For individuals who have epilepsy and related disorders, seizure prediction is important. Although seizure medication is available, it is important for people to know in advance when a seizure will take place, so that patients can live a safe and normal life. Consider individuals who drive vehicles and operate hazardous machinery. A seizure can occur at any time, putting the patient and others in harms way.
According to Shouyi Wang of the Department of Industrial and Manufacturing Systems Engineering, at University of Texas at Arlington; Wanpracha Art Chaovalitwongse of the University of Washington, Seattle; and Stephen Wong of the University of Medicine and Dentistry of New Jersey, in New Brunswick, current seizure prediction algorithms require previous information on a patient’s pre-seizure electroencephalogram (EEG) behavior. Unfortunately, these algorithms are impractical because pre-seizure EEGs are not always available in the number required.
The researchers have developed software that has the ability to learn about a patient’s normal and seizure activity from long-term EEG readings. The algorithms learning capability allows prediction for the next seizure episode. In the near future, a portable medical device that has discrete electrodes that can be worn under a cap would make use of this algorithm to worn a patient of an upcoming seizure. If the patient is driving, this would allow them to pull over into a safe environment.
Researchers note, “Our experimental results showed that the adaptive prediction scheme could achieve a consistent better prediction performance than a chance model and the non-updating system. 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.”