this project developed AI-based data-driven methods that allow real-world data to serve as a high-quality external control. This can help make decisions during the pre-authorisation phase of a medicinal product.
If you are a medical device manufacturer dealing with data variability in post-market monitoring — this project developed tools for the effective analysis of real-world data. This helps in safety monitoring and regulatory decision-making along the product lifecycle.
If you are an analytics firm dealing with heterogeneous health claims data across different European countries — this project developed AI/ML approaches for target trial emulation. This allows for better prediction of drug effectiveness and safety using existing registries.
Based on available project data, there is no pricing information provided as this is a research project funded by an EU contribution of EUR 6,999,425.
The project focuses on developing methods for regulatory decision-making and HTA across Europe, involving 10 partners from 6 countries to ensure broad applicability.
Based on available project data, specific IP and licensing terms are not disclosed; however, the results are intended to inform guidelines for regulatory authorities and HTA bodies.
The project aims to enable the use of real-world data in pre-authorisation and evaluation phases, which could potentially streamline the evidence-gathering process for regulators.
The project specifically addresses the challenge of analyzing data from different settings and sources, including health insurances and electronic health records.
The consortium is heavily weighted toward public and research entities, consisting of 10 partners across 6 countries. It includes 4 research organizations, 2 universities, and 4 other entities (including regulatory agencies like BfArM and DKMA). Notably, there is a 0% industry ratio, with only 1 SME involved, indicating that the primary driver is regulatory standard-setting rather than immediate commercial productization.
Contact BUNDESINSTITUT FUR ARZNEIMITTEL UND MEDIZINPRODUKTE (BfArM) in Germany
Contact us to find out how to apply these AI-driven RWD methods to your regulatory submission strategy.
