A novel approach for migraine detection using localized component filtering and electroencephalographic spectral asymmetry index.

Background: This study aims to improve the accuracy and reliability of migraine detection by combining the localized component filtering (LCF) method with the electroencephalographic (EEG) spectral asymmetry index (SASI) method. The integration of LCF and SASI in the frequency domain under 3 Hz photic stimulation offers a novel approach for robust classification. Methods: EEG recordings from 13 control subjects and 15 migraineurs were used in this study. The SASI values, obtained from LCF pre-processed signals, served as features for classification. The K-means clustering algorithm was applied, and the accuracy was evaluated using the silhouette values method. Results: The combination of the LCF method with the SASI technique resulted in a 17% improvement in clustering accuracy, achieving an overall accuracy of around 87%. This new approach outperformed the histogram K-means clustering method and the SASI technique used alone. The accuracy attained by this combined approach was as high as multi-layer perceptron (MLP) and superior to K-means clustering, which are two well-known approaches of artificial and machine learning (ML) clustering methods, respectively. Conclusion: This study presents a novel and effective approach by combining LCF and SASI for migraine detection, which enhances classification accuracy and provides valuable insights into migraine-related brain activity. Accurate and reliable detection of migraine can lead to more effective treatment and management of the condition, ultimately improving the quality of life for migraine sufferers.