Human-artificial intelligence collaboration for comanaging epilepsy in real time.

A research team validated an inpatient prototype in 13 patients with epilepsy, linking scalp and intracranial EEG to a secure artificial intelligence system based on a large language model that communicates bidirectionally with patients through a smartphone app. The system analyzes biomarkers of sleep, medication, cognition and seizure probability, notifies patients of clinical events and trends, records symptoms and responses, and uses feedback to retrain its seizure detector to reduce false alarms. All patients were undergoing video EEG monitoring: scalp EEG n = 11, intracranial EEG n = 2.