A machine-learning algorithm for detecting seizure termination in scalp EEG

► Description of a machine-learning algorithm for detecting the cessation of epileptic seizures in scalp EEG. ► Algorithm detects the end of 85% of test seizures within a 15-second error margin. ► Algorithm can be used to detect the onset of status epilepticus or trigger the delivery of therapies to lessen the severity of post-ictal period symptoms.