Researchers at Ben-Gurion University develop a device that predicts epileptic seizures
The system is based on machine learning algorithms and can predict a seizure up to an hour before one is due
The device, called Epiness, uses machine learning algorithms to detect and predict upcoming seizures, sending a warning message directly to the user’s smartphone. It does this by monitoring EEG-based brain activity which causes epileptic fits, while filtering noise that is not related to such a risk.
"Epileptic seizures expose epilepsy patients to various preventable hazards, including falls, burns and other injuries," said Dr. Oren Shriki, the Department of Cognitive and Brain Sciences at BGU and NeuroHelp's scientific founder. "Unfortunately, currently there are no seizure-predicting devices that can alert patients and allow them to prepare for upcoming seizures. We are therefore very excited that the machine-learning algorithms that we developed enable accurate prediction of impending seizures up to one hour prior to their occurrence.”
According to Dr. Shriki, NeuroHelp is already developing a prototype that will be assessed in clinical trials later this year. The algorithm has reached a 97% accuracy rate and is expected to help meet some of the unmet medical needs in identifying upcoming onsets.
Epilepsy is a chronic non-communicable disease that affects more than 65 million around the world. It is mostly characterized by seizures which can lead to loss of consciousness. They vary in frequency and can occur up to several times a day in severe cases.
BGN Technologies is the technology transfer company of Ben-Gurion University. To date, it has established more than 100 startups pertaining to biotech, hi-tech, and cleantech. Over the last 10 years, BNG Technologie has created long term partnerships such as PayPal, Deutsche Telekom, and Dell-EMC.