Title:Classification of Patients with Alzheimer’s Disease and Dementia with
Lewy Bodies using Resting EEG Selected Features at Sensor and Source
Levels: A Proof-of-Concept Study
Volume: 18
Issue: 12
Author(s): Rodrigo San-Martin, Francisco J. Fraga*, Claudio Del Percio, Roberta Lizio, Giuseppe Noce, Flavio Nobili , Dario Arnaldi , Fabrizia D'Antonio, Carlo De Lena, Bahar Güntekin , Lutfu Hanoğlu , John Paul Taylor, Ian McKeith, Fabrizio Stocchi, Raffaele Ferri, Marco Onofrj, Susanna Lopez , Laura Bonanni and Claudio Babiloni
Affiliation:
- Engineering, Modeling and Applied Social Sciences Center, Federal University of the ABC, Santo André, Brazil
- Department of Physiology and Pharmacology “V. Erspamer”, Sapienza University of Rome, Rome, Italy
Keywords:
Alzheimer’s disease, lewy body dementia, EEG source connectivity, LORETA, machine learning, feature selection.
Abstract:
Background: Early differentiation between Alzheimer’s disease (AD) and Dementia
with Lewy Bodies (DLB) is important for accurate prognosis, as DLB patients typically show
faster disease progression. Cortical neural networks, necessary for human cognitive function, may
be disrupted differently in DLB and AD patients, allowing diagnostic differentiation between AD
and DLB.
Objective: This proof-of-concept study assessed whether the application of machine learning techniques
to data derived from resting-state electroencephalographic (rsEEG) rhythms (discriminant
sensor power, 19 electrodes) and source connectivity (between five cortical regions of interest) allowed
differentiation between DLB and AD.
Methods: Clinical, demographic, and rsEEG datasets from DLB patients (N=30), AD patients
(N=30), and control seniors (NOld, N=30), matched for age, sex, and education, were taken from
our international database. Individual (delta, theta, alpha) and fixed (beta) rsEEG frequency bands
were included. The rsEEG features for the classification task were computed at both sensor and
source levels. The source level was based on eLORETA freeware toolboxes for estimating cortical
source activity and linear lagged connectivity. Fluctuations of rsEEG recordings (band-pass waveform
envelopes of each EEG rhythm) were also computed at both sensor and source levels. After
blind feature reduction, rsEEG features served as input to support vector machine (SVM) classifiers.
Discrimination of individuals from the three groups was measured with standard performance
metrics (accuracy, sensitivity, and specificity).
Results: The trained SVM two-class classifiers showed classification accuracies of 97.6% for
NOld vs. AD, 99.7% for NOld vs. DLB, and 97.8% for AD vs. DLB. Three-class classifiers (AD
vs. DLB vs. NOld) showed classification accuracy of 94.79%.
Conclusion: These promising preliminary results should encourage future prospective and longitudinal
cross-validation studies using higher resolution EEG techniques and harmonized clinical procedures
to enable the clinical application of these machine learning techniques.
