Research aims to develop a cap which can predict seizures

Posted Jul 11 2018 in Epilepsy general / Living with epilepsy

A team led by Dr Omid Kavehei of Sydney University’s Faculty of Engineering and IT has developed a non-surgical device using artificial intelligence and machine learning to develop a cap which can read a patient’s brain activity and warn the wearer if a seizure is on its way.

For many people with epilepsy the unpredictability of a seizure causes a great deal of stress and anxiety and for those whose epilepsy is poorly controlled there is always the worry that a seizure may lead to injury.

Researchers from the University of Sydney are working on developing a cap which aims to predict with 80 per cent accuracy whether a person will have an epileptic seizure in the next 30 minutes.
The cap, which is in the early stages of development reads the brain signals from the patient’s head and can trigger an alarm between 5 and 30 minutes before a seizure occurs so that the patient has enough time to make themselves safe and so helps to reduce the potential for stress and anxiety.

As Dr Kavehei says “People think that seizures are random, but there must be some pattern in the immediate time before the seizure takes place …… Artificial intelligence is good in detecting hidden patterns in data. There are patterns that we may not be able to detect with conventional techniques.”

To read more about this research, please click here

News categories