Handling heterogeneity in the analysis of biomedical information

2021 AI4Health practical session

This session focuses on the problem of statistical analysis of heterogeneous data in biomedical studies. Through guided examples, we will first introduce the basics of latent variable modelling for the joint analysis of heterogeneous data types (such as imaging, clinical or biological measurements). We will initially focus on linear approaches, such as partial least squares and canonical correlation analysis. We will then present more flexible methods based on recent advances in deep learning and stochastic variational inference, such as the multi-channel variational autoencoder. We will finally address the problem of deploying latent variable models for federated learning in multi-centric studies, where models must account for data-privacy and heterogeneity across datasets.

Material usage

Herein you will find the material that will be developed during the practical session. Some of the material corresponds to text and images that you can download in the upper right corner

Launch my notebooks

You can have an environment for yourself by clicking here: Binder