introduction: Attention Deficit Hyperactivity Disorder (ADHD) is a complex neurodevelopmental disorder that affects cognitive and behavioral functions. This study aims ADHD classification and medication effects using statistical features extracted from Variational Mode Decomposition (VMD) applied to fMRI signals. materials and methods: The ADHD-200 dataset was used to analyze fMRI data from 41 healthy controls, 41 medicated ADHD individuals, and 41 non-medicated ADHD individuals. Signal decomposition was performed using VMD with nine sub-bands, and the extracted features were used for classification. Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Linear Discriminant Analysis (LDA) were applied to distinguish ADHD subtypes and control groups across three scenarios: medicated vs. control, non-medicated vs. control, and medicated vs. non-medicated ADHD. results: The results showed that SVM and LDA achieved 88.41 discussion: --- conclusion: This study highlights the effectiveness of VMD-based signal processing for ADHD classification, demonstrating its potential for distinguishing ADHD subtypes and assessing medication effects. The integration of statistical features from VMD sub-bands offers a novel approach to improving ADHD diagnosis and treatment strategies.
Aker et al. (Mon,) studied this question.