Related Experiment Video
Updated: Sep 25, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Sleep EEG-Based Approach to Detect Mild Cognitive Impairment
Duyan Geng1,2, Chao Wang2, Zhigang Fu3
1State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, China.
Abstract:
Mild Cognitive Impairment (MCI) is an early stage of dementia, which may lead to Alzheimer's disease (AD) in older adults. Therefore, early detection of MCI and implementation of treatment and intervention can effectively slow down or even inhibit the progression of the disease, thus minimizing the risk of AD. Currently, we know that published work relies on an analysis of awake EEG recordings. However, recent studies have suggested that changes in the structure of sleep may lead to cognitive decline. In this work, we propose a sleep EEG-based method for MCI detection, extracting specific features of sleep to characterize neuroregulatory deficit emergent with MCI. This study analyzed the EEGs of 40 subjects (20 MCI, 20 HC) with the developed algorithm. We extracted sleep slow waves and spindles features, combined with spectral and complexity features from sleep EEG, and used the SVM classifier and GRU network to identify MCI. In addition, the classification results of different feature sets (including with sleep features from sleep EEG and without sleep features from awake EEG) and different classification methods were evaluated. Finally, the MCI classification accuracy of the GRU network based on features extracted from sleep EEG was the highest, reaching 93.46%. Experimental results show that compared with the awake EEG, sleep EEG can provide more useful information to distinguish between MCI and HC. This method can not only improve the classification performance but also facilitate the early intervention of AD.
Insights
Detecting Mild Cognitive Impairment (MCI) using sleep EEG is more effective than using awake EEG. This novel approach, analyzing sleep features, achieved 93.46% accuracy, aiding early Alzheimer
Area of Science:
- Neuroscience
- Gerontology
- Biomedical Engineering
Background:
- Mild Cognitive Impairment (MCI) is an early precursor to Alzheimer's disease (AD), necessitating early detection for intervention.
- Existing methods primarily analyze awake electroencephalogram (EEG) recordings, potentially overlooking sleep-related neurophysiological changes.
- Emerging evidence links altered sleep architecture to cognitive decline, suggesting sleep EEG as a valuable diagnostic tool.
Purpose of the Study:
- To develop and validate a novel method for MCI detection using sleep EEG features.
- To investigate the utility of sleep EEG in characterizing neuroregulatory deficits associated with MCI.
- To compare the diagnostic performance of sleep EEG features against awake EEG features for MCI classification.
Main Methods:
- Analysis of sleep EEG recordings from 40 participants (20 MCI, 20 healthy controls).
- Extraction of specific sleep features, including slow waves and spindles, alongside spectral and complexity features.
- Classification of MCI using Support Vector Machine (SVM) and Gated Recurrent Unit (GRU) network models.
Main Results:
- The GRU network utilizing sleep EEG features achieved the highest MCI classification accuracy of 93.46%.
- Sleep EEG features demonstrated superior performance in distinguishing MCI from healthy controls compared to awake EEG.
- The study identified specific sleep EEG characteristics indicative of neuroregulatory deficits in MCI.
Conclusions:
- Sleep EEG analysis offers a promising, high-accuracy approach for early MCI detection.
- Incorporating sleep features into EEG analysis significantly enhances the ability to differentiate MCI from healthy cognition.
- This method holds potential for early intervention strategies to mitigate Alzheimer's disease progression.
