Taylor, Beatrice;
(2024)
Computational Modelling of Symptoms, Biomarkers, and Care Needs in the Rarer Dementias.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
BTaylor_thesis_computational_dementia.pdf - Accepted Version Download (17MB) | Preview |
Abstract
The rarer dementias are often associated with cognitive symptoms other than memory, a younger age at disease onset, and some are autosomal dominant conditions. Even within clinical phenotypes, there is heterogeneity in both symptom occurrence and neuroanatomy. Together these factors make the rarer dementias harder to diagnose, and care for than typical Alzheimer’s disease. Over the past 13 years, significant advancements have been made in the field of computational disease progression modelling. Machine learning methods, such as the Subtype and Stage Inference algorithm, have been increasingly utilised to enhance our understanding of neurodegenerative conditions like dementia. In this thesis I developed and applied disease progression models to further our understanding of the symptoms and neuroanatomy of the rarer dementias. In my first project I conducted a scoping review of activities of daily living in the rarer dementias, identifying a lack of suitable staging scales. This informed the second project, the development of a new methodology for understanding caregiver survey data. I used the Mallows model to describe the distribution of survey responses, and hence infer a data-driven description of symptom change. The model was validated using primary progressive aphasia and posterior cortical atrophy datasets. In the third project I used the Subtype and Stage Inference algorithm to characterise the neuroanatomy of primary progressive aphasia, using a dataset of MRI scans. The algorithm identified four data-driven subtypes. Apart from the semantic variant, there was variable alignment between the data-driven subtypes and clinical phenotypes. This work inspired my fourth and final project on the ethical considerations of using machine learning with neuroimaging data modalities.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Computational Modelling of Symptoms, Biomarkers, and Care Needs in the Rarer Dementias |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2024. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Centre for Advanced Spatial Analysis UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10201091 |
Archive Staff Only
 |
View Item |
