RHU AI-Triomph

2024 – 2029

The hospital-university health research program (RHU) run by the ANR aims to support translational health and clinical research projects.

The RHU AI-Triomph (Artificial Intelligence – clinical TRIals Optimization for oncology with Multimodal PatHology) is coordinated and led by Prof. Magali Svrcek, Department of Anatomy and Cytology Pathology, Hôpital Saint-Antoine, AP-HP, AP-HP.Sorbonne Université. The other two co-sponsors of this project are Pr Jean-Baptiste Bachet, Hepato-gastroenterology Department, Pitié-Salpêtrière Hospital, AP-HP. Sorbonne Université, and Prof. Xavier Tannier, Professor of Computer Science at LIMICS, Sorbonne Université.

The RHU AI-TRIOMPH aims to develop a cutting-edge artificial intelligence system to revolutionize personalized therapeutic approaches and optimize the design of clinical trials for three poor-prognosis cancers that represent a major public health problem in France and worldwide: ductal adenocarcinomas of the pancreas, esogastric adenocarcinomas and certain thyroid cancers.
The tripartite consortium (Sorbonne University, AP-HP and Owkin) will generate multimodal data sets, including data from the AP-HP health warehouse, digitized slides – building on the deployment of digital pathology at AP-HP.SU – and, for the first time, liquid biopsies. This methodology will first be applied to pancreatic cancer, then extended to the other two cancers. An AI platform based on OWKIN technology (federated learning) will be implemented within the AP-HP infrastructure, notably for the construction of external control arms.