Time-Frequency functional connectivity alterations in Alzheimer's disease and frontotemporal dementia: An EEG analysis using machine learning

Objective: Alzheimer's disease (AD) and frontotemporal dementia (FTD) are prevalent neurodegenerative diseases characterized by altered brain functional connectivity (FC), affecting over 100 million people worldwide. This study aims to identify distinct FC patterns as potential biomarkers for differential diagnosis.

Methods: Resting-state EEG data from 36 AD patients, 23 FTD patients, and 29 healthy controls were analyzed using time-frequency and bandpass filtering FC metrics. These metrics were estimated through Pearson's correlations, mutual information, and phase lag index, and served as input features in a support vector machine (SVM) with Leave-One-Out Cross-Validation for group classification.

Results: Both AD and FTD exhibited significantly decreased FC in the theta band within the frontal lobe and increased FC in the beta band in the posterior regions. Additionally, a decreased FC in central regions at theta band was observed uniquely in AD, but not in FTD. SVM classification accuracies reached 95% for AD and 86% for FTD.

Conclusions: High classification accuracies underscore the potential of these FC alterations as reliable biomarkers for AD and FTD.

Significance: This is the first study to integrate time-frequency and bandpass filtering FC metrics to reveal brain network alterations in AD and FTD, providing new insights for diagnostics and neurodegenerative pathologies.