Precise Discrimination for Multiple Underlying Pathologies of Dementia Cases Based on Deep-Learning with Electroencephalography
Abstract Background: Developing accurate and universally available biomarkers for dementia diseases is demanded under world-wide rapid increasing of patients with dementia. Electroencephalogram (EEG) offers promising examinations due to their inexpensiveness, high availability, and sensitiveness to neural functions. EEG applicability can be expanded by deep-learning.Methods: We analyzed EEG signals based on novel deep neural network in healthy volunteers (HV, N=55), patients with Alzheimer's disease (AD, N=101), dementia with Lewy bodies (DLB, N=75), and idiopathic normal pressure hydrocephalus (iNPH, N=60) to evaluate the discriminative accuracy of these diseases.Results: High discriminative accuracies were archived between HV and patients with dementia, yielding 81.7 %(vs AD), 93.9% (vs DLB), and 93.1% (vs iNPH).Conclusions: This study revealed that the EEG data of patients with dementia were successfully discriminated from healthy volunteers based on deep learning and could produce a new purpose of EEG measurement in screening for dementia diseases.