To date, more than 7,000 rare diseases affecting 400 million people worldwide including 3 million in France have been identified. There are still no approved treatments for 95% of these diseases. The use of real-world health data and AI may thus lead to major innovations in diagnosis and the identification of therapeutic molecules. The “Artificial Intelligence and Rare Diseases” project thus aims to respond to the strong expectations of patients with rare diseases.


The objective of this project is to develop a concrete example of the use of artificial intelligence in healthcare to contribute to the structuring and competitiveness of the sector and make France a leader in the field of rare diseases.

Through this project, the idea is first to have an interoperable data warehouse in a secure environment to be able to match, standardize and poll public and private data on rare diseases. This initiative will be based on already existing infrastructures, such as the National Data Bank for Rare Diseases (BNDMR), the French health insurance data, the Health Data Hub or the Data Warehouse of the Public Hospitals of Paris (AP-HP).

Thanks to this infrastructure, the aim is to meet a key medical need: shorten diagnostic odyssey and reduce diagnostic dead-end for patients.


Supported by a joint committee composed of representatives of the whole sector, the project governance will be similar to that of the Strategic Committee of the 3rd French National Plan for Rare Diseases