Abstract
Introduction: Dementia is a neurological disorder associated with aging thatcan cause a loss of cognitive functions, impacting daily life. Alzheimer’s disease(AD) is the most common cause of dementia, accounting for 50–70% ofcases, while frontotemporal dementia (FTD) affects social skills and personality.Electroencephalography (EEG) provides an effective tool to study the effects ofAD on the brain.Methods: In this study, we propose to use shallow neural networks applied totwo sets of features: spectral-temporal and functional connectivity using fourmethods. We compare three supervised machine learning techniques to the CNNmodels to classify EEG signals of AD / FTD and control cases. We also evaluatedifferent measures of functional connectivity from common EEG frequency bandsconsidering multiple thresholds.Results and discussion: Results showed that the shallow CNN-based modelsachieved the highest accuracy of 94.54% with AEC in test dataset whenconsidering all connections, outperforming conventional methods and providingpotentially an additional early dementia diagnosis tool.