Advanced Computational Modelling for the Differential Diagnosis of Dementia Lead Investigator: Felicity Guest Institution : University of Exeter E-Mail : fg248@exeter.ac.uk Proposal ID : 688 Proposal Description: This data-driven project will explore the use of advanced quantitative analysis to develop a ???disease signature??? of each dementia subtype in order to assist clinicians in memory clinics during the diagnostic assessment. A combination of advanced computational machine learning techniques will be employed and the resulting model will inform the debate about the optimal diagnostic categories. It could also be developed into a computerised clinical decision support system. The specific goals of the project are as follows: 1. Develop and validate a computational model that profiles heterogeneous dementia disease signatures. 2. Extend this model by predicting two year conversion to dementia in patients free from dementia at the initial assessment. In summary, this project aims to address a critical barrier to progress in dementia research and develop a novel approach to the problematic task of accurately diagnosing dementia. Please Note: We are collaborating with Professor Andrew Zhou on this project.