A new algorithm has been developed by big data experts, which could be instrumental in helping to predict epileptic seizures.Computer scientists and mathematicians at the CEU Cardenal Herrera University, in Valencia, created the prediction model as part of the American Epilepsy Society’s Seizure Prediction Challenge in 2014, and they came third place out of 502 submissions.Further analysis of the model, published in the medical journal Brain, has underlined the potential benefits it offers. The team created the algorithm by assessing a large data set of intracranial EEG recordings taken from people and dogs with epilepsy.The algorithm is able to interpret the relevant data and find the specific brain signals that indicate a seizure is about to occur, potentially making it possible to predict incidents up to 20 minutes before they actually happen.It is hoped that the algorithm could ultimately be incorporated into a portable device, such as a mobile phone or a smartwatch. The device would read signals sent from a microchip implanted in the brain and warn the user of upcoming seizures, allowing the person to find a place of safety to avoid injury.If this is indeed feasible, it would help enormously in reducing the daily restrictions placed on people with epilepsy. It has also been suggested that this approach may, one day, allow for medication to only be needed at the time of a seizure rather than every day, decreasing the risk of adverse side effects.Juan Pardo, Director of the Department of Physical Sciences, Mathematics and Computing at CEU Cardenal Herrera University, said: “We are not doctors, but we are experts in massive data processing. This work shows how computer scientists and mathematicians are needed in many fields to help solve pressing issues, in this instance in neuroscience.”Click here to read more stories about living with epilepsy.
2019-10-26T22:48:39+01:00May 18th, 2016|