The Predictive Clinical Neuroscience group at the Donders Institute and RadboudUMC aims to use artificial intelligence and big data neuroimaging to change the way people think about psychiatric disorders. We develop statistical and machine learning techniques to predict and stratify brain disorders and to understand their underlying neurobiological mechanisms on the basis of neuroimaging data. We focus both on supervised techniques for predicting clinical variables as well as unsupervised approaches for stratifying clinical groups on the basis of the underlying biology. Specific methodological techniques of interest include:
- Bayesian non-parameteric methods for pattern classification and regression
- Normative modelling approaches for modelling variation in clinical cohorts
- Spatial statistical methods (e.g. continuous stochastic processes, point processes)
- Neural network and deep learning models
- Kernel and regularization methods for high-dimensional data
- Multivariate statistical methods for finding associations between datasets
- Markov chain Monte Carlo methods for inference in probabilistic models
- Multi-output, multi-task and structured output learning methods
While the methods we develop have applications in many clinical settings, we have a particularly strong focus on psychiatric and neurological disorders.
Predictive Clinical Neuroscience Lab 