An Automated Approach for the Detection of Alzheimer's Disease From Resting State Electroencephalography

Abstract

Early detection is crucial to control the progression of Alzheimer's disease and to postpone intellectual decline. Most current detection techniques are costly, inaccessible, or invasive. Furthermore, they require laborious analysis, what delays the start of medical treatment. To overcome this, researchers have recently investigated AD detection based on electroencephalography, a non-invasive neurophysiology technique, and machine learning algorithms. However, these approaches typically rely on manual procedures such as visual inspection, that requires additional personnel for the analysis, or on cumbersome EEG acquisition systems. In this paper, we performed a preliminary evaluation of a fully-automated approach for AD detection based on a commercial EEG acquisition system and an automated classification pipeline. For this purpose, we recorded the resting state brain activity of 26 participants from three groups: mild AD, mild cognitive impairment (MCI-non-AD), and healthy controls. First, we applied automated data-driven algorithms to reject EEG artifacts. Then, we obtained spectral, complexity, and entropy features from the preprocessed EEG segments. Finally, we assessed two binary classification problems: mild AD vs. controls, and MCI-non-AD vs. controls, through leave-one-subject-out cross-validation. The preliminary results that we obtained are comparable to the best reported in literature, what suggests that AD detection could be automatically detected through automated processing and commercial EEG systems. This is promising, since it may potentially contribute to reducing costs related to AD screening, and to shortening detection times, what may help to advance medical treatment.

EEG is better left alone

“…Unlike other artifact rejection methods with tunable parameters, Autoreject automatically scans the parameter space to reject the best number of channels and bad data regions. The algorithm was validated on four EEG datasets 31 and has been used with default parameters by at least one other group 32 . We followed the online documentation (https:// autor eject.…”

EEG is better left alone

“…The algorithm was validated on four EEG datasets 32 and has been used with default parameters by at least one other group. 33 We followed the online documentation (https://autoreject.github.io/stable/auto_examples/plot_autoreject_workflow.html; August 8 th 2022) and used, as in the tutorial, 1 to 4 channels to interpolate. Another parameter in the Autoreject tutorial is the number of epochs to fit.…”