Use this URL to cite or link to this record in EThOS:
Title: Characterization of neurological disorders using evolutionary algorithms
Author: Picardi, Chiara
ISNI:       0000 0004 7431 9305
Awarding Body: University of York
Current Institution: University of York
Date of Award: 2018
Availability of Full Text:
Access from EThOS:
Access from Institution:
The life expectancy increasing, in the last few decades, leads to a large diffusion of neurodegenerative age-related diseases such as Parkinson’s disease. Neurodegenerative diseases are part of the huge category of neurological disorders, which comprises all the disorders affecting the central nervous system. These conditions have a terrible impact on life quality of both patients and their families, but also on the costs associated to the society for their diagnosis and management. In order to reduce their impact on individuals and society, new better strategies for the diagnosis and monitoring of neurological disorders need to be considered. The main aim of this study is investigating the use of artificial intelligence techniques as a tool to help the doctors in the diagnosis and the monitoring of two specific neurological disorders (Parkinson’s disease and dystonia), for which no objective clinical assessments exist. The evolutionary algorithms are chosen as the artificial intelligence technique to evolve the best classifiers. The classifiers evolved by the chosen technique are then compared with those evolved by two popular well-known techniques: artificial neural network and support vector machine. All the evolved classifiers are not only able to distinguish among patients and healthy subjects but also among different subgroups of patients. For Parkinson’s disease: two different cognitive impairment subgroups of patients are considered, with the aim of an early diagnosis and a better monitoring. For dystonia: two kinds of dystonia patients are considered (organic and functional) to have a better insight in the division of the two groups. The results obtained for Parkinson’s disease are encouraging and evidenced some differences among the cognitive impairment subgroups. Dystonia results are not satisfactory at this stage, but the study presents some limitations that could be overcome in future work.
Supervisor: Smith, Stephen L. Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available