Lei Clifton
Official Fellow in AI & ML, Reuben College
Statistics and AI for clinical studies
My research interest is at the interface of medical statistics and AI, with over 20 years of research experience.
I am the Programme Director of the MSc in Applied Digital Health, where I am also module leader and lecturer, working alongside the Academic Directors, Profs. John Powell and Catherine Pope.
My research focuses on a wide range of methodology, including foundation models (and large language models) for healthcare, disease prediction, and the fusion of AI with medical statistics. Much of this work collaborates closely with the "AI for Healthcare" group in the Department of Engineering Science, where I also hold an affiliation.
After studying engineering and machine learning, I did my postdoctoral training at the Department of Engineering Science (2009-14), before training as a medical statistician under Prof. Doug Altman at the Centre for Statistics in Medicine (2014-18). Subsequently, I was team leader in the Nuffield Department of Population Health (2019-24), where I led a programme of research in translational epidemiology.
When at home, I can be found painting watercolours, practising yoga, and making noise on the violin with friends.
Recent publications
-
Dysregulated Immune Proteins in Plasma in the UK Biobank Predict Multiple Myeloma 12 years Before Clinical Diagnosis
Preprint
Fieggen J. et al, (2025)
-
Aligning, Autoencoding and Prompting Large Language Models for Novel Disease Reporting
Journal article
Liu F. et al, (2025), IEEE Transactions on Pattern Analysis and Machine Intelligence
-
Exploring the effectiveness of instruction tuning in biomedical language processing
Journal article
Rohanian O. et al, (2024), Artificial Intelligence in Medicine, 158
-
Are Time Series Foundation Models Ready for Vital Sign Forecasting in Healthcare?
Conference paper
Gu X. et al, (2024), Proceedings of Machine Learning Research, 259, 401 - 419
-
Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark
Conference paper
Liu F. et al, (2024), EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, 13696 - 13710
Collaborators
-
John Powell
Professor of Digital Health
-
Catherine Pope
Professor of Medical Sociology
-
Andrew Farmer
Professor of General Practice
-
Lionel Tarassenko
Department of Engineering Science, University of Oxford