Event-related potentials (ERPs) are one of the most informative and dynamic methods of monitoring cognitive processes, which are widely used in clinical research to deal a variety of psychiatric and neurological disorders as attention-deficit/hyperactivity disorder (ADHD). This work proposes an extraction and selection methodology for discriminating between normal and pathological patients with ADHD by using ERPs. Three different sets of features (morphological, wavelets, and nonlinear based) are analyzed, looking for the best classification accuracy. The results show that the wavelet features provided a good discriminative capability, but it improved by combining all the set of features and applying a feature selection algorithm, reaching a maximum accuracy rate of 91.3%.
Understanding how global brain networks are affected in mild cognitive impairment may explain the changes concerning the electrophysiology of the brain. We research functional changes within neuronal networks in frontal, temporal, parietal lobe and central zone using graph theory in visual oddball paradigm. Thirty subjects (19 females; mean age of 70.63 years old, age range 61 to 79 years old, 11 males; mean age of 70.36 years old, and age range 63 to 81 years old) 14 with mild cognitive impairment and 16 health control. Oddball protocol with target and no target stimuli electroencephalography (EEG) signal were analyzed through functional connectivity (FC) along with Change point detection method and a detailed preprocessing in order to detect dynamical changes in the signal, which reflect the non-stationary behavior of a given EEG signal. Linear Discriminant Analysis (LDA), K-Nearest Neighbor (KNN) and Decision Tree (DT) were trained to classify brain activity in Mild Cognitive Impairment (MCI) and Health Control (HC) subjects based on graph measurements and the physiology interpretation of the Mild Cognitive Impairment. The findings show that using a combination of EEG-based model-free functional connectivity measurements and machine learning to categorize cognitive impairment is effective. The research can be expanded upon to study the possibilities of identifying cognitive decline in real-time, dynamic, and complicated real-world circumstances.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.