Biography
Lei is affiliated with the "AI for Healthcare'' CHI Lab led by Prof David Clifton, and currently leads a group of 3-4 researchers in the Nuffield Department of Population Health. She also leads analytical work in the Pandemic Science Institute on effective pandemic preparedness and response. Lei is a senior advisor of the NIHR Research Support Service team, which provides free advice on research design to researchers.
Lei was awarded a PhD in Statistical Machine Learning in 2007 from UMIST (now the University of Manchester), and subsequently worked as a post-doctoral researcher and then a medical statistician in the University of Oxford. She enjoys painting watercolours and playing violin, both amateurishly, in her spare time.
Other Information
Statistical and machine learning expertise in large-scale clinical records.
Most Recent Publications
When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
The FAIR Case for A Coherent Interoperability to support NHS 10 Year Health Plan
The FAIR Case for A Coherent Interoperability to support NHS 10 Year Health Plan
Development and validation of a multimodal artificial intelligence-based model for predicting post-prostatectomy treatment outcomes from baseline biparametric prostate magnetic resonance imaging
Development and validation of a multimodal artificial intelligence-based model for predicting post-prostatectomy treatment outcomes from baseline biparametric prostate magnetic resonance imaging
Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
Assessing the Importance of Variation in Diagnostic Coding Among the Three Countries in the UK Biobank
Assessing the Importance of Variation in Diagnostic Coding Among the Three Countries in the UK Biobank
Research Interests
Lei's research interests are in the field of medical statistics and AI, for large-scale observational studies and electronic health records.
Most Recent Publications
When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
The FAIR Case for A Coherent Interoperability to support NHS 10 Year Health Plan
The FAIR Case for A Coherent Interoperability to support NHS 10 Year Health Plan
Development and validation of a multimodal artificial intelligence-based model for predicting post-prostatectomy treatment outcomes from baseline biparametric prostate magnetic resonance imaging
Development and validation of a multimodal artificial intelligence-based model for predicting post-prostatectomy treatment outcomes from baseline biparametric prostate magnetic resonance imaging
Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
Assessing the Importance of Variation in Diagnostic Coding Among the Three Countries in the UK Biobank
Assessing the Importance of Variation in Diagnostic Coding Among the Three Countries in the UK Biobank
