A new AI system lets epilepsy patients hold real-time conversations with their own brain monitors.

University of Pennsylvania researchers linked live EEG data to a smartphone AI assistant.

Thirteen patients in an epilepsy monitoring unit used it to ask questions and flag possible seizures.

Patient feedback cut false seizure alarms by 80 percent in a retrospective simulation.

The study was published October 13 in the journal Nature Medicine.

Senior author Brian Litt led the NIH-funded work at Penn’s Perelman School of Medicine.

The researchers call it a new class of AI devices that collaborate with patients.

Read the full article for more details on the AI epilepsy study.