Epilepsy is a neurological disorder that affects millions of people, regardless of age, but has yet to discover why it happens and how to effectively stop it. So far, most epilepsy patients manage their seizures with prescription drugs or by using cannabis.
While scientists continue to study minibrains in order to understand the origins of epilepsy and other neurological disorders, however, a team of engineering students from Rice University developed an algorithm that could effectively predict an oncoming seizure and prevent it through neurostimulation.
Ictal Inhibitor Project Algorithm
The Ictal Inhibitor project's goal is to replace invasive methods of treating epilepsy so they focused on developing a machine learning algorithm that could successfully predict oncoming seizures in real time.
"About one-third of the 3 million epilepsy patients in the United States don't respond to anti-seizure medications. The only option left for those patients is to undergo surgery to remove the part of the brain that is the issue; we hope to replace that option with something a lot less invasive," Erik Biegert, a graduating member of Team Ictal Inhibitor, said.
The team tested the algorithm afterwards using data sets from real intracranial patient seizure data supplied by renowned neurosurgeon and project co-investigator, Dr. Nitin Tandon.
After running the algorithm and testing it on the data sets, the group found that the program was able to predict oncoming seizures at least two minutes prior, though it also produced 3.9 false positive results per hour.
Ictal Inhibitor Hardware Testing
After getting favorable results from their algorithm, the team hooked up the program to custom-made hardware, which includes electrodes implanted in the brain.
"Using the electrical signals that are produced in the brain, we can predict if a seizure is going to occur in the next five minutes or so," Sarah Hooper, a senior electrical engineering major explained.
Hooper further explained that, using their group's program, the electrodes keep track of brain activity as the program runs and, if a seizure were about to occur, the hardware would communicate with the electrode to apply electrical neurostimulation and prevent the attack from happening.
The Next Step
The project is still using a huge computer board as its hardware but the team claims the project will continue and may work on transforming the hardware into a small, wireless chip that can be implanted in the brain.
"What we really focused on this year was to create the processing unit and all of the machine learning intelligence that can make this happen ... [The] next steps could be to flesh out the design and move it onto a silicon chip," Randy Zhang, also a senior electrical engineering major, explained.
Professor Behnaam Aazhang, team Ictal Inhibitor's faculty adviser, said that the project is still a work in progress and is still five to seven years away from an actual product.
The Ictal Inhibitor is a project borne from discussions between Professor Aazhang and Dr. Tandon from the University of Texas Health Science Center at Houston. It is a part of Rice University's Vertically Integrated Projects or VIP program, which brings together underclassmen, seniors, and graduate students to work on a project, and is funded by the National Science Foundation.
Watch Team Ictal Inhibitor explain their project below.
