Researchers say they can predict epileptic seizures an hour in advance
Their wearable device uses machine learning algorithms to analyze EEG signals.
Researchers from Ben-Gurion University of the Negev in Israel have developed a wearable electroencephalogram (EEG) device they claim can predict epileptic seizures up to an hour before the onset. Epiness uses machine learning algorithms to analyze brain activity and detect potential seizures, and it can send a warning to a connected smartphone.
Other devices on the market can detect seizures in real-time, but can’t give advance warnings. However, researchers from the University of Louisiana at Lafayette last year unveiled an AI prediction model of their own. That was said to offer a similar level of prediction accuracy to Epiness, and it can also alert patients up to an hour in advance of a seizure taking hold.
Sufficient warnings could afford patients time to prepare for the onset of a seizure by taking medication. Those who don’t respond well enough to anti-epileptic drugs would also have the chance to minimize the risk of seizure-related injuries.
Epiness, according to the BGU researchers, minimizes the number of EEG electrodes that a wearer would need to use. They developed and tested algorithms using EEG data from epilepsy patients who were monitored for several days before surgery. The algorithm with the best prediction performance was 97 percent accurate, and it kept almost the same level of performance (95 percent) with fewer electrodes.
It’ll probably be some time yet before the device is available to epilepsy patients. A new startup called NeuroHelp has licensed the Epiness tech for further development and commercialization. Clinical trials for a prototype are scheduled for later this year.
