Professor of Artificial Intelligence
I am Professor of Artificial Intelligence based at the Big Data Institute in Oxford working across the Nuffield Department of Women's and Reproductive Health and the Nuffield Department of Population Health. I am a Turing AI Fellow and my research is support by a UKRI/EPSRC Turing AI Acceleration Fellowship. Outside of Oxford, I am also a PhD Programme Director at Health Data Research UK, leading the Health Data Research UK-Turing Wellcome PhD programme in Health Data Science.
I studied undergraduate Engineering at Cambridge where I did my masters dissertation with Professor Andrew Blake at Microsoft Research on digital image analysis. Afterwards, I joined the EPSRC-funded Life Sciences Interface Doctoral Training Centre, led by Professor David Gavaghan in Oxford where I completed my doctoral thesis in Statistics under the supervision of Professor Chris Holmes.
I subsequently took up MRC Fellowship in Biomedical Informatics before joining Imperial College London as a Lecturer in Statistics in the Department of Mathematics. I rejoined Oxford where I became Associate Professor in Genomic Medicine as a Principal Investigator at the Wellcome Trust Centre for Human Genetics. I then became Professor of Artificial Intelligence at the Universities of Birmingham and Manchester prior to rejoining Oxford.
I currently sit on the MRC Better Methods, Better Research Panel, the Molecular & Cellular Medicine Board and the Centenary Prize Award Committee. I also lead the Machine Learning sub-domain for the Genomics England Clinical Interpretation Partnership in Quantitative Methods, Functional Genomics and Machine Learning.
A major part of my research is focused on issues related to the interpretation of high-dimensional data arising from modern molecular technologies and health systems and how such data can be used to give insights into the molecular basis of human disease particularly cancer. My efforts in this area span a spectrum of areas from core statistical and machine learning methodological research to wet lab-based experimental investigations to translational clinical research. I have significant ongoing collaborations with Professor Ahmed Ahmed in Ovarian Cancer.
Real-world data modelling
The group is part of two major UK consortia MUM-PREDICT and OPTIMAL. Both projects seek to use routinely collected healthcare records to predict health trajectories in individuals suffering from multiple long-term conditions. In MUM-PREDICT, we will specifically looking at conditions linked to pregnancy, while OPTIMAL will examine more general populations.
Artificial intelligence guidelines and practice
I collaborate with the CONSORT/SPIRIT-AI consortium and the MHRA to develop guidelines and best practice information for the development of AI-based medical devices.
Joining my group
If you wish to find out more about joining or working with my research group as a PhD student, Postdoc or collaborator, see the Research Group website.
An atlas of genetic scores to predict multi-omic traits.
Xu Y. et al, (2023), Nature, 616, 123 - 131
Maternal and child outcomes for pregnant women with pre-existing multiple long-term conditions: protocol for an observational study in the UK.
Lee SI. et al, (2023), BMJ Open, 13
Polypharmacy during pregnancy and associated risk factors: a retrospective analysis of 577 medication exposures among 1.5 million pregnancies in the UK, 2000-2019.
Subramanian A. et al, (2023), BMC Med, 21
Epidemiology of pre-existing multimorbidity in pregnant women in the UK in 2018: a population-based cross-sectional study.
Lee SI. et al, (2022), BMC pregnancy and childbirth, 22
Patient Derived Organoids Confirm That PI3K/AKT Signalling Is an Escape Pathway for Radioresistance and a Target for Therapy in Rectal Cancer.
Wanigasooriya K. et al, (2022), Frontiers in oncology, 12