Investigation of EEG-Based Graph-Theoretic Analysis for Automatic Diagnosis of Alcohol Use Disorder
Date issued
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Abstract
U alkoholismu (AUD) bývá pozorována abnormální funkční konektivita mozku (FC). Tato práce popisuje analýzu FC s využitím grafové teoretické analýzy založené na EEG a strojového učení (ML). Mozková FC byla kvantifikována s využitím synchronization likelihood (SL). Neorientované grafy byly vytvořeny pro každou dvojici EEG kanálů s využitím hodnot SL. Dále byly vypočteny příznaky založené na grafech, jako je minimální kostra, vzdálenosti mezi uzly a maximální tok mezi uzly. Příznaky byly použity jako vstupní data pro klasifikaci účastníků studie. Klasifikace byla ověřena daty získanými od 30 pacientů s AUD a 30 zdravých účastníků.
Abnormal functional connectivity (FC) has been commonly observed during alcohol use disorder (AUD). In this work, FC analysis has been performed by incorporating EEG-based graph-theoretic analysis and a machine learning (ML) framework. Brain FC was quantified with synchronization likelihood (SL). Undirected graphs for each channel pair were constructed involving the SL measures. Furthermore, the graph-based features such as minimum spanning tree, distances between nodes, and maximum flow between the graph nodes were computed. The matrix was used as input data to the ML framework to classify the study participants. The ML framework was validated with data acquired from 30 AUD patients and an age-matched group of 30 healthy controls.
Abnormal functional connectivity (FC) has been commonly observed during alcohol use disorder (AUD). In this work, FC analysis has been performed by incorporating EEG-based graph-theoretic analysis and a machine learning (ML) framework. Brain FC was quantified with synchronization likelihood (SL). Undirected graphs for each channel pair were constructed involving the SL measures. Furthermore, the graph-based features such as minimum spanning tree, distances between nodes, and maximum flow between the graph nodes were computed. The matrix was used as input data to the ML framework to classify the study participants. The ML framework was validated with data acquired from 30 AUD patients and an age-matched group of 30 healthy controls.
Description
Subject(s)
strojové učení, support vector machines, analýza časových řad, grafová teoretická analýza, EEG, synchronization likelihood
Citation
MUMTAZ, W., VAŘEKA, L., MOUČEK, R. Investigation of EEG-Based Graph-Theoretic Analysis for Automatic Diagnosis of Alcohol Use Disorder. In: Lecture Notes in Computer Science. Cham: Springer, 2019. s. 205-218. ISBN 978-3-030-30492-8 , ISSN 0302-9743.