Enhanced Classification of Migraine Headaches: Leveraging Machine Learning, Deep Learning, and Bayesian Networks with Data Augmentation

This study addresses the classification of migraine headaches using advanced machine learning techniques, specifically ensemble models and boosting methods. We employed data augmentation to enhance a dataset of 400 samples to 1449, ensuring balanced class distribution. Our approach leverages Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbours (KNN), Decision Trees (DT), Deep Neural Networks (DNN), and Bayesian Network. The results demonstrate significant improvements in classification accuracy, with the best-performing models achieving up to 99.66% accuracy. This research contributes to the field by showcasing the effectiveness of combining data augmentation with advanced machine learning techniques for improved migraine classification.