Machine learning-based classification of physiological and pathological high-frequency oscillations recorded by stereoelectroencephalography

Epilepsy is a chronic neurological disease characterized by recurrent seizures, which can potentially cause severe damage to the development and function of the brain. While a majority of patients may achieve a seizure-free status with the appropriate use of antiepileptic drugs, about 30% of the patients are drug-resistant [1] and require surgical intervention to achieve seizure freedom [2]. Complete resection of the epileptogenic zone (EZ) is essential for postoperative seizure control [3]. Epileptologists primarily rely on the seizure onset zone (SOZ) determined by intracranial electroencephalography recording techniques such as stereoelectroencephalography (SEEG) due to its high temporal and spatial resolution [4,5].

0