I am a UKRI Innovation Fellow funded by Health Data Research UK. I work closely with clinical collaborators across King’s Health Partners applying machine learning to patient records at scale. My research develops machine learning methods based on knowledge graphs that combine large public datasets with health records to predict and explain patient outcomes. The focus is on delivering real world clinical value through multiple clinical collaborations including atrial fibrillation management, patient flow, adverse drug reactions, cancer subtyping and kidney failure. I did my PhD at Cambridge University where I worked on applying systems biology methods to neurodegenerative disease, then I joined the Dobson group in 2016 as a postdoctoral research fellow in the NIHR Maudsley BRC.
Using knowledge graphs to improve machine learning performance; Putting machine learning into clinical practice with explainability and real-time support; Natural language processing methods for clinical text; Modelling patient trajectories.
- Bleeding in cardiac patients prescribed antithrombotic drugs: electronic health record phenotyping algorithms, incidence, trends and prognosis
- Semantic computational analysis of anticoagulation use in atrial fibrillation from real world data
- Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records
- A patient flow simulator for healthcare management education
- Network analysis of patient flow in two UK acute care hospitals identifies key sub-networks for A&E performance