Ben Gurion University’s portable device could make a difference for epileptics
The Epiness system, based on automatic learning algorithms and EEG-based monitoring of brain activity, can predict upcoming seizures up to an hour before they begin.
A breakthrough for epileptic patients?
Researchers at the Ben-Gurion University of the Negev have developed a device to detect and predict epileptic seizures.
The portable Epiness device, whose technology is based on automatic learning algorithms and EEG-based monitoring of brain activity, can generate an advanced warning for an upcoming seizure that will be sent to a user’s smartphone up to an hour before it occurs.
Algorithms are designed to filter out noise that is not related to brain activity, extract informative measures of underlying brain dynamics, and distinguish between brain activity before an expected seizure and brain activity when a seizure is not expected to occur.
Up to 30% of epileptic patients do not respond adequately to antiepileptic drugs.
For these patients, a viable seizure prediction device could offer a substantial improvement in quality of life, enabling them to avoid seizure-related injuries. Current crisis alarm devices can detect a crisis in real time, but are not able to provide early warnings of impending crises.
The system has licensed its development and commercialization to NeuroHelp, a company that was recently founded by BGN Technologies, BGU’s technology transfer company, and Dr. Oren Shriki of BGU’s Department of Cognitive and Brain Sciences, who is also NeuroHelp’s scientific founder.
“Seizures expose epilepsy patients to a variety of preventable risks, including falls, burns and other injuries,” Shriki said.
“Unfortunately, there is currently no crisis prediction system in place that can alert patients and enable them to prepare for future crises. We are therefore very pleased that the machine learning algorithms we have developed allow for accurate prediction of impending seizures up to an hour in advance.
As we have also shown that our algorithms allow a significant reduction in the number of EEG electrodes required, the device we develop is both accurate and user-friendly. We are currently developing a prototype that will be evaluated in clinical trials at a later date. “added Shikri.
Source: Alliance Mag
Be the first to comment