TY - JOUR AU - Quirarte Tejeda , Jaime Arturo AU - Flores Nuñez, Jorge Luis AU - Romo Vázquez, Rebeca PY - 2021/06/07 Y2 - 2024/03/29 TI - Feature Extraction from Distributions of Phase Synchronization Values of EEG Recordings JF - Revista Mexicana de Ingenieria Biomedica JA - Rev Mex Ing Biom VL - 42 IS - 2 SE - Research Articles DO - 10.17488/RMIB.42.2.7 UR - http://rmib.mx/index.php/rmib/article/view/1140 SP - 78-89 AB - <p>Epilepsy is the most common neurological pathology. Despite treatments available to patients only 58% to 73% will be free of seizures. This uncertainty of the treatment’s outcome is the basis of other psychiatric affections to patients who are uncertain of the success of their treatment. Seizure prediction models (SPMs) emerged as an aid to help the patient know if he is susceptible to an imminent crisis; such models are based of continuous monitoring of EEG signals of the patient and subsequent continuous analysis of those signals. Looking for features in the signals which differentiate ictal from interictal is an ongoing field of research which aims to get a robust set of features to feed the SPM and get a high degree of certainty of when the next seizure will occur. In this work we propose the analysis of phase differences of EEG as a method to extract features which are able to discriminate between ictal and preictal states of a patient, in specific the numeric distance between q1 and q3 of the distribution of phase differences, We compare this values with other phase synchronization methods and test our hypothesis getting a p = &nbsp;0.0001 with our proposed method.</p> ER -