Year: 2013
Type: dissertation
Abstract: The goal of the research reported in this thesis is to contribute to early and \naccurate detection of dementia. Early detection of dementia is essential to \nmaximising the effectiveness of treatment against memory loss. This goal is \npursued by interpreting the Mini-Mental State Examination (MMSE) in novel \nways. The MMSE is the most widely used screening tool for dementia, it is a \nquestionnaire of 30 items. The objectives of the research are as follows: \nto reduce the dimensions of the MMSE to the most relevant ones in order \nto inform a predictive model by using computational methods on a data \nset of MMSE results, \nto construct a model predicting a diagnosis informed by the features \nextracted from the previous step by applying, comparing and combining \ntraditional and novel modelling methods, \nto propose a semantic analysis of the sentence writing question in the \nMMSE in order to utilise information recorded in MMS examinations \nwhich has not been considered previously. \nTraditional methods of analysis are inadequate for questionnaire data such \nas the MMSE due to assumptions of normally distributed data. Alternative \nmethods for analysis of discrete data are investigated and a novel method for \ncomputing information theoretic measures is proposed. The methods are used \nto demonstrate that an automated analysis of the MMSE sentence improves \nthe accuracy of differentiating between types of dementia. Finally, models are \nproposed which integrate the semantic annotations with the MMSE data to \nderive rules for difficult to distinguish types of dementia.
Author: Diman Todorov
Language: English
Subfield: Psychiatry and Mental health
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W761272724