Epileptic seizures can be predicted through researchers' software

Two University of Windsor professors in Ontario have designed software they say predicts an epileptic seizure 17 minutes before it happens, and researchers believe it can potentially be applied to many other events, such as predicting heart attacks, earthquakes and the onset of Alzheimer's disease.

2 University of Windsor profs say it can predict an epileptic seizure 17 minutes in advance

University of Windsor researcher Robin Gras says a device that can constantly monitor a patient’s brain activity is needed to pair with his software. (University of Windsor)

Two University of Windsor professors have designed software they say can predict an epileptic 17 minutes before it happens.

“Up until now, the best prediction was a few minutes ahead and had an accuracy of 50 to 60 per cent,” Prof. Robin Gras said in a post on the University of Windsor's website. “We got 17 minutes with 100 per cent accuracy."

Gras and Abbas Golestanti, a PhD student in the School of Computer Science, analyzed the brain’s electrical activity, specifically the electroencephalography (EEG) readings of patients.

Thirty minutes of readings plugged into the software is enough data to give someone with epilepsy 17 minutes of advance warning of a seizure.

The researchers based their findings on data from 21 epileptic patients.

Their test results were published in Scientific Reports in October.

Gras and Golestanti have patented the software, and now need a device that can constantly monitor a patient’s EEG.

“If you have this device on you all the time, it reads your EEG values and 17 minutes in advance it can ring and say: You will have trouble in 17 minutes. Stop your car. Go to a safe place. Phone someone to help you,” Gras said.

Gras said the method is "innovative" and based on chaos theory, which allows people to make long- term predictions of the evolution of complex systems.

The pair originally developed the software to predict the next financial crisis. They've also analyzed 100 years of climate data and evaluated the next 30 years for climate change.

"We used financial time series, medical time series and climate time series to evaluate our method," reads the pair's research in Scientific Reports. "The results we obtained show that the long-term prediction of complex nonlinear time series is no longer unrealistic."

Gras believes their method can potentially be applied to many other events, such as predicting heart attacks, earthquakes and the onset of Alzheimer's disease.

Comments

To encourage thoughtful and respectful conversations, first and last names will appear with each submission to CBC/Radio-Canada's online communities (except in children and youth-oriented communities). Pseudonyms will no longer be permitted.

By submitting a comment, you accept that CBC has the right to reproduce and publish that comment in whole or in part, in any manner CBC chooses. Please note that CBC does not endorse the opinions expressed in comments. Comments on this story are moderated according to our Submission Guidelines. Comments are welcome while open. We reserve the right to close comments at any time.