Summary
Since December 2001, I have been a research statistician at the Medical Research Council Biostatistics Unit in Cambridge, becoming an MRC Investigator (Programme Leader) in 2017. Prior to this I worked as a consulting statistician and project statistician within the (now defunct) University of Cambridge Department of Public Health and Primary Care’s Centre for Applied Medical Statistics (CAMS) (1997-2000) and Epidemiology for Policy Group (2000-2001) respectively. I currently lead the Stratified Medicine Initiative at the Unit. Prior to this I worked within Professor Vern Farewell’s programme for “Statistical Modelling: theory and applications” which deals with methods of statistical inference for challenging data structures. However, I also collaborate with other senior scientists (present and former) in the Unit, in particular Professor Sheila Bird, Dr Daniela De Angelis, Professor Wally Gilks and Professor Carlo Berzuini.
BSU Research Overview
Stratified medicine, where “homogeneous” groups of people likely to respond similarly to treatment or have similar underlying disease mechanism or outcome risk are sought based on molecular (biomarker) information, is a first step towards reducing biological variability and lies within the continuum of “patient therapy”, in which empirical or “all comer” medicine sits at one end and precision medicine at the other. The fact that genetic, molecular and imaging modalities have transformed biology from an observational science to a more data and computationally intensive quantitative science has meant that the need for those who are trained in handling data, accounting for uncertainty and making inference is ever more paramount. Many of the issues and challenges confronting stratified medicine are of a statistical nature.
We are undertaking a programme of research that encompasses risk stratification, prediction and validation, integrative and joint modelling of molecular and clinical data of various kinds and complexities (and their conversion into meaningful outputs that can inform health care decisions), mechanistic understanding and causality, treatment strategies and the design of innovative/purposeful clinical trials for biomarkers and dynamic treatment regimes.
Current Research Interests
- Causal Inference
- Chronic Disease Epidemiology (in particular related to Inflammatory Arthritis)
- Dynamic Graphical Modelling of Stochastic Processes
- Efficiency
- Modelling of Longitudinal and Correlated Data
- Multi-state Models and Survival Data
- Stratified Medicine
Selected Papers
- Yiu S, Farewell V T, Tom B D M. (2017) Clustered multi-state models with observation-level random effects, mover-stayer effects and dynamic covariates: modelling transition intensities and sojourn times in a study of psoriatic arthritis. Journal of the Royal Statistical Society Series C
- O'Keeffe A G, Farewell D M, Tom B D M & Farewell V T (2016) Multiple imputation of missing composite outcomes in longitudinal data. Statistics in Biosciences 8: 310-332
- Yiu S, Tom B D M & Farewell V T (2016) Trivariate mover-stayer counting process models for investigating joint damage in psoriatic arthritis. Statistics in Medicine 35: 5701-5716
- Farewell V T, Long D L, Tom B D M, Yiu S L & Su L (2017) Two-part and related regression models for longitudinal data. Annual Reviews of Statistics and its Applications 4: 283-315
- Yiu S & Tom B D M (2017) A joint modelling approach for multi-state processes subject to resolution and under intermittent observations. Statistics in Medicine 36: 496-508
- Yiu S, Farewell V T & Tom B D M (2017) Exploring the existence of a stayer population with mover-stayer counting process models: Application to joint damage in psoriatic arthritis. Journal of the Royal Statistical Society, Series C 66(4): 669-690
- Kassanjee R, De Angelis D, Farah M, Hanson D, Labuschagne P, Laeyendecker O, Le Vu S, Tom B, Wang R & Welte A (2017) Cross-sectional HIV incidence surveillance: A benchmarking of approaches for estimating the 'mean duration of recent infection'. Statistical Communications in Infectious Diseases 9(1): 20160002
- Huang Z, Muniz-Terrera G & Tom B D M (2017) Power analysis to detect treatment effects in longitudinal clinical trials for Alzheimer's disease. Alzheimer's & Dementia: Translational Research & Clinical Interventions 3(3): 360-366
- Yiu S & Tom B D M (2017) Two-part models with stochastic processes for modelling longitudinal semicontinuous data:computationally efficient inference and modelling the overall marginal mean. Statistical Methods in Medical Research : (Published Online)
