Aristotle University Of Thessaloniki (AUTH)
Προσδιορισμός υποφαινοτύπων του γλαυκώματος με την χρήση μεθόδων κατηγοριοποίησης
Abstract
dc:descriptionPurpose: The purpose of this study is to create discriminating functions between normal subjects and glaucoma phenotypes. The parameters from several imaging technologies together were used (OCT, HRT, GDx) and also AGIS SCORE. The discriminating functions produced refer to specific phenotypes. Due to the existence of a multitude of parameters (total 63 parameters), our goal also is to distinguish the most statistically significant to optimize the discriminating functions. Methodology: The analysis used data from 182 individuals, of which 111 belong to the category of normal, 30 in the category of PEX and the remaining 41 in the category of POAG. Individuals who participated in the study came from the glaucoma clinic of the Second University Clinic of Papageorgiou General Hospital, and the database of the Thessaloniki Eye Study. Using ANCOVA, we determined the optimal subset of parameters and the classification was performed using discriminant analysis. Results-Conclusions: In all cases a reduction in the number of variables was achieved. Discriminating functions were created, but the division into three categories was not achieved, while among the phenotypes there were no satisfactory results. The Discriminating functions were used to create a decision support system.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2011
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Αντωνιάδης, Αντώνιος
- Antoniadis, Antonios
Subjects
dc:subject × 20- Μέθοδοι κατηγοριοποίησης
- Φαινότυπος
- Γλαύκωμα
- Σύστημα στήριξης αποφάσεων ANDREW
- Διαχωριστική ανάλυση
- Ανάλυση συνδιακύμανσης
- Classification methods
- Phenotypes
- Glaucoma
- Decision support systems
- Discriminant analysis
- ANALYSIS OF COVARIANCE
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Ιατρική και Επιστήμες Υγείας
- Κλινική Ιατρική
- Natural Sciences
- Computer and Information Sciences
- Medical and Health Sciences
- Clinical Medicine
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/26047