Electroencephalography Applications in Alzheimer's Disease Diagnostics

Electroencephalography (EEG) has re-emerged as a versatile, non-invasive technique for detecting and monitoring Alzheimer’s disease (AD). By recording electrical activity at the scalp, EEG reveals characteristic shifts in brain rhythms—most notably an increase in low-frequency (delta and theta) power and a decline in higher-frequency bands. These spectral changes, coupled with measures of functional connectivity such as coherence and synchrony, offer insight into the neural network disruptions that accompany cognitive decline. Advances in time–frequency analysis, including adaptive wavelet transforms, and in non-linear complexity measures have sharpened the sensitivity of EEG to early AD-related alterations, even at the stage of mild cognitive impairment (MCI).

In parallel, machine learning methods have been deployed to classify EEG patterns, yielding automated frameworks that distinguish healthy controls, MCI and AD with growing accuracy. Crucially, modern approaches emphasise explainability, allowing clinicians to interrogate which spectral or connectivity features drive algorithmic decisions. This convergence of signal-processing innovation and computational modelling supports the development of accessible screening tools that may supplement or, in some contexts, replace more expensive neuroimaging and invasive biomarker assays.

Worldwide, the ability to deploy portable EEG systems promises broader screening and longitudinal monitoring in diverse clinical and community settings. By lowering costs and improving patient comfort, EEG-based diagnostics could facilitate earlier intervention, better patient stratification in clinical trials and more personalised management of AD progression.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Electroencephalography Applications in Alzheimer's Disease Diagnostics publication trend

The graph below shows the total number of articles in electroencephalography applications in alzheimer's disease diagnostics across all publications each year (not limited to Nature Index journals).

Technical terms

Electroencephalography (EEG): A technique for recording electrical brain activity via electrodes placed on the scalp.

Power spectral density: A measure of signal power across frequency bands, used to quantify the strength of neural oscillations.

Coherence: A metric of synchrony between EEG signals at different scalp locations, reflecting functional connectivity.

Wavelet transform: A time–frequency decomposition method that adapts to transient signal fluctuations, improving resolution of brief events.

Biomarker: A quantifiable indicator of a biological state or condition, used here to denote EEG-derived measures that correlate with AD pathology.

References

1. Adazd-Net: Automated adaptive and explainable Alzheimer’s disease detection system using EEG signals. Knowledge-Based Systems (2023).
2. Neural biomarker diagnosis and prediction to mild cognitive impairment and Alzheimer’s disease using EEG technology. Alzheimer's Research & Therapy (2023).
3. Systematic Review on Resting‐State EEG for Alzheimer’s Disease Diagnosis and Progression Assessment. Disease Markers (2018).