Researchers at Ben-Gurion University in Negev, Israel, developed a device that can warn users of an oncoming epileptic seizure up to an hour in advance. The wearable tech uses AI detection algorithms to analyze electroencephalograms (EEG) in real-time. If indicative brain patterns are recognized, it sends an alert to the user’s smartphone.
The technology, dubbed Epiness, can help sufferers prevent episodes by letting them know they should take medication before the seizure happens. Since as many as 30 percent of epilepsy patients do not respond to medications, the device could also provide enough time to take precautions to eliminate the risks of related injuries before the onset of a seizure.
“Epiness [is] a new, first of its kind device for detecting and predicting epileptic seizures based on proprietary machine-learning algorithms,” the scientists claim.
IEEE Spectrum reported last year that researchers at the University of Louisiana came up with a similar AI design with nearly the same accuracy (99.6 percent) and speed (one hour notice). However, it was not a wearable device, only a set of algorithms.
BGU already has the gears in motion for commercializing Epiness. A new university-held startup called NeuroHelp licensed the technology for further commercial development.
“Since we have also shown that our algorithms enable a significant reduction in the number of necessary EEG electrodes, the device we are developing is both accurate and user friendly,” said BGU’s Dr. Oren Shriki. “We are currently developing a prototype that will be assessed in clinical trials later this year.”
It is unclear what the final design will be, but it could be similar to the Nightwatch epilepsy armband worn on the upper arm rather than something worn on the head. Even further development could potentially lead to sensors built into a smartwatch.