This post was originally published on here
Scientists have developed a “unique” AI-powered headset that can predict epileptic seizures minutes before they occur.
The researchers say the wearable device could dramatically transform the way the condition is managed.
Currently, there is no readily available device that can give people with epilepsy advanced warnings of seizures.
The headset analyses brainwaves and heart functions to detect an impending seizure, allowing the wearer to take precautions, or warn those around them.
The scientist behind the project says its greatest benefit could be giving people with epilepsy more confidence about the condition, helping them to avoid any secondary injuries caused by a seizure.
Professor Hadi Larijani, who leads the research team at Glasgow Caledonian University, said: “Providing even a few minutes’ warning could be life-changing.
“Our goal is to empower patients and families with time to act to stay safe and live more independently.”
He said the headset was “very unique” and they hoped to one day release it as a wearable device similar to a cap.
“We want it to be as discreet as possible, to be wireless, light — it’s a lot of features that none of the other tools right now have.”
The system was trained using thousands of hours of historical electroencephalography and electrocardiography recordings.
The researchers also used a custom-made “phantom head”, attaching electrodes to it to simulate a real user.
By learning to identify the subtle electrical and physiological patterns that precede a seizure, the AI can issue a timely alert, giving patients and families crucial minutes to prepare and stay safe.
It has an accuracy of up to 95%, and the AI algorithm can display its levels of confidence about the chances of an impending seizure.
Prof Larijani added: “For families affected by epilepsy, even a brief warning means they can prevent injuries and reduce fear.
“That is the true measure of success for us.”
The team is still refining the design for the headset, which they intend to be suitable for children to wear.
Their initial prototypes have used third-party hardware but they hope to develop their own models.
Due to the need for regulatory approvals, it will likely be some years before the product becomes widely available.
