Start date: 2025
Funding: Sorbonne Université
This project aims to improve drug database management by proposing an advanced structuring of drug information and further automation of the database construction. By further structuring information, the resulting database can take into account the patient’s context in a more comprehensive manner, thus reducing unnecessary alerts and improving the safety of medical prescriptions. Winner of a challenge organized by the French National Authority for Health in 2022, our solution is based on the integration of large language models (LLM) to automate and optimize the structuring of drug information. This approach reduces the human resources required, while ensuring increased reliability and completeness. The objective is to develop a proof of concept (POC) demonstrating the feasibility and effectiveness of this innovation, in order to convince health authorities and national and international market players.
Contact: Jean-Baptiste Lamy