I'm an Associate Professor in Health Data Science at the
Leeds Institute of Health Sciences, University of Leeds.
My research aims to improve the healthcare system by
using electronic healthcare records (GP and hospital data) to improve the way decisions are made throughout the NHS.
I do this using statistics, machine learning, and high-performance computing.
I focus on improving treatment via better prediction of
patient outcomes, and optimizing healthcare service provision. Though I work across a range of clinical areas,
much of my work involves multimorbidity, healthy ageing,
and the interface between physical and mental health.
I specialise in longitudinal data analysis (looking for changes over time) and methods that are alternatives to randomised control trials.
Throughout all my research, I aim to produce high-quality evidence which makes good use of taxpayer funds to optimise healthcare provision and improve the lives of people across the world.
I was previously a Postdoctoral Research Assistant at Manchester University specializing in Numerical Linear Algebra.
My research was previously in High Performance Computing (HPC). As part of the NLAFET project (funded through Horizon 2020) we aimed to deliver a linear algebra library capable of exascale performance on distributed, heterogeneous architectures.
This involved parallel computing using GPUs, Xeon Phis, and other accelerators combined with traditional multi-core parallellism and MPI. The project also aims to make advances in offline (and online) autotuning, algorithm-based fault tolerance, and other issues related to modern HPC.
Much of this work was around parallel computing of matrix multiplication, a key task underpinning most of statistics and machine learning. The algorithms we designed are currently used within Intel, NVIDIA, and ARM chips billions of times per day.
Before that my research was focused on matrix functions - a generalization of functions like the exponential and logarithm to square matrices that retains their useful properties. I'm interested in all aspects of such functions, from theoretical properties and algorithm design to discovering new applications and computer programming. Some of my algorithms have been incorporated in the NAG and SciPy libraries.