About the Project
Location: UCL, London UK
Supervisors: Neil Oxtoby (Primary, CMIC/CS); Chris Hardy (Secondary, DRC/ND); Simon Cohn (Subsidiary, LSHTM); Daniel Alexander (Subsidiary, CMIC/CS); Sebastian Crutch (Subsidiary, DRC/ND)
UCL Centre for Medical Image Computing (CMIC), Department of Computer Science (CS);
UCL Dementia Research Centre (DRC), Department of Neurodegenerative Disease (ND);
London School of Hygiene and Tropical Medicine (LSHTM), Department of Health Services Research and Policy (HSRP)
Very little information is available about the order of appearance and rates of change for symptoms and care-related needs in the rarer dementias. When the “What next?” question is raised, people living with dementia (PLWD) and carers all too often receive responses such as “It is difficult to say” or “It affects everyone differently” — which are simultaneously true and completely unhelpful. Approximate guides to the stages of Alzheimer’s disease have been produced (e.g. Reisberg’s 7 stages of Alzheimer’s) but these are based on clinical experience, not quantitative data, and are not available for most rare, atypical or young-onset conditions.
The overarching goal of the project is to provide doctors, patients and families with tools to better plan for people’s future — finally answering the “What next?” question.
Data-driven quantitative approaches to understanding neurological disease progression emerged early in the last decade, benefitting from the availability of large medical data sets in neurodegenerative diseases such as Alzheimer’s disease, the most common cause of dementia. “Imaging Plus X” computational models are now a mature research field in their own right [Oxtoby2017; Khatami2019]. One of the original methods, the event-based model (EBM [Fonteijn2012; Young2014]), is a robust computational approach to describing disease progression without requiring a priori clinical staging and requiring only cross-sectional data.
EBMs have been applied across a range of neurological diseases including Alzheimer’s disease, Huntington’s disease, and Multiple Sclerosis, using biomarker-based events including regional atrophy (shrinkage) in the brain, levels of abnormal proteins in cerebrospinal fluid, and more recently in our EPSRC-funded work to measures of cognitive ability [Firth2019; Firth2020]. While this work has generated unique biomarker-based understanding of disease progression, it tells us very little about patient and carer experience. This project will address this gap by developing and applying data-driven computational modelling and machine learning techniques to self-report data from PLWD and their carers.
This project will focus on data from the rarer dementias including posterior cortical atrophy (PCA), primary progressive aphasia (PPA), and amnestic Alzheimer’s disease (AD). The rarer dementias are a particular strength of the UCL Dementia Research Centre in the Department of Neurodegenerative Disease. Data includes a semi-structured telephone-based retrospective cohort study of >1000 current and historical members. The project will also explore cross-linking this self-reporting data with available biomarker data from medical imaging, cognitive tests, and clinical assessment (>100 PLWD).
The approach taken in this project will be to apply computational models (e.g., EBMs and machine learning approaches) to learn the sequence and timing of self-reported symptoms, changes in activities of daily living, evolving care-related events and needs. Developing and applying these approaches are particular strengths of the UCL Centre for Medical Image Computing in the Department of Computer Science.
Results from the computational analyses in this project will be compared and contrasted with the co-created, consensus-based “Stages of PPA/PCA/AD” frameworks developed with support group members. The output will be a tool for providing healthcare professionals with data-driven predictions on the clinical trajectory of different dementias. This project will investigate how this information could be useful to caregivers for making timely preparations for care needs. There is also the unique possibility to explore deployment of such a tool in a clinical scenario to augment broader efforts on rare dementia support at the DRC (www.raredementiasupport.org).
The ideal candidate will have a strong enthusiasm for developing and applying data-driven solutions to advance healthcare, particularly in Neurology. This could be a computational scientist with medical application interests, or a medical scientist with computational methods interest. Some experience in computational analyses, including coding/scripting languages (e.g., python, R, MATLAB) and using version-control systems like Git, is essential. Interest in medical imaging analysis is desirable, but not essential.
– Khatami2019: Khatami et al., Frontiers in Molecular Biosciences 6:158 (2019). https://doi.org/10.3389/fmolb.2019.00158
– Fonteijn2012: Fonteijn et al., NeuroImage 60:1880 (2012). https://doi.org/10.1016/j.neuroimage.2012.01.062
– Young2014: Young et al., Brain 137:2564 (2014). https://doi.org/10.1093/brain/awu176
– Firth2019: Firth et al., Brain 142:2082 (2019). https://doi.org/10.1093/brain/awz136
– Firth2020: Firth et al., Alzheimer’s and Dementia, Early View (2020). https://doi.org/10.1002/alz.12083
Why not add a message here
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.