EEG-based detection of early functional brain changes in subjective cognitive decline: a prospective cohort study

Comprehensive Summary

The study investigates whether EEGs can detect early brain changes usually associated with amyloid pathology in patients with SCD (subjective cognitive decline), a preclinical early stage of Alzheimer’s. The researchers analyzed data from 120 SCD patients, classifying them into amyloid-positive and amyloid-negative, and used spectral power analysis and machine learning to interpret the data. They found that amyloid-positive SCD patients exhibited increased low-frequency power, delta, and theta activity, and reduced alpha activity compared to amyloid-negative participants. The EEG machine learning models accurately distinguished amyloid-positive from amyloid-negative patients and outperformed other models based on demographics. The authors highlight that these EEG alterations are both stable and closely linked with amyloid presence, confirming their original hypothesis as an early indicator of Alzheimer's disease.

Outcomes and Implications

This research is clinically relevant because identifying one’s risk for Alzheimer's at such an early stage is critical for intervention and clinical trial enrollment if one wishes. The results indicate that with EEG and machine learning, a non-invasive and low-cost tool for detecting amyloid brain dysfunctions, populations at risk of SCD, and even Alzheimer's, is possible. This approach is extremely relevant because of the widespread availability of EEG relative to PET scans and its long-term applicability. There must still be more research and clinical trials across a larger and more diverse group; however, the results are promising for the future of EEG applications in this sector.