Alzheimer’s Disease and Frontotemporal Dementia: A Robust Classification Method of EEG Signals and a Comparison of Validation Methods

• DOI: 10.3390/diagnostics11081437
• Publication Date: 2021-08-10T01:41:46Z
• Authors: Andreas Miltiadous; Katerina D. Tzimo...; Nikolaos Giannakeas; Markos G. Tsipouras; Theodora Afrantou; Panagiotis Ioannidis; Alexandros T. Tza...
• Keywords: Medicine (General); electroencephalogram; frontotemporal dementia; Article; 3. Good health; 03 medical and health sciences; R5-920; 0302 clinical medicine; classification; k-fold; EEG; leave-one-patient-out; Alzheimer’s disease; dementia

Dementia is the clinical syndrome characterized by progressive loss of cognitive and emotional abilities to a degree severe enough interfere with daily functioning. Alzheimer’s disease (AD) most common neurogenerative disorder, making up 50–70% total dementia cases. Another type frontotemporal (FTD), which associated circumscribed degeneration prefrontal anterior temporal cortex mainly affects personality social skills. With rapid advancement in electroencephalogram (EEG) sensors, EEG has become suitable, accurate, highly sensitive biomarker for identification neuronal dynamics cases dementia, such as AD FTD, through signal analysis processing techniques. In this study, six supervised machine-learning techniques were compared on categorizing processed signals FTD cases, provide an insight future methods early diagnosis. K-fold cross validation leave-one-patient-out also evaluate their performance classification problem. The proposed methodology accuracy scores 78.5% detection decision trees 86.3% random forests.