Personalised epilepsy seizure prediction a possibility with AI

December 5, 2017 by Holly Bennett, University of Melbourne
Using the world’s most comprehensive epilepsy patient EEG dataset collected from electrodes inside patients’ skulls, Professor David Grayden, Head of the University’s Department of Biomedical Engineering, said the technology has the ability to adapt to individual patient’s needs. Credit: Pixabay

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.

Using the power of artificial intelligence (AI) technology, researchers have used a mobile, brain-inspired processor to analyse brain signals from retrospective patient data recorded under the skull, successfully predicting an average of 69 per cent of seizures across all patients.

A third of patients worldwide currently living with unpredictable seizures that are not adequately controlled through medication or otherwise. Professor Mark Cook, Director of the University's Graeme Clark Institute for Biomedical Engineering and Director of Neurology at St Vincent's Hospital Melbourne said this research could dramatically improve the lives of 250,000 Australians and 65 million people worldwide.

"Epilepsy is a neurologic condition that can be incredibly debilitating," said Professor Cook.

"It prevents some patients from doing simple activities such as getting a driver's license or swimming.

"This technology has the potential to improve millions of lives and reduce the physical, emotional, and financial costs of one of the world's most common, yet intractable chronic disorders."

Using the world's most comprehensive epilepsy patient EEG dataset collected from electrodes inside patients' skulls, Professor David Grayden, Head of the University's Department of Biomedical Engineering, said the technology has the ability to adapt to individual patient's needs.

"By collecting data from inside the patient's skull and combining this with deep learning and AI, we're able to develop a system that can self-train, based on learning the brain states and signs that pre-empt seizures unique to an individual," said Professor Grayden.

"Our algorithm also allows for instantaneous and easy adjustment, giving patients the flexibility to control how sensitive and in advance the warning is."

While previous epilepsy prediction research has only been possible on high powered computers, Dr Stefan Harrer, IBM Research-Australia's Brain-Inspired Computing Manager, said that by using IBM's brain-inspired computing chip, there is the potential to create a wearable, real-time patient warning system.

"By deploying the technology on a computing chip that is the size of a postage stamp and runs on the same power use of a hearing aid, we're able to simulate how such systems could one day operate in real life," Dr Harrer said.

"The hope is that one day this research could help inform the development of assistive technologies that could not only warn people with epilepsy of imminent seizures, but constantly adapt to how their brains change over time."

Professor Cook said developing a reliable means of predicting epileptic seizures for individual was an incredibly complex area of research.

"This is in large part due to how epilepsy manifests itself uniquely in each patient, as well as individual long-term changes in ," said Professor Cook.

"While we still need to continue to build on this research before we can confidently say that we can identify any before it occurs, these results have proven incredibly promising."

Explore further: World-first study predicts epilepsy seizures in humans

Related Stories

World-first study predicts epilepsy seizures in humans

May 2, 2013
A small device implanted in the brain has accurately predicted epilepsy seizures in humans in a world-first study led by Professor Mark Cook, Chair of Medicine at the University of Melbourne and Director of Neurology at St ...

Wristband devices detect dangerous seizures in patients with epilepsy

October 30, 2017
New research published in Epilepsia, a journal of the International League Against Epilepsy (ILAE), indicates that wristband devices may improve the detection and characterization of seizures in patients with epilepsy.

Treatments available for drug-resistant epilepsy

August 22, 2016
One in 26 people will develop epilepsy – a chronic disease characterized by unpredictable seizures—in their lifetime.

New method identifies brain regions most likely to cause epilepsy seizures

August 17, 2017
Scientists have developed a new way to detect which areas of the brain contribute most greatly to epilepsy seizures, according to a PLOS Computational Biology study. The strategy, devised by Marinho Lopes of the University ...

Robot reduces need for open brain surgery to map epileptic seizures

January 23, 2017
A minimally invasive robotic device is eliminating the need for some patients to undergo open brain surgery to pinpoint the origin of their epileptic seizures. The device, in use at Duke and a small handful of epilepsy centers ...

Study sheds light on safety of driving with epilepsy

December 5, 2016
(HealthDay)—People with epilepsy who experienced longer seizures during a simulated driving test may face an increased risk for crashes while on the road, a new study suggests.

Recommended for you

When the eyes move, the eardrums move, too

January 23, 2018
Simply moving the eyes triggers the eardrums to move too, says a new study by Duke University neuroscientists.

Cognitive training helps regain a younger-working brain

January 23, 2018
Relentless cognitive decline as we age is worrisome, and it is widely thought to be an unavoidable negative aspect of normal aging. Researchers at the Center for BrainHealth at The University of Texas at Dallas, however, ...

Lifting the veil on 'valence,' brain study reveals roots of desire, dislike

January 23, 2018
The amygdala is a tiny hub of emotions where in 2016 a team led by MIT neuroscientist Kay Tye found specific populations of neurons that assign good or bad feelings, or "valence," to experience. Learning to associate pleasure ...

Your brain responses to music reveal if you're a musician or not

January 23, 2018
How your brain responds to music listening can reveal whether you have received musical training, according to new Nordic research conducted in Finland (University of Jyväskylä and AMI Center) and Denmark (Aarhus University).

New neuron-like cells allow investigation into synthesis of vital cellular components

January 22, 2018
Neuron-like cells created from a readily available cell line have allowed researchers to investigate how the human brain makes a metabolic building block essential for the survival of all living organisms. A team led by researchers ...

Finding unravels nature of cognitive inflexibility in fragile X syndrome

January 22, 2018
Mice with the genetic defect that causes fragile X syndrome (FXS) learn and remember normally, but show an inability to learn new information that contradicts what they initially learned, shows a new study by a team of neuroscientists. ...

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.