FINAL NewMind Ltogo.png (1)

Unlocking evidence from electronic patient records

Unlocking the evidence from electronic patient records for smart intervention of mental health disorders - a case study in Alzheimer’s Disease

Led by Dr Chi-Hun Kim, University of Oxford in association with University of Manchester & DeepCognito Ltd

Alzheimer disease (AD) is the most common causes of dementia that affects an estimated 850,000 people in the UK. Given the lack of cure for AD and accelerated ageing of the population, AD has become one of the biggest health burdens in the world. Large scale electronic patient records (EPRs) collected from the daily clinical practice may provide novel perspectives on the care and treatment of AD. The goal of the feasibility funding is to build a learning platform that will use both structured and free text EPR data by focusing on particular drugs and their impacts on AD patients. As recent studies suggested strong genetic links between inflammation and AD, we seek seed funding to pilot extraction of anti-inflammatory drugs and AD severity indicators and to analyse these at population level. We will develop and validate our text mining (TM) algorithms using the Oxford UK-CRIS database as a test-bed: a de-identified EPR database from a mental health NHS trust in Oxfordshire with 100,000 patient records.

Presentation from the Stage 1 Update Workshop, November 2017.