Introduction à l’apprentissage artificiel en santé

Par Jean-Daniel Zucker, IRD – UMMISCO

  • Introduction
  • Les types de problèmes d’apprentissage en santé et bio-informatique
  • Préparation des données : sélection de variables, imputation et outliers
  • Les tâches de classification
  • Les tâches de stratification (clustering)
  • Les méthodes de validations
  • Applications dans le domaine des maladies cardiométaboliques

Prof. Jean-Daniel Zucker got his PhD. in 1996 in Machine Learning from Paris 6 University where he became an associate professor. In 2002, he became Full Professor of Computer Science at Paris 13 University where he started a laboratory on Medical Informatics and Bioinformatics (LIM&BIO) in which he was heading a team on Prediction Analysis for Transcriptomics Data. In 2008 he became a Senior Researcher at the National institute of Research for development (IRD) on the themes of Data Mining and Decentralized AI for Complex Systems modeling. He is now the director of the Mathematical and Computer Modeling of Complex Systems Laboratory UMMISCO (IRD & University Paris 6) that counts 60 permanent staff in France, Vietnam, Morocco, Senegal and Cameroun. He is also heading the Bioinformatics team Karine Clément’s team (NutriOmics Nutrition and obesity systemic approaches) which has been involved in genetic and functional genomics aspects of human obesity. His research is focused on AI in finding approaches for the automatic
construction of predictive models (supervised learning) or characteristic model (unsupervised learning or “clustering”). His main field of application is today Metagenomics of the gut microbiota and contributed to several European Networks in genetics and functional genomics (Diogenes, METAHIT, METACARDIS, …). His research is developed through International collaboration with Vietnam, China, Taiwan, USA, Italy. He has been posted in Vietnam for five years. Total publications > 240.