Current Fellows

David Hughes

Approximation Approaches for Efficient Clinical Predictions
High-dimensional data is now routinely collected in many settings, due to the number of different variables being measured on a subject, the number of times a variable is measured and the number of individuals in a study. This data can be used for screening patients to determine their risk of disease, or to classify patients into risk groups.
In the machine learning literature variational Bayes approximation methods have been shown to give fast and accurate estimates of model parameters in a variety of settings.
My proposal is to derive a mean-field variational Bayes (MFVB) approach to estimating joint models for multiple longitudinal biomarkers of different types and time-to-event data. Making it practicable to fit such models in a reasonable time frame, will allow personalised risk-prediction and diagnostics to be performed in real-time.
This project will be at the interface of statistics and computer science with significant statistical, methodological, and computational components.

Maya Wardeh

Data approaches to identifying potential sources of emerging pathogens in humans, domesticated animals and crops
Ecological networks, in which nodes represent species and links illustrate different interactions between those species, have been used to model and investigate a spectrum of important phenomena. In ecological multi-host networks, nodes are host species linked through sharing of pathogens. The relative importance of nodes can be quantified using centrality measures. Central hosts act as interspecies super-spreaders, and their identification is important for developing surveillance protocols and interventions aimed at preventing future disease emergence in populations of humans, their domesticated animals or crops. Link prediction models which take into account the typology of observed interactions networks and evolutionary relationships between hosts can be used to predict missing links between hosts and pathogens. Missing links indicate future emerging pathogens or undocumented interactions between host and pathogen species. Developing the various components of this project requires combining skills in programming, data mining and management (in order to mine the information required to build the networks), with mathematical and statistical skills (for network analysis, and prediction of missing links), underpinned by understanding of evolutionary relationships between species (for link prediction model parametrisation and interpretation). This project will be at the interface of data science and network analysis, with statistical components.

Open Days for Candidates

15th & 26th March 2018

Applications Close

21st May 2018


8th & 12th June 2018

Start the Fellowship

June 2018 - March 2019