Machine learning detects EEG microstate alterations in patients living with temporal lobe epilepsy

Diagnosis of epilepsy is dependent on accurate clinical history and/or identification of ictal or interictal discharges (IED) on EEG. Repeated scalp EEG having a sensitivity upto 90% is considered gold standard in the management of epilepsy owing to its wide availability and low cost [1]. However, the detection of interictal discharges is dependent on several factors including seizure frequency, sleep deprivation, type of epilepsy, medications, interobserver variability etc. making the sensitivity of scalp EEG in temporal lobe epilepsy (TLE) highly variable [2].

0