Prediction method for epileptic seizures developed - (ScienceDaily via NewsPoints Desk)

  • A study published in Neural Networks suggests that advanced artificial intelligence and machine learning have been used to develop a generalised, patient-specific seizure-prediction method that can alert patients with epilepsy within 30 minutes of the likelihood of a seizure, ScienceDaily reported.

  • Study author Omid Kavehei said that "we are on track to develop an affordable, portable and non-surgical device that will give reliable prediction of seizures for people living with treatment-resistant epilepsy."

  • The researchers used deep machine learning and data-mining techniques to develop a dynamic analytical tool that can read a patient's electroencephalogram data from a wearable cap or other portable device.

  • Meanwhile, three data sets were used to develop a predictive algorithm with sensitivity of up to 81.4 percent and a false prediction rate as low as 0.06 an hour.

  • "While this still leaves some uncertainty, we expect that as our access to seizure data increases, our sensitivity rates will improve," Kavehei said, adding that an advantage of the system is that is unlikely to require regulatory approval, and could easily work with existing implanted systems or medical treatments.

  • The next step for the researchers is to apply the neural networks across much larger data sets, to improve sensitivity, and to develop a physical prototype to test clinically.

Did you like this article?

Reference Articles