scholarly journals Deep Learning of resting-state electroencephalogram signals for 3-class classification of Alzheimer’s Disease, Mild Cognitive Impairment and Healthy Ageing

Author(s):  
Cameron James Huggins ◽  
Javier Escudero ◽  
Mario A Parra ◽  
Brian Scally ◽  
Renato Anghinah ◽  
...  
2021 ◽  
pp. 1-30
Author(s):  
Claudio Babiloni ◽  
Raffaele Ferri ◽  
Giuseppe Noce ◽  
Roberta Lizio ◽  
Susanna Lopez ◽  
...  

Background: In relaxed adults, staying in quiet wakefulness at eyes closed is related to the so-called resting state electroencephalographic (rsEEG) rhythms, showing the highest amplitude in posterior areas at alpha frequencies (8–13 Hz). Objective: Here we tested the hypothesis that age may affect rsEEG alpha (8–12 Hz) rhythms recorded in normal elderly (Nold) seniors and patients with mild cognitive impairment due to Alzheimer’s disease (ADMCI). Methods: Clinical and rsEEG datasets in 63 ADMCI and 60 Nold individuals (matched for demography, education, and gender) were taken from an international archive. The rsEEG rhythms were investigated at individual delta, theta, and alpha frequency bands, as well as fixed beta (14–30 Hz) and gamma (30–40 Hz) bands. Each group was stratified into three subgroups based on age ranges (i.e., tertiles). Results: As compared to the younger Nold subgroups, the older one showed greater reductions in the rsEEG alpha rhythms with major topographical effects in posterior regions. On the contrary, in relation to the younger ADMCI subgroups, the older one displayed a lesser reduction in those rhythms. Notably, the ADMCI subgroups pointed to similar cerebrospinal fluid AD diagnostic biomarkers, gray and white matter brain lesions revealed by neuroimaging, and clinical and neuropsychological scores. Conclusion: The present results suggest that age may represent a deranging factor for dominant rsEEG alpha rhythms in Nold seniors, while rsEEG alpha rhythms in ADMCI patients may be more affected by the disease variants related to earlier versus later onset of the AD.


NeuroImage ◽  
2020 ◽  
Vol 215 ◽  
pp. 116795 ◽  
Author(s):  
F.R. Farina ◽  
D.D. Emek-Savaş ◽  
L. Rueda-Delgado ◽  
R. Boyle ◽  
H. Kiiski ◽  
...  

2019 ◽  
Author(s):  
FR Farina ◽  
DD Emek-Savaş ◽  
L Rueda-Delgado ◽  
R Boyle ◽  
H Kiiski ◽  
...  

AbstractAlzheimer’s disease (AD) is a neurodegenerative disorder characterised by severe cognitive decline and loss of autonomy. AD is the leading cause of dementia. AD is preceded by mild cognitive impairment (MCI). By 2050, 68% of new dementia cases will occur in low- and middle-income countries. In the absence of objective biomarkers, psychological assessments are typically used to diagnose MCI and AD. However, these require specialist training and rely on subjective judgements. The need for low-cost, accessible and objective tools to aid AD and MCI diagnosis is therefore crucial. Electroencephalography (EEG) has potential as one such tool: it is relatively inexpensive (cf. magnetic resonance imaging; MRI) and is portable. In this study, we collected resting state EEG, structural MRI and rich neuropsychological data from older adults (55+ years) with AD, with MCI and from healthy controls (n~60 per group). Our goal was to evaluate the utility of EEG, relative to MRI, for the classification of MCI and AD. We also assessed the performance of combined EEG and behavioural (Mini-Mental State Examination; MMSE) and structural MRI classification models. Resting state EEG classified AD and HC participants with moderate accuracy (AROC=0.76), with lower accuracy when distinguishing MCI from HC participants (AROC=0.67). The addition of EEG data to MMSE scores had no additional value compared to MMSE alone. Structural MRI out-performed EEG (AD vs HC, AD vs MCI: AROCs=1.00; HC vs MCI: AROC=0.73). Resting state EEG does not appear to be a suitable tool for classifying AD. However, EEG classification accuracy was comparable to structural MRI when distinguishing MCI from healthy aging, although neither were sufficiently accurate to have clinical utility. This is the first direct comparison of EEG and MRI as classification tools in AD and MCI participants.


Sign in / Sign up

Export Citation Format

Share Document