A step closer to seizure prediction
Researchers in America have developed a piece of software that might one day be used in the development of a seizure prediction device.
Approximately a third of people with epilepsy don’t respond to anti-epileptic drugs (AEDs) and they continue to experience recurrent seizures. The ability to predict an on-coming seizure would be life-transforming, and in some cases life-saving; and research to develop a seizure prediction device is ongoing. One of the challenges of seizure prediction is that it requires a lot of information about a person’s pre-seizure EEG patterns. This usually makes it impractical, because pre-seizure EEGs are rarely available in the appropriate quantity or detail.
A group of scientists from the University of Texas, the University of Washington and the University of Medicine and Dentistry of New Jersey has now developed a piece of software that can analyse a person’s normal and seizure electrical activity using long-term EEG recordings after diagnosis. This so-called ‘learning process’ then allows the software to predict when another seizure might occur based on patterns that it has detected.
The researchers believe that in the future a portable device that uses this software could potentially be developed. This could be worn under a cap or hat, and it would give the person an early warning of a seizure (allowing them to move to safety before the seizure began).
Dr Shouyi Wang, at the University of Texas, said “This study confirmed that the concept of using adaptive learning algorithms to improve the adaptability of seizure prediction is conceivable. If a seizure-warning device is ever to become a reality, adaptive learning techniques will play an important role.”
Although the development of a clinical device is still a long way off, this is very important progress. We look forward greatly to the next update from this group.