New Mathematical Model Could be the Key to Early-warning for Seizures

A research team at the University of Southern California is currently working on a powerful new seizure prediction model which could vastly improve the ability to predict seizure activity. 

Using this new model, it is noted that people with epilepsy could be warned from 5 minutes up to an hour before they are likely to experience a seizure. This could offer millions of people who have epilepsy enhanced freedom and confidence if it is found to be as effective as initial results show. 

For many with epilepsy, a seizure can feel very much like a ticking time bomb, and often it’s this that severely limits the quality of life they can enjoy. The expectation of a seizure can prevent people with epilepsy from taking part in many activities they would otherwise enjoy. 

This new mathematical model works by learning from an exponential amount of brain signal data that has been collected via an electrical implant in the patient. The implant collects data over a large period of time in order to create a unique formula that learns each person’s unique brain signals and searches out precursors or patterns to identify the likelihood seizure activity. This new model is shown to offer accurate prediction within an hour, giving the person time to take the necessary precautions. 

Mathematical models aren’t new in the world of epilepsy with many already existing. Where this one differs is that it utilises linear and non-linear data collected over a much larger timescale and is unique to each individual person who undertakes the research. 

“Linear is the simple feature. If you understand the parts, you can understand the whole,” Song said. “Whereas the non-linear feature means that even if you understand the parts, when you scale up it has some emergent properties that cannot be explained.”

“For some patients, linear features are more important and for other patients, non-linear features are more important,” said by research author Dong Song, USC. 

Currently research must be carried out in a hospital environment, which only offers a small amount of data in a single setting. This new research can monitor over a much longer timescale and collect data in a variety of scenarios as the person goes about their day to day life. 

Song continued by saying: “So we need to create a new workflow by which, instead of bringing patients to the ICU, we take the recordings from their home and use the computation models to do everything they would have done in the hospital,” Liu said. “Not only can you manage patients using physical distancing, you can also scale in a way that only technology allows. Computation can analyze thousands of pages of data at once, whereas a single neurologist cannot.”

Of course, this is still in the research phase, but theoretically could be rolled out on a person by person basis to offer those with epilepsy that can not be controlled by AEDs more freedom over their lives and more certainty as to when they may experience a seizure. 

You can read the full article from Science Daily here.