I am a biostatistician and informatician working with large-scale electronic medical records databases. I conduct primary research in this area and I build software to facilitate quantitative medical research.
In particular I am interested in using big datasets to address important medical and biological questions. To achieve this I use a combination of programming, multilevel statistics, machine learning, simulation, text and data mining.
My work includes:
- Investigating the validity of electronic medical records databases for assessing the effectiveness of treatments and interventions in primary care.
- Examining the effect of pay-for-performance (The UK Quality and Outcomes framework) for general-practitioners on care received by individual patients.
- Maintaining the http://www.clinicalcodes.org repository for clinical code lists to improve data sharing and reproducibility in healthcare research.
- Producing open-source software to help researchers to analyse medical data (https://github.com/rOpenHealth).