Rechercher
Results
-
Interpret
We build explainable AI methods that uncover the biological and spatial drivers behind AI model predictions, enabling discovery of biological mechanisms, and spatial biomarkers that can be pursued for validation and therapeutic targeting. In the Interpret theme, we develop AI methods that provide ex
-
CHORUS: enhancing secure biomedical data access
CHORUS, a secure processing environment developed at CHUV, enables reliable sharing of biomedical data and collaboration among research teams. By combining advanced encryption with rigorous authentication protocols, CHORUS promotes biomedical innovation while protecting sensitive patient information
-
Comparative analysis of genomic methods for identifying genetic variants in actionable pharmacogenes
We evaluate genotyping versus low-coverage whole-genome sequencing for detecting variants in pharmacogenes, to identify the most reliable method for clinical use and inform standardized genome-based protocols to prevent adverse drug reactions. This research project aims to advance personalized medic
-
Integrating somatic and germline variation for the prediction of chronic kidney disease
This project aims to develop a comprehensive prediction model for chronic kidney disease by integrating classical risk factors with inherited and acquired genetic data. To do so we will use the cutting-edge Blended Genome–Exome sequencing technology on DNA samples from the Swiss HIV Cohort Study, as
-
ImCORE Germline Genomics initiative - iGGi
An international project aiming to establish the role of germline DNA variation in determining the efficacy and toxicity of cancer immunotherapy. We analyze the DNA of patients undergoing immunotherapy to identify biomarkers that can help predict the efficacy and toxicity of these treatments. An imp
-
MOOVE-CHUV: improving medical AI with real‑world clinical insights
We have developed Meditron-CHUV, an open-source medical Large Language Model, fine-tuned on more than 12,000 clinician preference annotations from over 250 CHUV clinicians. We introduce a clinician-centric framework that positions human expert participation as a central pillar of LLM development and
-
MED.USE : Medical large language model for reducing resource overuse in the emergency department
We develop a decision-support system based on a medical language model, capable of processing commonly available information and providing recommendations to emergency department clinicians, with the goal of reducing low-value care. This project, funded by the Swiss National Science Foundation, aims
-
SYNTHIA: synthetic data generation framework for healthcare applications
This project aims to promote the responsible use of synthetic data in health research and innovation. It addresses challenges related to data confidentiality and complexity through innovative techniques for generating multimodal and longitudinal datasets. The open platform SYNTHIA will provide valid
-
Sustainable COVID-19 Vaccination for Long-term Immunity and Effectiveness
We take part in the European SOLVE project, which aims to develop advanced vaccine technologies for stronger and longer-lasting protection against COVID-19. Within this project, our team builds and maintains a system for managing and analyzing high-dimensional data generated during vaccine trials. W
-
Creating a spatially-resolved omics reference database in oncology
We are part of the MOSAIC consortium, which aims to build the largest reference dataset in spatial omics for oncology. This dataset will help uncover treatment resistance mechanisms and improve patient stratification, ultimately paving the way for the discovery and development of personalized therap