Israeli researchers have developed a prototype of a wearable device that predicts epileptic seizures based on machine-learning algorithms, and generates an advance warning of an upcoming seizure an hour before onset.

Epiness, a first-of-its-kind device, was developed by researchers at Ben-Gurion University of the Negev. It has been licensed out for further development and commercialization to NeuroHelp, a startup company founded by BGU’s technology transfer company BGN Technologies and Dr. Oren Shriki from the university’s Brain and Cognitive Science department, who serves as its scientific founder. Clinical trials are planned later this year.

Epilepsy is a chronic disease of the brain that affects around 65 million people worldwide and is characterized by recurrent seizures resulting from excessive electrical discharges in a group of brain cells.

Up to 30 percent of epilepsy patients don’t adequately respond to anti-epileptic drugs, meaning that they live in fear of impending seizures. For such patients, a prediction device could offer improvement in quality of live and enable them to avoid seizure-related injuries.

97% accuracy

Epiness is based on a combination of EEG-based monitoring of brain activity and machine-learning algorithms. It is comprised of a wearable EEG device and software that minimizes the number of necessary EEG electrodes and optimizes electrode placement on the scalp.

Its machine-learning algorithms extract informative measures of underlying brain dynamics and distinguish between brain activity before an expected epileptic seizure and brain activity when a seizure is not expected to occur.

The algorithms were developed and tested using EEG data from a large dataset of people with epilepsy who were monitored for several days prior to surgery. The best prediction performance reached a 97% level of accuracy, with near-optimal performance maintained (95%) even with relatively few electrodes.

“Epileptic seizures expose epilepsy patients to various preventable hazards, including falls, burns and other injuries,” says Shriki.

“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.”

He added that the device being developed is both accurate and user friendly. “We are currently developing a prototype that will be assessed in clinical trials later this year.”

“Current seizure alert devices can detect seizures while they are happening, and most of them depend on changes in movement, such as muscle spasms or falls,” explained Dr. Hadar Ron, NeuroHelp’s chairperson.

“Epiness is unique in that it can predict an upcoming seizure and allow the patients and their caretakers to take precautionary actions and prevent injuries. It is also the only device that is based on brain activity rather than muscle movements or heart rate. We are confident that Epiness will be a valuable tool in the management of drug-resistant epilepsy.”