Prediction method for epileptic seizures developed

May 30, 2018, University of Sydney
Dr. Omid Kavehei from the Faculty of Engineering and Sydney Nano Institute at the University of Sydney. Credit: University of Sydney

Epileptic seizures strike with little warning and nearly one third of people living with epilepsy are resistant to treatment that controls these attacks. More than 65 million people worldwide are living with epilepsy.

Now researchers at the University of Sydney have used advanced artificial intelligence and machine learning to develop a generalised method to predict when seizures will strike that will not require .

Dr. Omid Kavehei from the Faculty of Engineering and IT and the University of Sydney Nano Institute said: "We are on track to develop an affordable, portable and non-surgical device that will give reliable prediction of seizures for people living with treatment-resistant ."

In a paper published this month in Neural Networks, Dr. Kavehei and his team have proposed a generalised, patient-specific, seizure-prediction method that can alert epilepsy sufferers within 30 minutes of the likelihood of a seizure.

Dr. Kavehei said there had been remarkable advances in as well as micro- and nano-electronics that have allowed the development of such systems.

"Just four years ago, you couldn't process sophisticated AI through small electronic chips. Now it is completely accessible. In five years, the possibilities will be enormous," Dr. Kavehei said.

The study uses three data sets from Europe and the United States. Using that data, the team has developed a predictive algorithm with sensitivity of up to 81.4 percent and false prediction rate as low as 0.06 an hour.

"While this still leaves some uncertainty, we expect that as our access to seizure data increases, our sensitivity rates will improve," Dr. Kavehei said.

Carol Ireland, chief executive of Epilepsy Action Australia, said: "Living with constant uncertainty significantly contributes to increased anxiety in people with epilepsy and their families, never knowing when the next seizure may occur.

"Even people with well controlled epilepsy have expressed their constant concern, not knowing if or when they will experience a seizure at work, school, travelling or out with friends.

"Any progress toward reliable seizure prediction will significantly impact the quality of life and freedom of choice for people living with epilepsy."

Dr. Kavehei and lead author of the study, Nhan Duy Truong, used deep machine learning and data-mining techniques to develop a dynamic analytical tool that can read a patient's electroencephalogram, or EEG, data from a wearable cap or other portable device to gather EEG data.

Wearable technology could be attached to an affordable device based on the readily available Raspberry Pi technology that could give a patient a 30-minute warning and percentage likelihood of a seizure.

An alarm would be triggered between 30 and five minutes before a seizure onset, giving patients time to find a safe place, reduce stress or initiate an intervention strategy to prevent or control the seizure.

Dr. Kavehei said an advantage of their system is that is unlikely to require regulatory approval, and could easily work with existing implanted systems or medical treatments.

The algorithm that Dr. Kavehei and team have developed can generate optimised features for each patient. They do this using what is known as a 'convolutional neural network', that is highly attuned to noticing changes in brain activity based on EEG readings.

Other technologies being developed typically require surgical implants or rely on high levels of feature engineering for each patient. Such engineering requires an expert to develop optimised features for each prediction task.

An advantage of Dr. Kavehei's methodology is that the system learns as brain patterns change, requiring minimum feature engineering. This allows for faster and more frequent updates of the information, giving patients maximum benefit from the seizure prediction algorithm.

The next step for the team is to apply the across much larger data sets of information, improving sensitivity. They are also planning to develop a physical prototype to test the system clinically with partners at the University of Sydney's Westmead medical campus.

Explore further: Too few adults taking epilepsy meds have seizure control

More information: Nhan Duy Truong et al, Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram, Neural Networks (2018). DOI: 10.1016/j.neunet.2018.04.018

Related Stories

Too few adults taking epilepsy meds have seizure control

April 23, 2018
(HealthDay)—Although most adults with epilepsy report taking epilepsy medication, less than half of those report having their seizures controlled, according to research published in the April 20 issue of the U.S. Centers ...

Personalised epilepsy seizure prediction a possibility with AI

December 5, 2017
The idea of personalised seizure prediction for epilepsy is closer to becoming a reality thanks to new research published today by the University of Melbourne and IBM Research-Australia.

Team develops method to identify seizure-causing regions in the brain

January 11, 2018
Epilepsy—a condition that affects an estimated 65 million people worldwide—can be a difficult condition to treat. A team at the University of Illinois at Urbana-Champaign and Mayo Clinic have developed a method with the ...

Getting to grips with seizure prediction

November 7, 2013
A device that could predict when a person with epilepsy might next have a seizure is one step closer to reality thanks to the development of software by researchers in the USA. Details are to be published in a forthcoming ...

Cannabis compound reduces seizures

February 27, 2018
About one third of patients treated for epilepsy continue to have seizures. Cannabidiol (CBD), one of the many active compounds in the cannabis (marijuana) plant, has gained attention as a treatment for epilepsy. Purified ...

Algorithms that can predict epileptic seizures

May 11, 2016
Computer scientists and mathematicians at the CEU Cardenal Herrera University in Valencia have developed a prediction model that can warn epileptic sufferers of an upcoming seizure with 20 minutes notice.

Recommended for you

Protein droplets keep neurons at the ready and immune system in balance

August 15, 2018
Inside cells, where DNA is packed tightly in the nucleus and rigid proteins keep intricate transport systems on track, some molecules have a simpler way of establishing order. They can self-organize, find one another in crowded ...

Self-control develops gradually in adolescent brain

August 15, 2018
Different parts of the brain mature at different times, which may help to explain impulsive behaviors in adolescence, suggest researchers from Penn State and the University of Pittsburgh.

Research reveals that what we see is not always what we get

August 15, 2018
Researchers are helping to explain why some people anticipate and react to fast-moving objects much quicker than others.

New approach to treating chronic itch

August 15, 2018
Researchers at the University of Zurich have discovered a new approach to suppressing itch by targeting two receptors in the spinal cord with the right experimental drug. In a series of experiments in mice and dogs, they ...

Immune cells in the brain have surprising influence on sexual behavior

August 14, 2018
Researchers have found a surprising new explanation of how young brains are shaped for sexual behavior later in life.

Scientists pinpoint brain networks responsible for naming objects

August 14, 2018
Scientists at The University of Texas Health Science Center at Houston (UTHealth) have identified the brain networks that allow you to think of an object name and then verbalize that thought. The study appeared in the July ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.