Analiza in klasifikacija elektroencefalograma za pomoč pri diagnosticiranju zgodnje Alzheimerjeve bolezni

Aljaž, Barbara (author), Jager, Franc (mentor), Sakić, mag., David (co-mentor)

Elektroencefalogram (EEG) se kot diagnostično orodje uporablja predvsem za diagnosticiranje relativno redkih možganskih bolezni, na primer epilepsije. V tej magistrski nalogi smo se usmerili na gručenje in analizo EEG-mikrostanj, ponavljajočih se topografij električnih potencialov na površini glave. Osredotočili smo se na problem zgodnjega odkrivanja Alzheimerjeve bolezni, najpogostejše oblike demence, ki prizadene od 5-10% ljudi starejših od 65 let. Analizirali smo tri algoritme za gručenje mikrostanj. Na podlagi pridobljenih mikrostanj smo opravili analizo statistične pojavljivosti EEG-mikrostanj in opazili signifikantne razlike v pojavljivosti nekaterih mikrostanj med zdravimi subjekti in subjekti, ki imajo najverjetneje demenco. Ta mikrostanja smo nato uporabili v postopku klasifikacije. S postopkom 10-kratnega križnega preverjanja smo ocenili natančnost osmih enostavnih klasifikatorjev, ki glede na statistično pojavljivost mikrostanj v EEG-posnetku določijo, ali je subjekt zdrav ali pa ima demenco. Najbolj natančen klasifikator je bil naučen z metodo podpornih vektorjev na podlagi mikrostanj, pridobljenih z metodo SCIMS, in ima AUC enak 0,76.

• Language: Slovenian
• Keywords: elektroencefalografija, mikrostanja, Alzheimerjeva bolezen, nevronske mreže
• Work type: Master's thesis/paper
• Typology: 2.09 - Master's Thesis
• Organization: FRI - Faculty of Computer and Information Science
• Year: 2023
• PID: 20.500.12556/RUL-152239
• COBISS.SI-ID: 172733187
• Publication date in RUL: 14.11.2023

Secondary language

• Language: English
• Title: Analysis and classification of electroencephalogram to help diagnose early Alzheimer’s disease

Abstract

The electroencephalogram (EEG) is mostly used as a diagnostic tool for relatively rare brain diseases, e.g. epilepsy. In this master's thesis, we focused on the clustering and analysis of EEG microstates, which are recurring topographies of electric potentials on the surface of the head. Our focus was on the problem of diagnosing early-onset Alzheimer's disease, the most common type of dementia that affects 5-10% of people older than 65 years. We analyzed three clustering algorithms. Based on the acquired microstates, we analyzed the frequency of EEG microstate occurrences and observed significant differences in the frequencies of certain microstates between healthy subjects and subjects with dementia. We then used these microstates in a classification. Using a 10-fold cross-validation approach, we assessed the accuracy of eight simple classifiers that determine, based on the statistical frequency of EEG microstate occurrences in the EEG recording, whether a subject is healthy or has probably dementia. The most accurate classifier was trained using the support vector machine method based on microstates acquired using the SCIMS method, with an AUC of 0.76.

• Keywords: electroencephalography, microstates, Alzheimer's disease, neural networks