Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental condition in children and is characterized by challenges in maintaining attention, hyperactivity, and impulsive behaviors. Despite ongoing research, we still do not fully understand what causes ADHD. Electroencephalography (EEG) has emerged as a valuable tool for investigating ADHD-related neural patterns due to its high temporal resolution and non-invasiveness. This study aims to contribute to diagnostic accuracy by leveraging EEG data to classify children with ADHD and healthy controls. We used a dataset containing EEG recordings from 60 children with ADHD and 60 healthy controls. The EEG data were captured during cognitive tasks and comprised signals from 19 channels across the scalp. Our primary objective was to develop a machine learning model capable of distinguishing ADHD subjects from controls using EEG data as discriminatory features. We employed several well-known classifiers, including a support vector machine, random forest, decision tree, AdaBoost, Naive Bayes, and linear discriminant analysis, to discern distinctive EEG patterns. To further enhance classification accuracy, we explored the impact of regional data on the classification outcomes. We arranged the EEG data according to the brain regions from which they were derived (namely frontal, temporal, central, parietal, and occipital) and examined their collective effects on the accuracy of our classifications. Notably, we considered combinations of three regions at a time and found that certain combinations led to enhanced accuracy. Our findings underscore the potential of EEG-based classification in distinguishing children with ADHD from healthy controls. The Naive Bayes classifier yielded the highest accuracy (84%) when applied to specific region combinations. Moreover, we evaluated the classification performance based on hemisphere-specific EEG data and found promising results, particularly when using the right hemisphere region channels.
1 January 2021 in Journal of Dental Anesthesia and Pain Medicine
Alzheimer’s disease (AD) is a progressive chronic illness that leads to cognitive decline and dementia. Neuroimaging technologies, such as functional magnetic resonance imaging (fMRI), and deep learning approaches offer promising avenues for AD classification. In this study, we investigate the use of fMRI-based functional connectivity (FC) measures, including the Pearson correlation coefficient (PCC), maximal information coefficient (MIC), and extended maximal information coefficient (eMIC), combined with extreme learning machines (ELM) for AD classification. Our findings demonstrate that employing non-linear techniques, such as MIC and eMIC, as features for classification yields accurate results. Specifically, eMIC-based features achieve a high accuracy of 94% for classifying cognitively normal (CN) and mild cognitive impairment (MCI) individuals, outperforming PCC (81%) and MIC (85%). For MCI and AD classification, MIC achieves higher accuracy (81%) compared to PCC (58%) and eMIC (78%). In CN and AD classification, eMIC exhibits the best accuracy of 95% compared to MIC (90%) and PCC (87%). These results underscore the effectiveness of fMRI-based features derived from non-linear techniques in accurately differentiating AD and MCI individuals from CN individuals, emphasizing the potential of neuroimaging and machine learning methods for improving AD diagnosis and classification.
30 September 2019 in International Journal of Fuzzy Logic and Intelligent Systems
Nishant Chauhan and Byung-Jae Choi. International Journal of Fuzzy Logic and Intelligent Systems 2024;24:10-8. https://doi.org/10.5391/IJFIS.2024.24.1.10