Seminar : Supervised and Unsupervised Methods for Modelling Trajectories through the Disease Process

Allan TUCKER de l'Université Brunel de Londres, en visite dans l'équipe SDC fera un séminaire ouvert à tous le mardi 30 janvier 2018 à 10h00 en salle A302 du pôle API à Illkirch. Plan

Titre : Supervised and Unsupervised Methods for Modelling Trajectories through the Disease Process

Abstract : In this talk I will explore issues with different methods for collecting and modelling clinical data. I will briefly discuss the advantages and disadvantages of cross-sectional and longitudinal studies, and the modelling of these types of data with the chief aim of forecasting disease progression whilst discovering subclasses of disease based on temporal aspects: This will include novel algorithms for identifying disease subclasses based upon different disease trajectories and disease subclasses based upon different disease dynamics where the process is inherently non-stationary. Finally, I will explore methods for integrating both cross-sectional and longitudinal data into probabilistic models that lever the advantages of both.

Bio : Allan TUCKER (Brunel University London) has worked with multivariate time series data for over 20 years. His PhD involved the use of dynamic probabilistic graphical models to explain processes in large time-series data. Since then, he has worked with health data (clinical), environmental data (botany & marine biology scientific survey data), and biological data (omic data using network models). Much of his work has explored the use of latent variables within state-space models including hidden Markov models, dynamic Bayesian networks, and their variations. He also developed a method that incorporates resampling and graph theory to build trajectories through disease processes. Currently,he is exploring the use of latent variables to assist in the identification of regime shifts in oceanic food web structures and temporal phenotypes in diabetes.