Abstract
BACKGROUND: Electroencephalogram (EEG) microstates, which reflect large-scale resting-state networks of the brain, have been proposed as potential endophenotypes for methamphetamine use disorder (MUD). However, current endophenotypes lack refinement at the frequency band level, limiting their precision in identifying key frequency bands associated with MUD. METHODS: In this study, we investigated EEG microstate dynamics across various frequency bands and different tasks, utilizing machine learning to classify MUD and healthy controls. RESULTS: During the resting state, the highest classification accuracy for detecting MUD was 85.5%, achieved using microstate parameters in the alpha band. Among these, the coverage of microstate class A contributed the most, suggesting it as the most promising endophenotype for specifying MUD. DISCUSSION: We accurately categorize the endophenotype of MUD into different sub-frequency bands, thereby providing reliable biomarkers.