Precise Discrimination for Multiple Etiologies of Dementia Cases Based on Deep Learning with Electroencephalography

Abstract

<b><i>Introduction:</i></b> It is critical to develop accurate and universally available biomarkers for dementia diseases to appropriately deal with the dementia problems under world-wide rapid increasing of patients with dementia. In this sense, electroencephalography (EEG) has been utilized as a promising examination to screen and assist in diagnosing dementia, with advantages of sensitiveness to neural functions, inexpensiveness, and high availability. Moreover, the algorithm-based deep learning can expand EEG applicability, yielding accurate and automatic classification easily applied even in general hospitals without any research specialist. <b><i>Methods:</i></b> We utilized a novel deep neural network, with which high accuracy of discrimination was archived in neurological disorders in the previous study. Based on this network, we analyzed EEG data of healthy volunteers (HVs, <i>N</i> = 55), patients with Alzheimer’s disease (AD, <i>N</i> = 101), dementia with Lewy bodies (DLB, <i>N</i> = 75), and idiopathic normal pressure hydrocephalus (iNPH, <i>N</i> = 60) to evaluate the discriminative accuracy of these diseases. <b><i>Results:</i></b> High discriminative accuracies were archived between HV and patients with dementia, yielding 81.7% (vs. AD), 93.9% (vs. DLB), 93.1% (vs. iNPH), and 87.7% (vs. AD, DLB, and iNPH). <b><i>Conclusion:</i></b> This study revealed that the EEG data of patients with dementia were successfully discriminated from HVs based on a novel deep learning algorithm, which could be useful for automatic screening and assisting diagnosis of dementia diseases.

Utilizing portable electroencephalography to screen for pathology of Alzheimer’s disease: a methodological advancement in diagnosis of neurodegenerative diseases

“…In studies using deep learning models, an applied convolutional neural network classifier showed a classification accuracy of 88% for patients with AD vs. HVs (31). In our previous study, a model leveraging deep learning techniques applied to EEG data demonstrated an accuracy of 82% in differentiating between HVs and patients with AD (32). However, these studies included cases of clinical AD diagnosis and lacked confirmed AD pathology.…”