Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.


Understanding the impact and implications of multiple long-term conditions and pregnancy using artificial intelligence applied to electronic health records


More and more people are living with two or more long-term health conditions. Some people may experience difficulties managing several long-term health conditions. They may have to coordinate appointments with different specialists and their medications need to be managed carefully.

During pregnancy, these challenges may increase. We know that it is becoming more common for women to have two or more long-term health conditions before pregnancy, but we don’t understand why this is and what the consequences are for mothers and babies. Without this deeper understanding of the problem, women with several long-term health conditions may not have the best experience of care before, during and after pregnancy because services are not tailored to their specific needs.

As part of a national multi-university collaboration called MuM-PreDiCT (, we are studying and improving maternity care for women who are also managing two or more long-term health conditions. These can be both physical conditions, such as diabetes and raised blood pressure, and mental health conditions such as depression and anxiety. The project utilises electronic health data resources from across the UK covering millions of individuals.

The purpose of the project is to develop artificial intelligence-based analysis tools to provide automated approaches for developing data-driven clinical decision support tools. The research will involve deep theoretical and methodological research into models of retrospective observational data collections (e.g. structural causal modelling) and the translation of these insights into applied analysis tools to answer a range of clinical questions which are often missed out in women’s health as the affected populations are small or conditions are rare.


The student will have access to a UK wide network of academic and clinical researchers as well as an extensive public-patient involvement and engagement network.

There will be opportunities to develop both theoretical and applied computational modelling skills principally in the areas of Bayesian Statistics, Causal Inference, and implementations using modern deep learning technologies.

The university also provides a wide-range of training opportunities.


Applicants interested in this opportunity may apply for an external funding award via Health Data Research UK:


To apply for this research degree, please click here.