Researchers have developed an artificial intelligence system that is able to predict epileptic seizures with 99.6 percent accuracy.
The system was created by researchers at the University of Louisiana. It can detect seizures up to an hour before they occur, which would allow people to prepare for them by taking medication.
Over 50 million people in the world suffer from epilepsy, according to the World Health Organization. Since 70 percent of those patients use medication to control their seizures, researchers say that a prediction system like this would be a great asset.
Current detection models analyze brain activity and then apply a predictive model afterwards. However, this new AI system is able to do both of those things at the same time through a deep learning algorithm.
Although this technique is not ready for widespread use, it could be life-changing for many patients with epilepsy.
The use of artificial intelligence in healthcare is increasing, as Microsoft recently developed an AI system that is able to detect cervical cancer.