From EEG signal to classification in Alzheimer disease: A mini review

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that is characterized by cognitive decline and memory loss. Early and accurate diagnosis of this disease is still very challenging. In order to identify relevant biomarkers to assess a subject's cognitive impairment, it has been proved that the electroencephalography (EEG) signals can help in the understanding of various brain dysfunctions. In this mini-review paper, our aim was to present the potential of EEG in the context of Alzheimer disease and the challenges to promote EEG as a diagnostic/prognostic tool for detecting AD. We focus on the integration of EEG data with machine learning algorithms to help in assessing AD. The approach involves a systematic process of EEG data collection, signal preprocessing, feature extraction, feature selection and classification.