Early Diagnosis and Classification of Alzheimer’s Disease Based on EEG Time–Frequency Images
TL;DR
The proposed intelligent EEG diagnostic framework shows potential for deployment in primary healthcare institutions and may provide theoretical support for addressing the growing challenges of AD diagnosis and treatment in the context of global population aging.
Abstract
Mild cognitive impairment (MCI) is a cognitive disorder characterized by memory impairment and is associated with an increased risk of progression to Alzheimer’s disease (AD). Therefore, classification of MCI and different stages of AD is fundamental for understan ding and treating this disease. This study aims to provide an efficient and clinically deployable technical approach for EEG -based early auxiliary diagnosis of AD. In this work, multichannel resting -state electroencephalography (EEG) signals were transformed into time–frequency images, and a lightweight convolutional neural network (CNN) was constructed for three - class classification of AD, MCI, and healthy controls (HC). The proposed model achieved an accuracy of 84.96%, an F1-score of 0.8486, and a macro -average area under the curve (AUC) of 0.965 on the randomly split test set, significantly outperforming conventional machine learning approaches. These results demonstrate the feasibility of using EEG for early AD detection. From a practical perspective, the proposed intelligent EEG diagnostic framework shows potential for deployment in primary healthcare institutions and may provide theoretical support for addressing the growing challenges of AD diagnosis and treatment in the context of global population aging.