White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Automated Assessment on Clinical Drawing Test for Diagnosis and Analysis of Parkinson’s Disease using Evolutionary Algorithm

Xia, Tian (2019) Automated Assessment on Clinical Drawing Test for Diagnosis and Analysis of Parkinson’s Disease using Evolutionary Algorithm. MSc by research thesis, University of York.

This is the latest version of this item.

[img]
Preview
Text
Tian_Xia_MSCR_Thesis_Final.pdf - Examined Thesis (PDF)
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (6Mb) | Preview

Abstract

The deadly Parkinson’s disease is always a focused area in medical research, even as today there is no cure for such disease. Patient does not have any vivid symptoms until the late stage of the disease when the condition has been threatening patient’s life already. Current diagnosing approach on Parkinson’s disease at early stage often includes test sets in questionnaire form with verdicts from clinical examiners. Such conventional approach has subjective assessment standard as well as verdicts with examiners’ personal judgement, which inevitably may contain human errors. In addition, such assessment method often takes several days for one patient, making it very inefficient. This research project proposed an objective approach by using machine learning to assess one of the tests from the questionnaire – the clinical drawing test, which can classify patients’ drawing performance automatically and is very efficient. This approach also allows the algorithm to catch the smallest detail in the drawing whilst minimise human errors from human-orientated assessments. The result proves that given the same assessment, the algorithm tends to perform better than human verdicts in terms of distinguishing patients in different stages. What’s more, the algorithm proposed in this thesis has an overall advantage over some conventional algorithm models, which not only optimised the computational effort, but also can allow clinical experts to understand how the figure data are used by the algorithm and assist them in further research in Parkinson’s disease.

Item Type: Thesis (MSc by research)
Related URLs:
Academic Units: The University of York > Electronics (York)
Depositing User: Mr Tian Xia
Date Deposited: 14 Jan 2020 16:50
Last Modified: 14 Jan 2020 16:50
URI: http://etheses.whiterose.ac.uk/id/eprint/25367

Available Versions of this Item

You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)