Abstract
Accurate diagnosis of dementia subtypes is crucial for optimizing treatment planning and enhancing caregiving strategies. To date, the accuracy of classifying Alzheimer's disease (AD) and frontotemporal dementia (FTD) using electroencephalogram (EEG) data has been lower than that of distinguishing individuals with these diseases from healthy elderly controls (HCs). This limitation has impeded the feasibility of a cost-effective differential diagnosis for the two subtypes in clinical settings. This study addressed this issue by quantifying communication between electrode pairs in EEG data, along with demographic information, as features to train machine learning (support vector machine) models. Our focus was on refining the feature set specifically for AD-FTD classification. Using our initial feature set, we achieved classification accuracies of 76.9% for AD-HC, 90.4% for FTD-HC, and 91.5% for AD-FTD. Notably, feature importance analyses revealed that the features influencing AD-HC classification are unnecessary for distinguishing between AD and FTD. Eliminating these unnecessary features improved the classification accuracy of AD-FTD to 96.6%. We concluded that communication between electrode pairs specifically involved in the neurological pathology of FTD, but not AD, enables highly accurate EEG-based AD-FTD classification.