Explainable prediction modelling for early detection of risks in multiple long-term conditions using health records data

 Multiple Long-Term conditions (MLTC) are a major healthcare challenge associated with high service utilization and expenditure. In the project, the candidate will help develop robust and explainable AI methods for MLTC risk prediction. The research will use a healthcare database from Norfolk to access the health records that the supervisory team has access to. This project will aim to design, and implement novel deep learning algorithms for risk prediction modeling and early detection of high-risk MLTC.Some of the suggestive activities are as follows:

1. Pre-processing longitudinal electronic health records data

2. Design and development of explainable deep learning modeling approaches for MLTC risk prediction (e.g. Multistate and neural-controlled differential equation models)

3. Formulating methods for efficient explanations for longitudinal time-series models

4. Conduct testing, validation, and risk assessment of the developed AI to ensure the system works fairly for minority patient populations or protected groups of patients.

Applicants with a master's degree and experience in data science, machine learning, and artificial intelligence will be given priority. 

Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.