Migraine Classification from EEG Signals Using ML Algorithms

Migraine is a complex neurological disorder with symptoms that often overlap with other conditions, complicating accurate diagnosis. This study applies machine learning (ML) for migraine classification using EEG data to improve diagnostic ac-curacy. EEG recordings from 36 subjects (healthy and migraine-affected) were processed to extract significant features through band-pass filtering, Independent Component Analysis (ICA), and Power Spectral Density (PSD) analysis. Two neural network models, Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN), were trained on these features, with CNN achieving 97% accuracy. These findings highlight the potential of EEG-based ML in reliable migraine classification, paving the way for practical clinical applications.