Harnessing artificial intelligence to control drug-resistant epilepsy

December 4, 2018, University of Montreal
Credit: Amélie Philibert

Epilepsy affects nearly one percent of the global population, making it one of the most common neurological disorders. While two-thirds of patients with epilepsy respond well to pharmacological treatment or are eligible for resective surgery, a significant proportion of epilepsy patients unfortunately continue to suffer from chronic, debilitating and unpredictable seizures.

Epileptic seizures can have consequences that include falls, injuries, fractures, insufficient blood flow to the brain, and in some cases even death. To minimize these risks, rapid intervention is essential. However, such interventions rarely occur in hospital settings or at home because patients often suffer seizures when they are alone, making it hard for medical staff or caregivers to detect them.

Microelectronics and AI

Thanks to major advances in computational capacities and data processing power in recent years, is poised to play a vital role in every area of future medicine.

The application of these advances in the healthcare sector has made it easier to formulate accurate diagnoses and offer customized treatment to patients while at the same time improving the overall quality of healthcare.

Over the past decade, our group has drawn on advances in microelectronics and artificial intelligence to explore several avenues in an effort to solve problems related to predicting, diagnosing and treating epilepsy. We initially focused on designing microsystems that could be implanted in the skull to continuously record , coupled with an algorithm capable of predicting seizures.

This approach made it possible to provide seizure alarms to patients, parents, caregivers or in order to trigger or even the automatic administration of local therapy aimed at blocking progression of the seizure.

Using algorithms to predict

More recently, we were able to show that it is possible to predict seizures using algorithms that tap into artificial intelligence techniques to monitor brain activity well in advance of their onset, much in same way that meteorologists are able to predict the next day's weather.

We also recently partnered with industry stakeholders to design smart apparel capable of early detection of seizures in a way that is non-invasive and discreet (without the need for electrodes on the head or inside the brain).

Since patients often manifest uncontrollable movements, abnormal noises, increased heart rate and rapid breathing when suffering a seizure, we believe it is possible to predict the onset of seizures using AI techniques based on physiological signs other than , such as , respiratory frequency, electrodermal activity, motor activity and sounds. These signs would be provided by miniature captors integrated into comfortably designed "smart" apparel.

Explore further: Some types of epilepsy pose more risks during pregnancy

Related Stories

Some types of epilepsy pose more risks during pregnancy

December 3, 2018
(HealthDay)—Women with frontal lobe epilepsy are much more likely to have an increase in seizures during pregnancy than those with focal epilepsy or generalized epilepsy, researchers report.

Crowdsourcing algorithms to predict epileptic seizures

August 9, 2018
A study by University of Melbourne researchers reveals clinically relevant epileptic seizure prediction is possible in a wider range of patients than previously thought, thanks to the crowdsourcing of more than 10 000 algorithms ...

Whole-brain connectome maps teach artificial intelligence to predict epilepsy outcomes

October 2, 2018
Medical University of South Carolina (MUSC) neurologists have developed a new method based on artificial intelligence that may eventually help both patients and doctors weigh the pros and cons of using brain surgery to treat ...

Non-epileptic seizure patients getting 'lost in system'

September 24, 2018
About 2,000 patients in Saskatchewan and 72,000 across Canada experience seizure-like episodes unrelated to epilepsy, but nearly half aren't receiving followup care, harming their quality of life and driving up health-care ...

Using network science to help pinpoint source of seizures

December 17, 2015
The ability to reliably pinpoint the anatomical source of epileptic seizures, different for each patient, remains elusive. One third of patients do not respond to medication and an alternative can be surgery to locate and ...

Brain implant could stop epilepsy seizures

August 30, 2018
For many people who suffer from neurological disorders, such as epilepsy, there are no viable treatment options. In our latest research, we developed an implantable device that may one day offer relief. We show that the implant ...

Recommended for you

The importins of anxiety

December 11, 2018
According to some estimates, up to one in three people around the world may experience severe anxiety in their lifetime. In a study described today in Cell Reports, researchers at the Weizmann Institute of Science have revealed ...

Neurons in the brain work as a team to guide movement of arms, hands

December 11, 2018
The apparent simplicity of picking up a cup of coffee or turning a doorknob belies the complex sequence of calculations and processes that the brain must undergo to identify the location of an item in space, move the arm ...

How returning to a prior context briefly heightens memory recall

December 11, 2018
Whether it's the pleasant experience of returning to one's childhood home over the holidays or the unease of revisiting a site that proved unpleasant, we often find that when we return to a context where an episode first ...

The richer the reward, the faster you'll likely move to reach it, study shows

December 11, 2018
If you are wondering how long you personally are willing to stand in line to buy that hot new holiday gift, scientists at Johns Hopkins Medicine say the answer may be found in the biological rules governing how animals typically ...

Using neurofeedback to prevent PTSD in soldiers

December 11, 2018
A team of researchers from Israel, the U.S. and the U.K. has found that using neurofeedback could prevent soldiers from experiencing PTSD after engaging in emotionally difficult situations. In their paper published in the ...

Study: Age, race differences determine risk of stroke in women and men

December 11, 2018
A new study found that, between the ages of 45 and 74 years, white women were less likely to have a stroke than white men, but at age 75 and older, there was no difference in stroke risk between white women and men. In contrast, ...


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.