Objective: Development of an EEG preprocessing technique for improvement of de tection of Alzheimer’s disease (AD).The technique is based on filtering of EEG data using blind source separation (BSS) and projection of...Objective: Development of an EEG preprocessing technique for improvement of de tection of Alzheimer’s disease (AD).The technique is based on filtering of EEG data using blind source separation (BSS) and projection of components which are possibly sensitive to cortical neuronal impairment found in early stages of AD. Methods: Artifact-free 20 s intervals of raw resting EEG recordings from 22 pat ients with Mild Cognitive Impairment (MCI) who later proceeded to AD and 38 age -matched normal controls were decomposed into spatio-temporally decorrelated c omponents using BSS algorithm‘AMUSE’. Filtered EEG was obtained by back projec tion of components with the highest linear predictability. Relative power of fil tered data in delta, theta, alpha 1, alpha 2, beta1, and beta 2 bands were proce ssed with Linear Discriminant Analysis (LDA). Results: Preprocessing improved th e percentage of correctly classified patients and controls computed with jack-k nifing cross-validation from 59 to 73%and from 76 to 84%, correspondingly. Co nclusions: The proposed approach can significantly improve the sensitivity and s pecificity of EEG based diagnosis. Significance: Filtering based on BSS can impr ove the performance of the existing EEG approaches to early diagnosis of Alzheim er’s disease. It may also have potential for improvement of EEG classification in other clinical areas or fundamental research. The developed method is quite g eneral and flexible, allowing for various extensions and improvements.展开更多
文摘Objective: Development of an EEG preprocessing technique for improvement of de tection of Alzheimer’s disease (AD).The technique is based on filtering of EEG data using blind source separation (BSS) and projection of components which are possibly sensitive to cortical neuronal impairment found in early stages of AD. Methods: Artifact-free 20 s intervals of raw resting EEG recordings from 22 pat ients with Mild Cognitive Impairment (MCI) who later proceeded to AD and 38 age -matched normal controls were decomposed into spatio-temporally decorrelated c omponents using BSS algorithm‘AMUSE’. Filtered EEG was obtained by back projec tion of components with the highest linear predictability. Relative power of fil tered data in delta, theta, alpha 1, alpha 2, beta1, and beta 2 bands were proce ssed with Linear Discriminant Analysis (LDA). Results: Preprocessing improved th e percentage of correctly classified patients and controls computed with jack-k nifing cross-validation from 59 to 73%and from 76 to 84%, correspondingly. Co nclusions: The proposed approach can significantly improve the sensitivity and s pecificity of EEG based diagnosis. Significance: Filtering based on BSS can impr ove the performance of the existing EEG approaches to early diagnosis of Alzheim er’s disease. It may also have potential for improvement of EEG classification in other clinical areas or fundamental research. The developed method is quite g eneral and flexible, allowing for various extensions and improvements.
