Imagine a “weather report for the brain” able to send out a warning via an implantable chip to an epileptic person a few hours or days before the onset of their seizure. A pipe dream, you think? Not for two researchers at the CHUM Research Centre (CRCHUM): Dr. Dang Khoa Nguyen, Canada Research Chair in Epilepsy and Functional Anatomy of the Brain, and Élie Bou Assi.

More than 50 million people worldwide have epilepsy, according to the World Health Organization. And nearly 20,000 Canadians are diagnosed with it every year. This neurological disorder, whose causes are varied, is characterized by recurrent, often disabling seizures, related to a temporary malfunction of the brain’s electrical activity.

Anti-seizure medications exist to prevent these “electrical storms” in the brain. But they are effective in only two thirds of patients.

For our two researchers, it is therefore essential to identify markers that will make it possible to predict seizures or at least to detect them as quickly as possible so that people have enough time to get to a safe place or get help from others.

A glimpse into their latest research work.

A Seizure Looming

“The goal of our seizure prediction work is to develop a sort of ‘weather report for the brain’ able to continuously provide forecasts and to warn the person a few hours or days prior to the onset of an epileptic seizure,” explained Dr. Nguyen, a neurologist at the CHUM and professor at the Université de Montréal.

In recent years, his research team has been able to develop algorithms to identify, in intracranial brain signal recordings, subtle changes (invisible to the naked eye) that are seizure precursors. Dr. Dang Khoa Nguyen and Élie Bou Assi are among the first in the world to explore the use of cross-frequency coupling in intracranial EEG recordings for predicting epileptic seizures.

The two researchers first tested the efficacy of their algorithms on EEG recordings of epileptic dogs (public, open-access databases) and then on recordings of patients with drug-resistant epilepsy.

The originality of their research work surely has something to do with their being awarded funding from the Canadian Institutes of Health Research in the latest Project Grant Program competition ($596,700 for 5 years). This funding will allow them to improve the performances of their algorithms, test them on a larger number of patients and with longer continuous recordings.

Facilitating the Work of the Algorithms

Continuously reducing the computational load before thinking about the “hardware” that would be implanted under the dome of the skull, in all likelihood a chip, is one of the major challenges that the two scientists are tackling.

To improve the performances of their algorithms based on intracranial signals, they are therefore considering introducing other clues such as the tendency to have seizures during menstruation or during sleep for some patients.

Another clue that the team is considering adding to reduce computational load is the epileptic “prodrome” reported by 15 to 20% of patients, who claim to be more tired, irritable and less focused hours before a seizure.

Detecting Seizures with Connected Objects

In addition to predicting seizures with implanted electrodes, the team is also working to detect seizures upon onset by using non-invasive connected objects such as watches, mattresses or smart apparel.

In a survey conducted in 2020 among 221 patients with epilepsy and 171 Canadian informal caregivers, in partnership with patient organizations (Épilepsie Québec and the Canadian Epilepsy Alliance), the vast majority said they were interested in these detection tools, which, in their opinion, could improve their quality of life and care quality.

“Consulting these people on aspects that were most important to them helped guide us in the development of our detection systems,” stated Université de Montréal professor Élie Bou Assi.

To successfully detect seizures, Dr. Dang Khoa Nguyen and Élie Bou Assi use non-invasive techniques to monitor physiological signals that suddenly “go cray” during seizures (e.g. movements, breathing, heart rate, muscle activity).

For example, they record breathing, movement and heart rate data by means of smart t-shirts (Hexoskin) supplied by their Montreal-based industry partner Carré Technologies, originally developed to monitor professional athletes. Patients also test connected bracelets, smart watches and even mattresses that continuously measure pressure over the entire surface of a bed.

“At the CHUM’s Epilepsy Monitoring Unit, nearly 300 seizures have already been recorded thanks to the Hexoskin connected t-shirt with over 60 hospitalized patients. Our team is exploring these recordings to develop algorithms capable of detecting epileptic seizures and generating alerts,” explained Bou Assi.

For Dr. Nguyen, “it’s clear that we’ll have to use more than one method to effectively detect epileptic seizures. Depending on the patients’ profiles and their activities, a combination of a watch, a t-shirt, a bracelet with an accelerometer or a pressure mattress will be necessary to ensure detection reliability.”

In the near future, the two researchers would like to monitor patients at home via connected objects and compare the results of automatic detection to observations recorded in patients’ seizure diaries.

A way of better understanding patients’ reality and reducing the risks of injuries and death related to epileptic seizures.