ASTRODEM: using astrophysics to close the ‘diagnosis gap’ for dementia in UK general practice

Dementia is one of the greatest public health challenges of our era. Timely diagnosis allows patients to benefit from current therapies, plan for the future and maximise their quality of life. However, there is a ‘diagnosis gap’ in UK general practice, with less than two-thirds of expected patients receiving a dementia diagnosis. Increasing diagnosis rates is a strategic aim of the UK government and NHS.

We aim to close this diagnosis gap in a novel collaboration between primary care epidemiology and astrophysics. We will use a very large set of electronic patient records (96,000 patients; 50% with dementia) spanning up to ten years per patient. We will use a probabilistic programming framework to apply statistical techniques to model dementia onset in this cohort, allowing for the inherent variability and duration of disease development. To achieve a clinically valuable model, these multi-dimensional data will require sophisticated analysis techniques that are not currently available in medical statistics and epidemiology, but which astrophysicists use daily. 

Our goal is to develop a statistical model to predict risk of dementia from patients’ GP records, which will help GPs and other NHS bodies better estimate and identify cases of dementia in the UK.