Search for a funded project
AI-Enhanced Monitoring Solutions for Anesthetized Patients – Anesth-IA
General anesthesia, although routine with 12 million cases annually in France and 300 million worldwide, presents challenges. 15-25% of patients undergo post-operative complications, increasing post-operative mortality, neurocognitive disorders, and burdening healthcare systems. Intra-operative hypo
Data Access, Transparency of Algorithms and (data subject) Rights – DATARights
Online platforms play a growing role in the circulation of information and in the production of power asymetries in surveillance capitalism. Accessing the data that is necessary to study them is, however, no easy task, given that these platforms often function as closed black-boxes. Several recent s
CITADEL: PrivaCy and bIas mitigation in federaTed leArning for Digital hEaLth – CITADEL
Federated learning (FL) is a promising paradigm that is gaining grip in the context of privacy-preserving machine learning for edge computing systems. Thanks to FL, several data owners called clients (e.g., organizations in cross-silo FL) can collaboratively train a model on their private data, wit
Seeing the EpileptogenIc Zone through machine learning on strUctuRal, functional and clinical nEurological data – SEIZURE
Epilepsy is resistant to antiepileptic drugs for 30% of patients. For those patients, surgical resection of the brain epileptogenic zone (EZ) is the best option. No biomarker allows to perfectly detect the EZ and surgical outcome is not a trivial task. Recent progress in statistical image processing
Prediction of cerebral injury secondary to endovascular recanalization of acute ischemic stroke – PRECISE-STROKE
Acute Brain Infarction complicating large vessel occlusion (LVO-AIS) are one of the first causes of neurological dependency and death in Europe. Their incidence is expected to increase by 20% in the next 10 years. Endovascular recanalisation (EVT) has revolutionized their management. It was initiall
Cathepsin O and intracranial aneurysm – COCA
Intracranial aneurysm (IA) is a cerebrovascular abnormality characterized by localized dilation and thinning of the wall of a cerebral artery affecting 3% of the population. IA is generally silent and its devastating complication is its unpredictable rupture, resulting in subarachnoid hemorrhage, fa
Physiologic and molecular determinant of brain susceptibility to reward- and metabolic-based diseases – BrainHealth
Obesity has reached a pandemic level and there is an urge to identify vulnerability/protective factors. Evidence support that obesity results from an interaction between genes and food environment. the TaqI A1 single nucleotide polymorphism is widely present in the population and has been identified
General pUrpose dIalogue-based DigitAl iNformation acCEss – GUIDANCE
- How to design new LLMs or re-use LLMs for DbIA; - How to leverage retrieval-Enhanced Machine Learning (ReML) techniques to improve the accuracy and efficiency of information retrieval systems; - Adapt LLMs and develop new architectures (for DbIA models) to deal with low resource and domain adapt
Checking Image Integrity for Anticipating Influence Attacks – CI2(IA)
The CI2(AI) project is part of a context marked by the proliferation of deepfakes and fake news. Its main objectives are: • Verify the integrity of visual content: Determine whether a media file is a deepfake and whether it has malicious intent. • Improve the generalization of detectors: Use domai
