Resting-state EEG microstate features for Alzheimer's disease classification

• Published in: PloS one 2024-12, Vol.19 (12), p.e0311958
• Main Authors: Yang, Xiaoli, Fan, Zhipeng, Li, Zhenwei, Zhou, Jiayi
• Format: Article
• Language: English
• Subjects: Aged; Aged, 80 and over; Algorithms; Alzheimer Disease - classification; Alzheimer Disease - diagnosis; Alzheimer Disease - physiopathology; Alzheimer's disease; Analysis; Bandpass filters; Biology and Life Sciences; Brain research; Care and treatment; Classification; Cognitive ability; Computer and Information Sciences; Datasets; Dementia; Dependent variables; Diagnosis; Disease; EEG; Effectiveness; Electroencephalography; Electroencephalography - methods; Engineering and Technology; Feature extraction; Female; Frequencies; Group theory; Humans; Life expectancy; Machine Learning; Male; Medicine and Health Sciences; Methods; Neurodegenerative diseases; Neuropsychology; Parameter identification; Patient compliance; Pattern analysis; Physical Sciences; Research and Analysis Methods; Rest - physiology; Signal Processing, Computer-Assisted; Support Vector Machine; Support vector machines; Topographic mapping; Topography
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0311958

Resting-state electroencephalogram (EEG) microstate analysis resolves EEG signals into topographical maps representing discrete, sequential network activations. These maps can be used to identify patterns in EEGs that may be indicative of underlying neurological conditions. One such pattern is observed in EEGs of patients with Alzheimer's disease (AD), where a global microstate disorganization is evident. We initially investigated the classification efficacy of microstate parameters as markers for AD classification. Subsequently, we compared the classification efficacy of EEG conventional features to ascertain the superiority of microstate features. We extracted raw EEG data from a public, independent database, OpenNeuro EEG. The raw EEG was subjected to preprocessing and band-pass filtering to obtain five distinct frequency bands. The SVM classifier was used to input the microstate feature set to determine the one with the best classification effect as the main band. In order to verify the advantage of the microstate features, the AD group and the healthy control group were filtered for the main frequency bands respectively. Then the microstate feature set and the regular feature set were extracted. The two feature sets were input into four different conventional machine learning classifiers, namely SVM, KNN, RF, and LR, in order to avoid the classifiers as the dependent variable. And the comparison of the classification results of simply two feature sets as the dependent variable can be obtained. The results show that in the Alpha (8-13 Hz) sub-band, the microstate feature set as model input to SVM is optimal for the recognition of AD, with a classification accuracy of 99.22%. The Alpha band, as the main frequency band, the microstate feature set as model input to the four classifiers obtains an average classification accuracy of 98.61%, and the average classification accuracy obtained by the conventional EEG feature set as model is 91.19%. Based on four different classifiers, microstate parameters can be served as markers to effectively classify the EEG of AD patients. The microstate feature set outperforms the conventional EEG feature set after excluding the effect of classifiers.