Automatic migraine classification using artificial neural networks

What is it about?

This study focuses on designing and testing an early classification system capable of distinguishing between seven types of migraines based on the patient’s symptoms. The methodology proposed comprises four steps: data collection based on symptoms and diagnosis by the treating physician, selection of the most relevant variables, use of artificial neural network models for automatic classification, and selection of the best model based on the accuracy and precision of the diagnosis.

Featured Image

Why is it important?

The novelty, significance, and relevance of this study are outlined as follows: • An indirect method aimed at classifying the type of migraine experienced by a patient, which, unlike existing methodologies, does not use procedures requiring brain wave measurement or the use of sensors. • The systematic migraine classification process used includes the stages of data collection based on symptoms and diagnosis by the treating physician, selection of the most relevant features, use of different classification models, and selection of the most suitable model based on the accuracy and precision of diagnosis.