Titre : Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder

Stéphanie Allassonnière is a professor in applied mathematics at the School of Medicine, University of Paris, PR[AI]RIE fellow and deputy director and  an associate Professor in the applied Mathematics department of Ecole Polytechnique. She manages master programs and masterclasses in AI in healthcare. Her researches deal with Statistical modelling, stochastic optimization, MCMC samplers and medical data analysis in order to propose decision support systems aiming at understanding diseases response to treatments, anticipating diagnosis and therapy follow-up.” She is co-founder of Sonio, a startup which provides a companion tool to support the practitioner in monitoring pregnancy, women's and children's health, and reassuring families.

Titre : Environnement, mobilité et santé : études à partir de données massives issues de capteurs embarqués et smartphones

Basile Chaix is a research director at Inserm. The Nemesis team that he coordinates, created at the start of the MobiliSense project funded by the European Research Council (ERC) in 2015, examines how life environments influence health, explores the impact of transport on health (benefits and exposures associated with the different modes), and study the health effects of heat waves inside and outside the urban heat island. This work is interested in the dynamics of exposure, behavior, and health status in space and time based on fine-grained space-time referenced data. The different projects rely on a monitoring of participants with wearable sensors of location, behavior, environmental exposures, and health, and with the Eco-emo tracker smartphone application developed by the team.

Atelier/Formation « IA et R » : Tidymodels workshop

Hannah Frick is a software engineer and statistician on the tidymodels team at RStudio. The tidymodels framework is a collection of packages for modeling and machine learning using tidyverse principles. She holds a PhD in statistics from the Universitaet Innsbruck and has worked in data science consultancy as well as interdisciplinary research at University College London in cooperation with Team GB Hockey.

 Titre : What deep learning in histology can bring to clinical trials design

After a PhD in dependence networks inference and a postdoc on the study of the human gut microbiota, Raphaëlle Momal joined Owkin where she currently works on the benefits of covariate adjustment for clinical trials design, as well as gene regulatory network inference from single-cell transcriptomic data.

Titre : Inferring causality from a mixture of observations and interventions

G. Nuel is a senior CNRS researcher of the Institute of Mathematics (INSMI) working in Laboratory of Probability, Statistics and Modeling (LPSM, CNRS 8001) at Sorbonne Université. Since 2018, G. Nuel is the head of the Stochastics and Biology Group. Throughout his career, G. Nuel has developed a genuine interest for biomedical applications in probability and statistics based on his strong theoretical background in mathematics. He is an expert in computational statistics (simulations, the expectation-maximization algorithm, Markov chain Monte Carlo techniques, etc.) and models with latent variables (Markov chains, hidden Markov models, Bayesian networks, etc.). He has a great interest for applications in bioinformatics, statistical genetics, cancer epidemiology, tropical diseases, and clinical research.

Titre : Analyzing transcriptomics data for understanding and predicting vaccine response in clinical trials

Rodolphe Thiebaut is professor of Public Health and Biostatistics at the University of Bordeaux. He is the director of the Department of Research in Public Health at the university and the department of medical information at the hospital. He is leading an Inserm/Inria research group (Statistics In Systems and Translational Medicine SISTM) devoted to statistical development applied to immunology and vaccinology. His research includes the inference and control with ODE based models, supervised and unsupervised statistical learning using longitudinal high dimensional (n<p) data. He is also leading the Graduate’s program Digital Public Health that includes a Master in Public Health data science.