Chairs | AI for Health

• Medical Data Lab (UCA Idex) 
• Health Data Hub, EDS APHP 
• International databases 
• Security, privacy, GDPR 
• In collaboration with other 3IA institutes 

• Neuronal level: spiking models to better understand neuronal dynamics 
• Cognition: neuronal dynamics for the analysis of learning/perception/action sequences 
• Simulation/electronics: brain models to provide new neuromorphic-biomimetic algorithms/architectures 

AI for e-patients and e-medicine
(AI for Integrative Computational Medicine)
Since 2019

We design and exploit modern AI methods: (i) to personalize the parameters of advanced models of the e-patient, (ii) to drive e-medicine algorithms on personalized e-patients (i.e. digital twins) for automated diagnosis, prognosis and therapy, in an efficient, robust, safe and explainable manner.

Human Lung Atlas
(AI for Computational Biology and Bio-inspired AI)
Since 2020

The project elaborates on state-of-the-art approaches in genomics and cell biology to describe complex biological samples at the single-cell resolution. Multidimensional biological experiments result in large scale descriptions of DNA, RNA and protein expressions that can be integrated in time and space. The project aims at: (1) developing novel data-mining approaches based on machine learning and AI; (2) apply them to the study of the normal and pathological lung, in the context of serious threats that touch this organ (COVID-19, asthma, cystic fibrosis, cancer,...).

Imaging for biology
(AI for Computational Biology and Bio-inspired AI)
Since 2019

Recent advances in microscope technology provide outstanding images that allow biologists to address fundamental questions. This project aims at developing new AI methods and algorithms for (i) novel acquisition setups for super resolution imaging, and (ii) extraction of valuable quantitative information from these large heterogeneous datasets. 

Video analytics for human behavior understanding
(AI for Integrative Computational Medicine)
Since 2019

Video analytics enables us to measure objectively the behavior of humans by recognizing their everyday activities, their emotion, eating habits and lifestyle. Human behavior can be modeled by learning from a large quantity of data from a variety of sensors to improve and optimize, for instance, the quality of life of people suffering from behavior disorders. 

AIMS: Artificial intelligence for molecular studies
(AI for Computational Biology and Bio-inspired AI)
Since 2019

By learning essential features of proteins and their complexes, we shall deliver biologically relevant information for large molecular systems on biologically relevant time scales, leveraging our understanding of biological functions at the atomic level, and providing key inputs for protein design and engineering, and protein interaction networks. 

Joint biological and imaging biomarkers in oncology
(AI for Integrative Computational Medicine)
Since 2019

We exploit joint information from imaging and biological data to improve the diagnosis and treatment planning, focusing on lung cancer. This approach relies on methods involving unsupervised deep learning, uncertainty quantification, sparse Bayesian feature selection and the handling of confounding factors.

Comprehensive omics profiling for precision medicine in Oncology
(AI for Integrative Computational Medicine)
Since 2019

I am combining various patient extracted “omics” data, including multimodal imaging features, for integrative and data-driven computational medicine. I focus on challenging fields in oncology such as (i) radiogenomics and outcome-focused research in metastatic breast cancer and (ii) the accurate prediction of response to immunotherapy. 

AI and biophysical models for computational cardiology
(AI for Integrative Computational Medicine)
Since 2019

The application of AI in healthcare is challenging due to its lack of robustness and explainability. This project aims to introduce physiological priors in AI through biophysical models. This can be done by reformulating problems through such models, by learning spatiotemporal dynamics from biophysics or by augmenting features and data with such simulations.

Global approach to research, development, and global deployment of digital solutions in surgery, with osteoarticular surgery and traumatology as a use case
(AI for Integrative Computational Medicine)
Since 2024

The theme developed by Dr. Gauci revolves around computational and augmented medicine & surgery using artificial intelligence tools and the reuse of healthcare data.
Digital surgery merges two complementary aspects:

• Computational surgery, which is fed by patient and imaging data, enabling the creation of 3D/4D geometric and biomechanical models to simulate and plan surgery before it is performed.
• Augmented surgery, which is based on a more or less complex digital model and enables planning to be applied using intraoperative assistance and guidance tools such as 3D printing (model, instrumentation, implant), navigation, robotics or mixed reality including collaborative cloud platform.

Assessing the clinical relevance of these digital solutions alone is not enough to demonstrate their usability and interest in a complex environment such as the operating room or interventional procedure room. The development of models adapted to surgical needs, and the analysis of multiparametric data derived from the use of these models' application tools, should enable us to optimize the integration of these tools in the operating room and in daily practice. Several technology platforms have been set up for experimental and clinical validation such as augmented operating room.

Decoding complex interactomes of macromolecules
(AI for Computational Biology and Bio-inspired AI)
Since 2025

This project aims to decode complex interactomes using AI-based tools that integrate quantitative biochemical data with advanced computational modeling. Building on recent breakthroughs in affinity interactomics —which can measure millions of affinities of macromolecular interactions— the project seeks to overcome current limitations in interpreting large-scale interaction networks. By developing novel AI-driven methods, Gergo's team will identify recurring short linear motifs, infer hidden network topologies, and predict binding affinities of experimentally so-far uncharted interactions, particularly within intrinsically disordered regions often implicated in cancer. Combining experimental data generation and machine learning, this interdisciplinary effort will reveal how mutations rewire cellular signaling, uncover novel cancer driver mechanisms, and establish a new paradigm for quantitative systems biochemistry at the interface of interactomics and artificial intelligence.

Applications of AI for patients with vascular diseases
(AI for Integrative Computational Medicine)
Since 2021

Our team develops AI-based applications for patients with vascular diseases We aim to create decision support systems to enhance evidence-based and precision medicine through a translational approach including the identification of biomarkers, the automation of vascular imaging analysis, and the development of predictive models Our group is strongly involved in federating national databases and European vascular registries to promote international research for patients with vascular diseases.