National Technical University of Athens (NTUA)
Υπολογιστικές μέθοδοι παρακολούθησης και διαχείρισης ασθενών με νευρολογικές παθήσεις
Abstract
dc:descriptionThis thesis focuses on developing computational methods to improve management and monitoring of patients suffering from epilepsy or Parkinson's disease (PD), two of the most common neurological disorders. In the case of epilepsy various methodologies were designed to perform electroencephalogram (EEG) analysis for automatic detection of epileptic seizures and the timely prediction of their occurrence, respectively. Innovative methodologies have been developed focusing on unsupervised seizure detection criteria, utilizing the available medical knowledge instead of relying on pre-evaluated EEG data for training. The proposed methodologies are the first implementations for unsupervised seizure detection that were developed without any apriori information or training and evaluated with open EEG data from big datasets. The proposed epileptic seizure prediction methodology introduces deep learning algorithms in the analysis of preictal EEG signals, using for the first time Long Short-Term Memory (LSTM) network models for seizure prediction, in order to identify and classify preictal patterns in patients’ EEG and alarm for incoming seizures. A broad set of features is extracted from small EEG segments using time and frequency domain analysis, signal correlation analysis between the different EEG channels and the most popular metrics from Graph theory. For the management of PD patients, a model to extract prognostic factors indicating high risk of developing rapid symptoms progression or the occurrence of early cognitive decline in PD patients, using data mining techniques and machine learning algorithms. The methodology is based on multiparametric evaluations of the initial symptoms at the early stages of the disease, using an extensive set of about 600 baseline evaluation features from an open database. A Decision Support System (DSS) was also developed to assist clinicians while assessing the current status of patients with PD using the Hoehn & Yahr scale and improve progression monitoring in PD. The proposed DSS system is the first such approach in this field based on machine learning algorithms, which are used to analyze the motor symptoms of PD patients in order to accurately categorize them into the five stages of the Hoehn & Yahr scale.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2020
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Tsiouris, Konstantinos
- Τσιούρης, Κωνσταντίνος
Subjects
dc:subject × 22- Επιληψία, Ηλεκτροεγκεφαλογράφημα
- Πρόβλεψη επιληπτικών κρίσεων
- Ανίχνευση επιληπτικών κρίσεων
- Δίκτυα βαθιάς μάθησης
- Νόσος Parkinson
- Προγνωστικοί παράγοντες
- Συστήματα υποστήριξης κλινικών αποφάσεων
- Epilepsy, Electroencephalogram
- Seizure prediction
- Seizure detection
- Deep learning algorithms
- Parkinson's disease
- Prognostic factors
- Clinical decision support systems
- Επιστήμες Μηχανικού και Τεχνολογία
- Βιοϊατρική Μηχανική
- Ιατρική και Επιστήμες Υγείας
- Ιατρική Βιοτεχνολογία
- Engineering and Technology
- Medical Engineering
- Medical and Health Sciences
- Medical Biotechnology
Rights
dc:rights- Statement dc:rights
-
- BY_NC_ND
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/47373