Automated Multiclass Classification of Spontaneous EEG Activity in Alzheimer’s Disease and Mild Cognitive Impairment

Abstract

Abstract:The discrimination of early Alzheimer's disease (AD) and its prodromal form (i.e., mild cognitive impairment, MCI) from cognitively healthy control (HC) subjects is crucial since the treatment is more effective in the first stages of the dementia. The aim of our study is to evaluate the usefulness of a methodology based on electroencephalography (EEG) to detect AD and MCI. EEG rhythms were recorded from 37 AD patients, 37 MCI subjects and 37 HC subjects. Artifact-free trials were analyzed by means of several spectral and nonlinear features: relative power in the conventional frequency bands, median frequency, individual alpha frequency, spectral entropy, Lempel-Ziv complexity, central tendency measure, sample entropy, fuzzy entropy, and auto-mutual information. Relevance and redundancy analyses were also conducted through the fast correlation-based filter (FCBF) to derive an optimal set of them. The selected features were used to train three different models aimed at classifying the trials: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and multi-layer perceptron artificial neural network (MLP). Afterwards, each subject was automatically allocated in a particular group by applying a trial-based majority vote procedure. After feature extraction, the FCBF method selected the optimal set of features: individual alpha frequency, relative power at delta frequency band, and sample entropy. Using the aforementioned set of features, MLP showed the highest diagnostic performance in determining whether a subject is not healthy (sensitivity of 82.35% and positive predictive value of 84.85% for HC vs. all classification task) and whether a subject does not suffer from AD (specificity of 79.41% and negative predictive value of 84.38% for AD vs. all comparison). Our findings suggest that our methodology can help physicians to discriminate AD, MCI and HC.

Measuring Alterations of Spontaneous EEG Neural Coupling in Alzheimer's Disease and Mild Cognitive Impairment by Means of Cross-Entropy Metrics

“…HC volunteers had no pathological background and underwent a medical examination and cognitive assessment in order to discard any symptoms of neurological disorder (Albert et al, 2011 ). Exclusion criteria were the same used in our previous studies (Poza et al, 2017 ; Ruiz-Gómez et al, 2018 ): (1) presence or history of another neurological or psychiatric disease, different from MCI or dementia due to AD; (2) atypical course or uncommon clinical presentations according to the NIA-AA criteria; (3) advanced dementia (Clinical Dementia Rating = 3); (4) institutionalized patients; (5) medication that could affect EEG activity; and (6) lack of cooperation during EEG acquisition. This study was carried out in accordance with the recommendations of the Code of Ethics of the World Medical Association with written informed consent from all subjects.…”

“…In our previous study (Ruiz-Gómez et al, 2018 ), we randomly divided the EEG database into training and test sets. The training set was composed of 60 subjects (20 of each group), while the remaining 51 subjects were assigned to the test set (17 of each group).…”

“…In past decades, the abnormalities in AD and MCI neural activity were typically characterized using local activation analyses in individual sensors, by means of spectral and non-linear measures. Spectral analyses reflect a power increase in low frequency bands as the disease worsens, and a decrease in higher frequencies (Baker et al, 2008 ; Gasser et al, 2008 ; Ruiz-Gómez et al, 2018 ). Parameters derived from non-linear techniques have revealed that AD and MCI are characterized by a decrease in complexity and variability (Jeong, 2004 ; Dauwels et al, 2010a ; McBride et al, 2014 ; Ruiz-Gómez et al, 2018 ).…”

“…Spectral analyses reflect a power increase in low frequency bands as the disease worsens, and a decrease in higher frequencies (Baker et al, 2008 ; Gasser et al, 2008 ; Ruiz-Gómez et al, 2018 ). Parameters derived from non-linear techniques have revealed that AD and MCI are characterized by a decrease in complexity and variability (Jeong, 2004 ; Dauwels et al, 2010a ; McBride et al, 2014 ; Ruiz-Gómez et al, 2018 ). Particularly, different notions of entropy, such as Approximate Entropy ( ApEn ) and Sample Entropy ( SampEn ), have paid great attention in discriminating AD patients, MCI subjects, and cognitively healthy control (HC) subjects, mostly using binary approaches.…”

Brain Network Modeling Based on Mutual Information and Graph Theory for Predicting the Connection Mechanism in the Development of Alzheimer's Disease

“…Most of the previously proposed models start their simulation with the assumptions that nodes 1 Mild cognitive impairment (MCI) causes a slight but noticeable and measurable decline in cognitive abilities, including memory and thinking skills. A person with MCI is at an increased risk of developing Alzheimer's or another dementia [34]. 2 Mini-mental state examination (MMSE) is a method to evaluate the cognitive state of AD patients and have been routinely used in clinical settings [37].…”